CA2472524A1 - Registration of separations - Google Patents

Registration of separations Download PDF

Info

Publication number
CA2472524A1
CA2472524A1 CA002472524A CA2472524A CA2472524A1 CA 2472524 A1 CA2472524 A1 CA 2472524A1 CA 002472524 A CA002472524 A CA 002472524A CA 2472524 A CA2472524 A CA 2472524A CA 2472524 A1 CA2472524 A1 CA 2472524A1
Authority
CA
Canada
Prior art keywords
image
area
areas
determining
alignment vector
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CA002472524A
Other languages
French (fr)
Other versions
CA2472524C (en
Inventor
Paul R. Klamer
Keren O. Perlmutter
Sharon M. Perlmutter
Eric Wang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Warner Bros Entertainment Inc
Historic AOL LLC
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Publication of CA2472524A1 publication Critical patent/CA2472524A1/en
Application granted granted Critical
Publication of CA2472524C publication Critical patent/CA2472524C/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/40—Scaling the whole image or part thereof
    • G06T3/403—Edge-driven scaling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/38—Registration of image sequences
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/40—Scaling the whole image or part thereof
    • G06T3/4084—Transform-based scaling, e.g. FFT domain scaling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/10—Image enhancement or restoration by non-spatial domain filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • G06T5/73—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/46—Colour picture communication systems
    • H04N1/56—Processing of colour picture signals
    • H04N1/58—Edge or detail enhancement; Noise or error suppression, e.g. colour misregistration correction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/10—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths
    • H04N23/13—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths with multiple sensors
    • H04N23/15—Image signal generation with circuitry for avoiding or correcting image misregistration
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/11—Scanning of colour motion picture films, e.g. for telecine
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20048—Transform domain processing
    • G06T2207/20064—Wavelet transform [DWT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details
    • G06T2207/20192—Edge enhancement; Edge preservation

Abstract

Separations or images relating to film or other fields may be registered using a variety of features, such as, for example: (1) correcting one or more film distortions; (2) automatically determining a transformation to reduce a film distortion; (3) applying multiple criteria of merit to a set of features to determine a set of features to use in determining a transformation; (4) determining transformations for areas in an image or a separation in a radial order; (5) comparing areas in images or separations by weighting feature pixels differently than non-feature pixels; (6) determining distortion values for transformations by applying a partial distortion measure and/or using a spiral search configuration; (7) determining transformations by using different sets of features to determine corresponding transformation parameters in an iterative manner; and (8) applying a feathering technique to neighboring areas within an image or separation.

Claims (91)

1.A method for automatic registration of film separations, the method comprising:
accessing component images that are based on digitized film separations, wherein each of the component images includes a set of gray-level pixels;
determining automatically an alignment vector for at least a part of a selected component image from among the accessed component images; and reducing one or more film distortions by applying the alignment vector to the part of the selected component image.
2. The method of claim 1 wherein the accessed component images are based on digitized color film separations.
3. The method of claim 1 wherein accessing component images comprises digitizing film separations.
4. The method of claim 1 wherein the alignment vector aligns the part of the selected component image with a corresponding part of a second of the accessed component images, the method further comprising combining the selected component image and the second of the accessed component images after applying the alignment vector.
5. The method of claim 1 further comprising selecting one of the accessed component images as a reference, wherein determining the alignment vector comprises determining an alignment vector between a part of the reference and the part of the selected component image.
6. The method of claim 5 wherein a green component image is selected as the reference.
7. The method of claim 5 further comprising determining an additional alignment vector between the part of the reference and a part of an additional one of the accessed component images.
8. The method of claim 5 wherein determining the alignment vector comprises:
determining a first set of features associated with the part of the reference;
determining a second set of features associated with the part of the selected component image;
comparing the first and second sets of features based on results obtained when applying one or more candidate alignment vectors; and determining the alignment vector based on results of the one or more comparisons.
9. The method of claim 8 wherein:
determining the first set of features comprises:
applying an edge detection filter to the part of the reference to generate a first preliminary set of edges, and applying an edge refinement procedure to the first preliminary set of edges to obtain the first set of features; and determining the second set of features comprises:
applying the edge detection filter to the part of the selected component image to generate a second preliminary set of edges, and applying the edge refinement procedure to the second preliminary set of edges to obtain the second set of features.
10. The method of claim 8 wherein comparing the sets of features based on results obtained when applying one or more candidate alignment vectors comprises:
assigning a non-zero amount of distortion to a pixel in a first of the accessed component images only if the pixel is part of a feature and if a pixel at a corresponding location in a second of the accessed component images is not part of a feature; and summing the distortion values obtained for a predefined set of pixels in an area being examined in the first component image.
11. The method of claim 10 wherein the first of the accessed component images is the selected component image.
12. The method of claim 9 wherein applying the edge refinement procedure comprises selecting edges based on a characteristic of at least one of the accessed component images.
13. The method of claim 12 wherein the characteristic comprises high intensity.
14. The method of claim 9 wherein applying the edge refinement procedure comprises:
identifying a connected edge within an area under consideration;
including the connected edge in a set of selected edges if the connected edge meets a first criterion of merit; and obtaining a set of features based on whether the entire set of selected edges satisfies a second criterion of merit.
15. The method of claim 14 wherein:
the connected edge meets the first criterion of merit if the connected edge has at least a predetermined amount of information in one direction, and the set of selected edges satisfies the second criterion of merit if the entire set of selected edges has at least a predetermined amount of information.
16. The method of claim 8 wherein comparing the sets of features based on results obtained when applying one or more candidate alignment vectors comprises:
selecting an initial candidate alignment vector; and varying the initial candidate alignment vector so as to represent multiple relative displacement possibilities within a particular proximity window of the initial candidate alignment vector.
17. The method of claim 16 wherein selecting the initial candidate alignment vector comprises:
determining a first set of features associated with a center part of the reference;
determining a second set of features associated with a center part of the selected component image;
comparing the first and second sets of features associated with the center parts of the reference and the selected component image; and selecting the initial candidate alignment vector based on results of the comparison of the center portions.
18. The method of claim 8 wherein determining the alignment vector comprises:
dividing the selected component image into a set of areas;
determining an initial alignment vector for a particular area based on at least one previously determined alignment vector for another area; and determining the alignment vector for the particular area based on the initial alignment vector for the particular area.
19. The method of claim 18 wherein determining the initial alignment vector comprises determining the initial alignment vector for a particular area based on at least one previously determined alignment vector for a neighboring area, where a neighboring area is defined as an area that shares a common border or at least one pixel with the particular area.
20. The method of claim 19 wherein determining the initial alignment vector comprises determining the initial alignment vector for a particular area based on at least one previously determined alignment vector for a neighboring area, where the initial alignment vector is chosen as the previously determined alignment vector that provides a minimum distortion value for the particular area among the previously determined alignment vectors for at least two of the neighboring areas.
21. The method of claim 8 wherein determining the alignment vector comprises:
dividing the selected component image into a set of areas arranged such that a center of at least one area of the set of areas and a center of at least one other area of the set of areas are in different proximity to a center of the selected component image;
grouping the areas into multiple rings;
determining an initial alignment vector for a particular area based on at least one previously determined alignment vector for at least one neighboring area, where the neighboring area is defined as an area that shares a common border or at least one pixel with the particular area and is defined to belong to either an inner ring or to the same ring as the particular area; and determining the alignment vector for the particular area based on the initial alignment vector for the particular area.
22. The method of claim 21 wherein determining the initial alignment vector is based on a previously determined alignment vector that provides a minimum distortion value for the particular area among previously determined alignment vectors for at least two neighboring areas.
23. The method of claim 21 wherein determining the initial alignment vector is based on a previously determined alignment vector for an inward radial neighbor area.
24. The method of claim 18 further comprising:
applying alignment vectors to multiple areas of an accessed component image;
and applying a technique to smooth discontinuities that may result when different areas possess different alignment vectors.
25. The method of claim 24 wherein applying a technique to smooth discontinuities comprises:
defining a window of nonzero horizontal or vertical extent along a boundary of contiguous blocks;
interpolating alignment vectors obtained from each of the contiguous blocks in order to obtain a new set of alignment vectors for parts of the contiguous blocks within the window; and applying the new set of alignment vectors to the parts of the contiguous blocks within the window.
26. A computer program for automatic registration of film separations, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
accessing component images that are based on digitized film separations, wherein each of the component images includes a set of gray-level pixels;
determining automatically an alignment vector for at least a part of a selected component image from among the accessed component images; and reducing one or more film distortions by applying the alignment vector to the part of the selected component image.
27. An apparatus for automatic registration of film separations, the apparatus comprising one or more processors programmed to perform at least the following operations:
accessing component images that are based on digitized film separations, wherein each of the component images includes a set of gray-level pixels, determining automatically an alignment vector for at least a part of a selected component image from among the accessed component images, and reducing one or more film distortions by applying the alignment vector to the part of the selected component image.
28. A method of performing registration of digitized images, the method comprising:
selecting at least two areas from each of a first image and a second image;
determining separate transformations for the selected areas of the first image based on a comparison of areas within the first and second images; and applying a feathering technique within a predetermined amount of at least two neighboring areas within the selected areas in order to obtain new transformations for the predetermined areas if the transformations for the neighboring areas differ, where the new transformations are based on the separate transformations.
29. The method of claim 28 further comprising applying the determined transformations to the selected areas of the first image.
30. The method of claim 28 wherein:
the transformations for the at least two areas are represented as alignment vectors; and applying the feathering technique comprises linearly interpolating between alignment vectors in the predetermined amount of the selected areas to obtain new alignment vectors for the predetermined amount of the areas.
31. The method of claim 28 wherein the images correspond to color film separations.
32. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
selecting at least two areas from each of a first image and a second image;
determining separate transformations for the selected areas of the first image based on a comparison of areas within the first and second images; and applying a feathering technique within a predetermined amount of at least two neighboring areas within the selected areas in order to obtain new transformations for the predetermined areas if the transformations for the neighboring areas differ, where the new transformations are based on the separate transformations
33. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
selecting at least two areas from each of a first image and a second image;
determining separate transformations for the selected areas of the first image based on a comparison of areas within the first and second images; and applying a feathering technique within a predetermined amount of at least two neighboring areas within the selected areas in order to obtain new transformations for the predetermined areas if the transformations for the neighboring areas differ, where the new transformations are based on the separate transformations.
34. A method of performing registration of digitized images, the method comprising:
dividing a selected component image into a set of areas;
grouping the areas into multiple rings; and determining transformations for at least two areas in the set of areas in an order that begins with at least one area within an innermost ring and proceeds to at least one area within a ring other than the innermost ring.
35. The method of claim 34 wherein the set of areas are arranged such that a center of at least one area of the set of areas and a center of at least one other area of the set of areas are in different proximity to a center of the selected component image.
36. The method of claim 34 wherein determining transformations comprises:
determining an initial alignment vector for a particular area of the set of areas based on a previously determined alignment vector corresponding to at least one neighboring area, where the neighboring area is defined as an area that shares a common border or at least one pixel with the particular area and the neighboring area belongs to either an inner ring or to a same ring as the particular area; and determining an alignment vector for the particular area based on the initial alignment vector for the particular area.
37. The method of claim 36 wherein the initial alignment vector is based on a previously determined alignment vector that provides a minimum distortion measure for the particular area among previously determined alignment vectors for at least two neighboring areas.
38. The method of claim 36 wherein the initial alignment vector is based on a previously determined alignment vector for an inward radial neighboring area.
39. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
dividing a selected component image into a set of areas;
grouping the areas into multiple rings; and determining transformations for at least two areas in the set of areas in an order that begins with at least one area within an innermost ring and proceeds to at least one area within a ring other than the innermost ring.
40. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
dividing a selected component image into a set of areas;
grouping the areas into multiple rings; and determining transformations for at least two areas in the set of areas in an order that begins with at least one area within an innermost ring and proceeds to at least one area within a ring other than the innermost ring.
41. A method of performing registration of digitized images, the method comprising:
selecting a first area in each of a first image and a second image;
determining which pixels in the first areas of the first and second images are feature pixels;
comparing the first areas of the first and second images by weighting (a) a comparison of feature pixels in the first area of the first image with corresponding pixels in the first area of the second image differently than (b) a comparison of non-feature pixels in the first area of the first image with corresponding pixels in the first area of the second image; and determining a transformation for the first area of the first image based on the comparison of the first areas of the first and second images.
42. The method of claim 41 wherein the first and second images are based on digitized color film separations.
43. The method of claim 41 wherein weighting comprises accumulating a non-zero distortion only if a pixel in the first area of the first image has been classified
44 as a feature and a corresponding pixel in the first area of the second image has not been classified as a feature.
44. The method of claim 41 wherein the features are edges.
45. The method of claim 41 wherein weighting comprises associating a weight of zero to the comparison of non-feature pixels in the first area of the first image with corresponding pixels in the first area of the second image, such that the comparison involving non-feature pixels in the first area of the first image need not be performed.
46. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
selecting a first area in each of a first image and a second image;
determining which pixels in the first areas of the first and second images are feature pixels;
comparing the first areas of the first and second images by weighting (a) a comparison of feature pixels in the first area of the first image with corresponding pixels in the first area of the second image differently than (b) a comparison of non-feature pixels in the first area of the first image with corresponding pixels in the first area of the second image; and determining a transformation for the first area of the first image based on the comparison of the first areas of the first and second images.
47. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
selecting a first area in each of a first image and a second image;
determining which pixels in the first areas of the first and second images are feature pixels;

comparing the first areas of the first and second images by weighting (a) a comparison of feature pixels in the first area of the first image with corresponding pixels in the first area of the second image differently than (b) a comparison of non-feature pixels in the first area of the first image with corresponding pixels in the first area of the second image; and determining a transformation for the first area of the first image based on the comparison of the first areas of the first and second images..
48. A method of performing registration of digitized images, the method comprising:
selecting a first area in each of a first image and a second image;
determining which pixels in the first areas of the first and second images are feature pixels; and determining a transformation for the first area of the first image, the determining including:
computing distortion values using a partial distortion measure on candidate alignment vectors that are processed in a spiral search configuration, and selecting one of the candidate alignment vectors as the transformation based on the computed distortion values.
49. The method of claim 48 wherein performing the spiral search comprises determining distortion values associated with different horizontal and vertical relative displacements of an initial alignment vector in an order characterized by increasing radial distance along a spiral scanning path.
50. The method of claim 49 wherein determining distortion values associated with different horizontal and vertical relative displacements comprises beginning at a location associated with the initial alignment vector and proceeding along the spiral scanning path within a preset window size.
51. The method of claim 48 wherein computing distortion values using the partial distortion measure comprises:
defining a set of pixels within an area;
calculating a partial sum of distortion values associated with a candidate alignment vector using a subset of the set of pixels;
comparing the partial sum to a current minimum distortion;
excluding the candidate alignment vector as a potential choice for the transformation if the partial sum is greater than or equal to the current minimum distortion;
adding to the partial sum an additional partial sum obtained using an additional subset of the set of pixels if the partial sum is less than the current minimum distortion; and continuing to add further additional partial sums and perform comparisons to the current minimum distortion until either the partial sum is greater than or equal to the current minimum distortion or all pixels in the set have been used.
52. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
selecting a first area in each of a first image and a second image;
determining which pixels in the first areas of the first and second images are feature pixels; and determining a transformation for the first area of the first image, the determining including:
computing distortion values using a partial distortion measure on candidate alignment vectors that are processed in a spiral search configuration, and selecting one of the candidate alignment vectors as the transformation based on the computed distortion values.
53. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
selecting a first area in each of a first image and a second image;
determining which pixels in the first areas of the first and second images are feature pixels; and determining a transformation for the first area of the first, the determining including:
computing distortion values using a partial distortion measure on candidate alignment vectors that are processed in a spiral search configuration, and selecting one of the candidate alignment vectors as the transformation based on the computed distortion values.
54. A method of performing registration of digitized images, the method comprising:
selecting a first image and a second image;
defining a first set of features and a second set of features;
determining a first alignment vector for a part of the first image based on the first set of features;
determining a second alignment vector for the part of the first image based on the second set of features, the determining comprising:
using the first alignment vector as an initial second alignment vector, and choosing the second alignment vector for the second set of features from a set of candidate alignment vectors obtained by varying the initial second alignment vector;
modifying the first alignment vector, the modifying comprising:
using the second alignment vector as an initial first alignment vector, and choosing the first alignment vector from a set of candidate alignment vectors obtained by varying the initial first alignment vector; and repeating the determining of the second alignment vector and the modifying of the first alignment vector until a particular stopping condition is met.
55. The method of claim 54 wherein the first set of features corresponds to edges in one direction and the second set of features corresponds to edges in an orthogonal direction.
56. The method of claim 54 wherein the set of candidate alignment vectors for each directional set of edges consists of alignment values that differ in only one direction.
57. The method of claim 54 wherein the set of candidate alignment vectors decreases in size each time the first and second alignment vectors are determined.
58. The method of claim 54 wherein the stopping condition is a preset number of iterations.
59. The method of claim 54 wherein the stopping condition is met when the first and second alignment vectors determined after a particular iteration are equivalent to the first and second alignment vectors after a previous iteration.
60. A computer program for performing registration of digitized images , the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
selecting a first image and a second image;
defining a first set of features and a second set of features;
determining a first alignment vector for a part of the first image based on the first set of features;
determining a second alignment vector for the part of the first image based on the second set of features, the determining comprising:

using the first alignment vector as an initial second alignment vector, and choosing the second alignment vector for the second set of features from a set of candidate alignment vectors obtained by varying the initial second alignment vector;
modifying the first alignment vector, the modifying comprising:
using the second alignment vector as an initial first alignment vector, and choosing the first alignment vector from a set of candidate alignment vectors obtained by varying the initial first alignment vector; and repeating the determining of the second alignment vector and the modifying of the first alignment vector until a particular stopping condition is met.
61. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
selecting a first image and a second image;
defining a first set of features and a second set of features;
determining a first alignment vector for a part of the first image based on the first set of features;
determining a second alignment vector for the part of the first image based on the second set of features, the determining comprising:
using the first alignment vector as an initial second alignment vector, and choosing the second alignment vector for the second set of features from a set of candidate alignment vectors obtained by varying the initial second alignment vector;
modifying the first alignment vector, the modifying comprising:
using the second alignment vector as an initial first alignment vector, and choosing the first alignment vector from a set of candidate alignment vectors obtained by varying the initial first alignment vector; and repeating the determining of the second alignment vector and the modifying of the first alignment vector until a particular stopping condition is met.
62. A method of performing registration of digitized images, the method comprising:
selecting a first area from each of a first image and a second image;
detecting a first set of features in the first area of the first image;
determining a second set of features consisting of the features from within the first set that include a first predetermined amount of information;
determining whether the second set of features is collectively sufficient to provide a meaningful comparison; and determining, if the second set of features is deemed collectively sufficient, a transformation for the first area of the first image based on a comparison of the first area of the first image with areas of the second image.
63. The method of claim 62 wherein determining whether the second set of features is sufficient comprises determining whether the second set collectively includes a second predetermined amount of information.
64. The method of claim 62 wherein the first set of features includes a set of features that are oriented in a particular direction.
65. The method of claim 62 wherein the first set of features comprises -edges in the first area of the first image.
66. The method of claim 62 wherein:
the first areas of the first and second images include pixels, and determining the transformation comprises:

determining which pixels in the first areas of the first and second images are feature pixels, and weighting (a) a comparison of feature pixels in the first area of the first image with corresponding pixels in the first area of the second image differently than (b) a comparison of non-feature pixels in the first area of the first image with corresponding pixels in the first area of the second image.
67. The method of claim 62 wherein the images are based on digitized spectral separations.
68. The method of claim 67 wherein the spectral separations comprise color film separations.
69. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
selecting a first area from each of a first image and a second image;
detecting a first set of features in the first area of the first image;
determining a second set of features consisting of the features from within the first set that include a first predetermined amount of information;
determining whether the second set of features is collectively sufficient to provide a meaningful comparison; and determining, if the second set of features is deemed collectively sufficient, a transformation for the first area of the first image based on a comparison of the first area of the first image with areas of the second image.
70. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
selecting a first area from each of a first image and a second image;
detecting a first set of features in the first area of the first image;

determining a second set of features consisting of the features from within the first set that include a first predetermined amount of information;
determining whether the second set of features is collectively sufficient to provide a meaningful comparison; and determining, if the second set of features is deemed collectively sufficient, a transformation for the first area of the first image based on a comparison of the first area of the first image with areas of the second image.
71. A method of performing registration of digitized images, the method comprising:
selecting automatically a first area in each of a first image and a second image;
determining automatically a transformation for the first area in the first image based on a comparison of the first area of the first image with corresponding areas of the second image; and applying automatically the transformation to the first area in the first image, wherein a film distortion is reduced.
72. The method of claim 71 wherein the first and second images are based on film separations.
73. The method of claim 72 wherein the film separations comprise color separations.
74. The method of claim 71 further comprising:
performing the method for a second area in the first image that is not isolated from the first area, wherein the two transformations are represented as alignment vectors that differ; and applying a feathering technique to the first and second areas within a predetermined amount of the first and second areas in order to obtain new alignment vectors within the predetermined amount where the new alignment vectors are based on the first and second alignment vectors.
75. The method of claim 71 further comprising:
performing the method for multiple areas in the first image; and determining the transformations for the multiple areas in an order of increasing radial distance.
76. The method of claim 71 wherein determining the transformation comprises:
selecting automatically a feature in the first areas of the first and second images; and using a feature-based measure to compare the first areas of the first and second images.
77. The method of claim 71 wherein determining the transformation comprises:
detecting automatically a feature in the first area of the first image;
eliminating automatically parts of the feature that do not contain a predetermined amount of information; and determining whether parts of the feature that were not eliminated provide a basis for meaningful comparison.
78. The method of claim 77 wherein determining whether the parts not eliminated provide a basis for meaningful comparison comprises determining whether the parts not eliminated collectively contain a second predetermined amount of information.
79. The method of claim 77 wherein the feature comprises edges in the first area.
80. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:

selecting automatically a first area in each of a first image and a second image;
determining automatically a transformation for the first area in the first image based on a comparison of the first area of the first image with corresponding areas of the second image; and applying automatically the transformation to the first area in the first image, wherein a film distortion is reduced.
81. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
selecting automatically a first area in each of a first image and a second image;
determining automatically a transformation for the first area in the first image based on a comparison of the first area of the first image with corresponding areas of the second image; and applying automatically the transformation to the first area in the first image, wherein a film distortion is reduced.
82. The method of claim 8 wherein determining the alignment vector comprises:
dividing the selected component image into a set of areas;
determining an initial alignment vector for a particular area based on at least one previously determined alignment vector for at least one other area, where a center of the other area is not farther in proximity to a center of the selected component image than is a center of the particular area; and determining the alignment vector for the particular area based on the initial alignment vector for the particular area.
83. The method of claim 82 wherein the other area is an inward radial neighboring area of the particular area, a neighboring area of the particular area being defined as an area that shares a common border or at least one pixel with the particular area.
84. A method of performing registration of digitized images, the method comprising:
dividing a selected component image into a set of areas; and determining a transformation for a particular area in the set of areas based on at least one previously determined transformation for at least one other area, where a center of the other area is not farther in proximity to a center of the selected component image than is a center of the particular area.
85. The method of claim 84 further comprising:
grouping the set of areas into multiple rings that form at least one inner ring and at least one outer ring; and determining transformations for at least two areas of the set of areas in an order that begins with at least one area within the inner ring and proceeds to at least one area within the outer ring.
86. The method of claim 84 wherein determining transformations comprises:
determining an initial alignment vector for a particular area of the set of areas based on a previously determined alignment vector corresponding to at least one neighboring area, where the neighboring area is defined as an area that shares a common border or at least one pixel with the particular area; and determining an alignment vector for the particular area based on the initial alignment vector for the particular area.
87. A computer program for performing registration of digitized images, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
dividing a selected component image into a set of areas; and determining a transformation for a particular area in the set of areas based on at least one previously determined transformation for at least one other area, where a center of the other area is not farther in proximity to a center of the selected component image than is a center of the particular area.
88. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
dividing a selected component image into a set of areas, and determining a transformation for a particular area in the set of areas based on at least one previously determined transformation for at least one other area, where a center of the other area is not farther in proximity to a center of the selected component image than is a center of the particular area.
89. The method of claim 1 wherein reducing one or more film distortions comprises correcting one or more film distortions.

1.~A method for automatic registration of film separations, the method comprising:
accessing component images that are based on digitized film separations, wherein each of the component images includes a set of gray-level pixels;
determining automatically an alignment vector for at least a part of a selected component image from among the accessed component images, the part being a strict subset of the selected component image; and reducing one or more film distortions by applying the alignment vector only to the part of the selected component image.

2. The method of claim 1 wherein the accessed component images are based on digitized color film separations.

3. The method of claim 1 wherein accessing component images comprises digitizing film separations.

4. The method of claim 1 wherein the alignment vector aligns the part of the selected component image with a corresponding part of a second of the accessed component images, the method further comprising combining the selected component image and the second of the accessed component images after applying the alignment vector.

5. The method of claim 1 further comprising selecting one of the accessed component images as a reference, wherein determining the alignment vector comprises determining an alignment vector between a part of the reference and the part of the selected component image.

23. The method of claim 21 wherein determining the initial alignment vector is based on a previously determined alignment vector for an inward radial neighbor area.
24. The method of claim 18 further comprising:
applying alignment vectors to multiple areas of an accessed component image;
and applying a technique to smooth discontinuities that may result when different areas possess different alignment vectors.
25. The method of claim 24 wherein applying a technique to smooth discontinuities comprises:
defining a window of nonzero horizontal or vertical extent along a boundary of contiguous blocks;
interpolating alignment vectors obtained from each of the contiguous blocks in order to obtain a new set of alignment vectors for parts of the contiguous blocks within the window; and applying the new set of alignment vectors to the parts of the contiguous blocks within the window.
26. A computer program for automatic registration of film separations, the computer program residing on a computer-readable medium and comprising instructions for causing a computer to perform operations including:
accessing component images that are based on digitized film separations, wherein each of the component images includes a set of gray-level pixels;
determining automatically an alignment vector for at least a part of a selected component image from among the accessed component images, the part being a strict subset of the selected component image; and reducing one or more film distortions by applying the alignment vector only to the part of the selected component image.

27. An apparatus for automatic registration of film separations, the apparatus comprising one or more processors programmed to perform at least the following operations:
accessing component images that are based on digitized film separations, wherein each of the component images includes a set of gray-level pixels, determining automatically an alignment vector for at least a part of a selected component image from among the accessed component images, the part being a strict subset of the selected component image, and reducing one or more film distortions by applying the alignment vector only to the part of the selected component image.
28. A method of performing registration of digitized images, the method comprising:
selecting at least two areas from each of a first image and a second image;
determining separate transformations for the selected areas of the first image based on a comparison of areas within the first and second images; and applying a feathering technique within a predetermined amount of at least two neighboring areas within the selected areas in order to obtain new transformations for the predetermined areas if the transformations for the neighboring areas differ, where the new transformations are based on the separate transformations.
29. The method of claim 28 further comprising applying the determined transformations to the selected areas of the first image.
30. The method of claim 28 wherein:
the transformations for the at least two areas are represented as alignment vectors; and applying the feathering technique comprises linearly interpolating between alignment vectors in the predetermined amount of the selected areas to obtain new alignment vectors for the predetermined amount of the areas.

center of the other area is not farther in proximity to a center of the selected component image than is a center of the particular area.
88. An apparatus for performing registration of digitized images, the apparatus comprising one or more processors programmed to perform at least the following operations:
dividing a selected component image into a set of areas, and determining a transformation for a particular area in the set of areas based on at least one previously determined transformation for at least one other area, where a center of the other area is not farther in proximity to a center of the selected component image than is a center of the particular area.
89. The method of claim 1 wherein reducing one or more film distortions comprises correcting one or more film distortions.
90. The method of claim 1 further comprising:
determining automatically a second alignment vector for at least a second part of the selected component image, the second part being a strict subset of the selected component image; and reducing one or more film distortions by applying the second alignment vector only to the second part of the selected component image.
91. The method of claim 73 wherein the film distortion that is reduced comprises a misregistration between the color separations.
CA2472524A 2002-01-04 2003-01-06 Registration of separations Expired - Lifetime CA2472524C (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US10/035,337 2002-01-04
US10/035,337 US7092584B2 (en) 2002-01-04 2002-01-04 Registration of separations
PCT/US2003/000212 WO2003058976A1 (en) 2002-01-04 2003-01-06 Registration of separations

Publications (2)

Publication Number Publication Date
CA2472524A1 true CA2472524A1 (en) 2003-07-17
CA2472524C CA2472524C (en) 2011-06-21

Family

ID=21882029

Family Applications (1)

Application Number Title Priority Date Filing Date
CA2472524A Expired - Lifetime CA2472524C (en) 2002-01-04 2003-01-06 Registration of separations

Country Status (7)

Country Link
US (9) US7092584B2 (en)
EP (1) EP1468570A4 (en)
JP (1) JP4606025B2 (en)
AU (1) AU2003202211B2 (en)
CA (1) CA2472524C (en)
MX (1) MXPA04006562A (en)
WO (2) WO2003058976A1 (en)

Families Citing this family (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005029835A2 (en) 2002-01-04 2005-03-31 Warner Bros.Entertainment Inc. Registration of separations
US20040117265A1 (en) * 2002-12-12 2004-06-17 Paul Hoffman Method and system for labeling and managing the sale of manufactured concrete blocks
US7680342B2 (en) 2004-08-16 2010-03-16 Fotonation Vision Limited Indoor/outdoor classification in digital images
US7606417B2 (en) 2004-08-16 2009-10-20 Fotonation Vision Limited Foreground/background segmentation in digital images with differential exposure calculations
MXPA06002505A (en) * 2003-09-05 2006-08-31 Warner Bros Entertainment Inc Registration of separations.
US7596273B2 (en) * 2004-04-19 2009-09-29 Fujifilm Corporation Image processing method, image processing apparatus, and image processing program
AU2005267848A1 (en) * 2004-07-30 2006-02-09 Pacific Title & Arts Studio, Inc. Method for conversion and reproduction of film images through a digital process
WO2006080950A1 (en) * 2005-01-27 2006-08-03 Thomson Licensing Edge based cmy automatic picture registration
US7924922B2 (en) * 2005-03-07 2011-04-12 Hewlett-Packard Development Company, L.P. Color registration in a digital video
JP4473779B2 (en) * 2005-05-23 2010-06-02 株式会社東芝 Ultrasonic diagnostic apparatus and image processing method thereof
US20070046781A1 (en) * 2005-08-29 2007-03-01 Honeywell International Inc. Systems and methods for processing digital video data
JP5237109B2 (en) * 2005-12-16 2013-07-17 トムソン ライセンシング Color component registration method, apparatus and system
US8050519B2 (en) * 2005-12-19 2011-11-01 Olympus Corporation Image combining apparatus
US7692696B2 (en) 2005-12-27 2010-04-06 Fotonation Vision Limited Digital image acquisition system with portrait mode
US7577292B2 (en) * 2005-12-30 2009-08-18 Microsoft Corporation Automatic removal of purple fringing from images
WO2007095477A2 (en) 2006-02-14 2007-08-23 Fotonation Vision Limited Image blurring
IES20060559A2 (en) 2006-02-14 2006-11-01 Fotonation Vision Ltd Automatic detection and correction of non-red flash eye defects
IES20060564A2 (en) 2006-05-03 2006-11-01 Fotonation Vision Ltd Improved foreground / background separation
JP2008009877A (en) * 2006-06-30 2008-01-17 Brother Ind Ltd Image processing device, image processing method and program
US7983505B2 (en) * 2007-03-30 2011-07-19 Intel Corporation Performing deblocking on pixel data
US9373076B1 (en) 2007-08-08 2016-06-21 Aol Inc. Systems and methods for building and using social networks in image analysis
WO2009078957A1 (en) 2007-12-14 2009-06-25 Flashfoto, Inc. Systems and methods for rule-based segmentation for objects with full or partial frontal view in color images
JP4926116B2 (en) * 2008-04-16 2012-05-09 株式会社日立ハイテクノロジーズ Image inspection device
KR101279573B1 (en) 2008-10-31 2013-06-27 에스케이텔레콤 주식회사 Motion Vector Encoding/Decoding Method and Apparatus and Video Encoding/Decoding Method and Apparatus
US8406507B2 (en) * 2009-01-14 2013-03-26 A9.Com, Inc. Method and system for representing image patches
US8411986B2 (en) * 2009-04-13 2013-04-02 Flashfoto, Inc. Systems and methods for segmenation by removal of monochromatic background with limitied intensity variations
JP5355292B2 (en) * 2009-08-10 2013-11-27 キヤノン株式会社 Image processing apparatus and image processing method
US8670615B2 (en) * 2009-09-30 2014-03-11 Flashfoto, Inc. Refinement of segmentation markup
US9311567B2 (en) 2010-05-10 2016-04-12 Kuang-chih Lee Manifold learning and matting
US8467629B2 (en) * 2010-08-12 2013-06-18 High Technology Video, Inc. Methods and systems for automatic coloring of digital images
JP2013101484A (en) * 2011-11-08 2013-05-23 Sony Corp Image processing apparatus, image processing method and program
WO2014002068A2 (en) 2012-06-28 2014-01-03 Koninklijke Philips N.V. System and method for registering an image sequence
US9241128B2 (en) 2013-02-14 2016-01-19 Warner Bros. Entertainment Inc. Video conversion technology
US9934577B2 (en) * 2014-01-17 2018-04-03 Microsoft Technology Licensing, Llc Digital image edge detection
US9361554B2 (en) 2014-09-26 2016-06-07 Ricoh Company, Ltd. Low overhead near unity scaling technique
US9819962B2 (en) * 2015-04-06 2017-11-14 Ati Technologies Ulc Efficient low-complexity video compression
US10339178B2 (en) 2015-06-30 2019-07-02 Samsung Electronics Co., Ltd. Fingerprint recognition method and apparatus
CN105335713A (en) * 2015-10-28 2016-02-17 小米科技有限责任公司 Fingerprint identification method and device
US20170372142A1 (en) * 2016-06-27 2017-12-28 Facebook, Inc. Systems and methods for identifying matching content
US10366501B2 (en) * 2016-11-07 2019-07-30 The Boeing Company Method and apparatus for performing background image registration
CN106780523A (en) * 2016-12-29 2017-05-31 怀宁鑫橙信息技术有限公司 A kind of method for correcting image
CN107610047A (en) * 2017-08-02 2018-01-19 深圳市易成自动驾驶技术有限公司 Fragmental image processing method, apparatus and computer-readable recording medium

Family Cites Families (118)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS55145493A (en) * 1979-04-27 1980-11-13 Toshiba Corp Color television camera device
US4285004A (en) * 1980-02-25 1981-08-18 Ampex Corporation Total raster error correction apparatus and method for the automatic set up of television cameras and the like
US4832485A (en) * 1982-09-03 1989-05-23 Commonwealth Technology, Inc. Image enhancer
US4641244A (en) * 1985-04-05 1987-02-03 Opti-Copy, Inc. Method and apparatus for registering color separation film
WO1987005769A1 (en) * 1986-03-19 1987-09-24 British Broadcasting Corporation Tv picture motion measurement
US5430478A (en) * 1986-09-04 1995-07-04 Mscl, Inc. Film weave correction system
US5555092A (en) * 1987-12-15 1996-09-10 Mscl Method and apparatus for correcting horizontal, vertical and framing errors in motion picture film transfer
JPS63182961A (en) * 1987-01-24 1988-07-28 Agency Of Ind Science & Technol System for detecting distortion of color image
US4849914A (en) 1987-09-22 1989-07-18 Opti-Copy, Inc. Method and apparatus for registering color separation film
US4924521A (en) * 1987-12-18 1990-05-08 International Business Machines Corporation Image processing system and method employing combined black and white and gray scale image data
US5023815A (en) * 1989-08-04 1991-06-11 Wilson Monti R Method and apparatus for registering color film separations
US5161035A (en) * 1989-10-31 1992-11-03 Brother Kogyo Kabushiki Kaisha Digital image processing device for enlarging original image with high fidelity
US5022089A (en) * 1990-01-19 1991-06-04 Wilson Monti R Method and apparatus for fast registration using crosshair register marks
US5002089A (en) * 1990-04-02 1991-03-26 Carrier Corporation Variable area refrigerant expansion device for heating mode of a heat pump
US5781666A (en) * 1990-04-17 1998-07-14 Canon Kabushiki Kaisha Image processing method and apparatus suitable for both high-resolution and low-resolution image data
US5129009A (en) * 1990-06-04 1992-07-07 Motorola, Inc. Method for automatic semiconductor wafer inspection
FR2665597B1 (en) * 1990-07-31 1995-11-17 Thomson Trt Defense METHOD AND APPARATUS FOR LOCALIZING REALTIME CONTOURS IN A DIGITAL IMAGE IN REAL TIME, IN PARTICULAR FOR RECOGNIZING SHAPES IN A SCENE ANALYSIS PROCESS.
US5185808A (en) 1991-06-06 1993-02-09 Eastman Kodak Company Method for merging images
US5283560A (en) * 1991-06-25 1994-02-01 Digital Equipment Corporation Computer system and method for displaying images with superimposed partially transparent menus
JP3253125B2 (en) * 1991-07-04 2002-02-04 株式会社東芝 Color image reading correction device
JPH05161145A (en) * 1991-10-09 1993-06-25 Olympus Optical Co Ltd Sequential image pickup device
US5251271A (en) * 1991-10-21 1993-10-05 R. R. Donnelley & Sons Co. Method for automatic registration of digitized multi-plane images
US8352400B2 (en) * 1991-12-23 2013-01-08 Hoffberg Steven M Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore
US7242988B1 (en) * 1991-12-23 2007-07-10 Linda Irene Hoffberg Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore
US6850252B1 (en) * 1999-10-05 2005-02-01 Steven M. Hoffberg Intelligent electronic appliance system and method
US5903454A (en) * 1991-12-23 1999-05-11 Hoffberg; Linda Irene Human-factored interface corporating adaptive pattern recognition based controller apparatus
US8032477B1 (en) * 1991-12-23 2011-10-04 Linda Irene Hoffberg Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore
US7006881B1 (en) * 1991-12-23 2006-02-28 Steven Hoffberg Media recording device with remote graphic user interface
JP3127598B2 (en) * 1992-09-07 2001-01-29 松下電器産業株式会社 Method for extracting density-varying constituent pixels in image and method for determining density-fluctuation block
US5418574A (en) * 1992-10-12 1995-05-23 Matsushita Electric Industrial Co., Ltd. Video signal correction apparatus which detects leading and trailing edges to define boundaries between colors and corrects for bleeding
US5734915A (en) * 1992-11-25 1998-03-31 Eastman Kodak Company Method and apparatus for composing digital medical imagery
US5308116A (en) 1992-11-30 1994-05-03 General Motors Corporation Rear seat shoulder belt guide
DE69315969T2 (en) * 1992-12-15 1998-07-30 Sun Microsystems Inc Presentation of information in a display system with transparent windows
JPH06233144A (en) 1993-01-29 1994-08-19 Fujitsu Ltd Color reader
CA2124624C (en) * 1993-07-21 1999-07-13 Eric A. Bier User interface having click-through tools that can be composed with other tools
US5475428A (en) * 1993-09-09 1995-12-12 Eastman Kodak Company Method for processing color image records subject to misregistration
US5548326A (en) * 1993-10-06 1996-08-20 Cognex Corporation Efficient image registration
TW297202B (en) * 1993-10-13 1997-02-01 Rca Thomson Licensing Corp
US5517234A (en) * 1993-10-26 1996-05-14 Gerber Systems Corporation Automatic optical inspection system having a weighted transition database
JPH07220056A (en) * 1993-11-26 1995-08-18 Philips Electron Nv Image composition method and image apparatus for execution of said method
JPH07203298A (en) * 1993-12-28 1995-08-04 Nec Corp Image composition circuit
JP3035690B2 (en) * 1994-01-27 2000-04-24 株式会社東京精密 Wafer diameter / cross-sectional shape measuring device and wafer chamfering machine incorporating the same
US5630037A (en) * 1994-05-18 1997-05-13 Schindler Imaging, Inc. Method and apparatus for extracting and treating digital images for seamless compositing
US5640200A (en) * 1994-08-31 1997-06-17 Cognex Corporation Golden template comparison using efficient image registration
US5537476A (en) 1994-11-21 1996-07-16 International Business Machines Corporation Secure viewing of display units by image superposition and wavelength separation
JPH08163594A (en) * 1994-12-12 1996-06-21 Sony Corp Moving image decoding method and moving image decoder
EP0771107B1 (en) * 1995-05-12 2002-12-11 Sony Corporation Key signal generating device, picture producing device, key signal generating method, and picture producing method
US5892554A (en) * 1995-11-28 1999-04-06 Princeton Video Image, Inc. System and method for inserting static and dynamic images into a live video broadcast
US5641596A (en) * 1995-12-05 1997-06-24 Eastman Kodak Company Adjusting film grain properties in digital images
US5641200A (en) * 1996-01-26 1997-06-24 Howell; Jo Ann Child restraint seat for shopping cart
US5812214A (en) * 1996-03-14 1998-09-22 Sierra Video Systems, Inc. Apparatus and method for compositing video images
US6118427A (en) * 1996-04-18 2000-09-12 Silicon Graphics, Inc. Graphical user interface with optimal transparency thresholds for maximizing user performance and system efficiency
US6075905A (en) * 1996-07-17 2000-06-13 Sarnoff Corporation Method and apparatus for mosaic image construction
US5917987A (en) * 1996-08-16 1999-06-29 Neyman; Yuri System for controlling the transfer of an image on a first medium to a second medium
GB9619117D0 (en) * 1996-09-12 1996-10-23 Pandora Int Ltd Digital image processing
GB9619119D0 (en) * 1996-09-12 1996-10-23 Discreet Logic Inc Processing image
US6002434A (en) * 1997-01-14 1999-12-14 Matsushita Electric Industrial Co., Ltd. Registration correction waveform determination method and system for a television camera
EP0878970A3 (en) * 1997-05-16 1999-08-18 Matsushita Electric Industrial Co., Ltd. Imager registration error and chromatic aberration measurement system for a video camera
JPH10327401A (en) * 1997-05-22 1998-12-08 Hitachi Ltd Motion vector detection method and encoding method and device for picture signal using the same
US6002424A (en) * 1997-06-12 1999-12-14 Schick Technologies, Inc. Dental imaging system with white balance compensation
US5926568A (en) * 1997-06-30 1999-07-20 The University Of North Carolina At Chapel Hill Image object matching using core analysis and deformable shape loci
JPH11161773A (en) 1997-11-28 1999-06-18 Konica Corp Method for processing picture and device for inputting picture
EP1043890B1 (en) * 1997-11-28 2002-04-17 Hamamatsu Photonics K.K. Solid state image pickup device and analyzer using it
DE19855885A1 (en) * 1997-12-04 1999-08-05 Fuji Photo Film Co Ltd Image processing method for digital photographic copier providing photographic prints
JP3783817B2 (en) 1998-03-11 2006-06-07 富士写真フイルム株式会社 Image processing method and image processing apparatus
JP4136044B2 (en) * 1997-12-24 2008-08-20 オリンパス株式会社 Image processing apparatus and image processing method therefor
US6295083B1 (en) * 1998-02-27 2001-09-25 Tektronix, Inc. High precision image alignment detection
JP3863294B2 (en) * 1998-07-02 2006-12-27 株式会社日立製作所 Noise reduction signal processing circuit and video display device
JP2000050054A (en) * 1998-07-31 2000-02-18 Canon Inc Recording system
US6870564B1 (en) * 1998-10-02 2005-03-22 Eastman Kodak Company Image processing for improvement of color registration in digital images
US6418166B1 (en) * 1998-11-30 2002-07-09 Microsoft Corporation Motion estimation and block matching pattern
US6393150B1 (en) * 1998-12-04 2002-05-21 Eastman Kodak Company Region-based image binarization system
US6317223B1 (en) * 1998-12-14 2001-11-13 Eastman Kodak Company Image processing system for reducing vertically disposed patterns on images produced by scanning
US6282326B1 (en) * 1998-12-14 2001-08-28 Eastman Kodak Company Artifact removal technique for skew corrected images
US6373970B1 (en) * 1998-12-29 2002-04-16 General Electric Company Image registration using fourier phase matching
US7904187B2 (en) * 1999-02-01 2011-03-08 Hoffberg Steven M Internet appliance system and method
JP3538055B2 (en) 1999-02-15 2004-06-14 日本電気株式会社 Motion vector detection device
US6266452B1 (en) * 1999-03-18 2001-07-24 Nec Research Institute, Inc. Image registration method
WO2001011870A1 (en) * 1999-08-05 2001-02-15 Hamamatsu Photonics K.K. Solid-state imaging device and range finding device
JP4005277B2 (en) * 1999-09-06 2007-11-07 富士フイルム株式会社 Image processing apparatus, method, and recording medium
US6477270B1 (en) * 1999-10-21 2002-11-05 Yecheng Wu Method for converting a high resolution image to true color using a low resolution color image
US6874420B2 (en) * 1999-10-22 2005-04-05 Cc1, Inc. System and method for register mark recognition
US6816604B2 (en) * 1999-12-30 2004-11-09 Eastman Kodak Company Digital film processing feature location method and system
US6529208B1 (en) * 2000-01-06 2003-03-04 International Business Machines Corporation Method and apparatus for updating a window identification buffer in a data processing system
US7276643B2 (en) * 2000-02-18 2007-10-02 The Regents Of The University Of California Transgenic animals, cell lines derived therefrom, and methods for screening for anti-amyloidogenic agents
US6610387B1 (en) * 2000-04-19 2003-08-26 Dai Nippon Printing Co., Ltd. Thermal transfer film and image forming method
JP4195958B2 (en) 2000-05-24 2008-12-17 パナソニック株式会社 Color image recording device
DE10041750C2 (en) * 2000-08-25 2003-02-27 Agfa Gevaert Ag On-light or transmitted-light scanners and image processing methods for scanned image originals
US6722432B2 (en) * 2001-01-29 2004-04-20 Schlumberger Technology Corporation Slimhole fluid tester
US7181081B2 (en) * 2001-05-04 2007-02-20 Legend Films Inc. Image sequence enhancement system and method
JP2002344724A (en) 2001-05-17 2002-11-29 Fuji Photo Film Co Ltd Imaging device, image processing apparatus, image processing method, and program
US7127125B2 (en) * 2002-01-04 2006-10-24 Warner Bros. Entertainment Inc. Registration of separations
US6947607B2 (en) * 2002-01-04 2005-09-20 Warner Bros. Entertainment Inc. Reduction of differential resolution of separations
US6713242B2 (en) * 2002-01-23 2004-03-30 Agfa-Gevaert Method for processing a black-and-white negative recording film material for motion picture soundtrack
US6792071B2 (en) * 2002-03-27 2004-09-14 Agfa-Gevaert Method of performing geometric measurements on digital radiological images
US6866255B2 (en) * 2002-04-12 2005-03-15 Xerox Corporation Sputtered spring films with low stress anisotropy
ITUD20020190A1 (en) * 2002-09-09 2004-03-10 De Longhi Spa DEVICE FOR THE PRODUCTION OF ICE CREAM
US6969991B2 (en) * 2002-12-11 2005-11-29 The Board Of Trustees Of The Leland Stanford Junior University Correction of the effect of spatial gradient field distortions in diffusion-weighted imaging
US6879731B2 (en) * 2003-04-29 2005-04-12 Microsoft Corporation System and process for generating high dynamic range video
US7245783B2 (en) * 2003-06-24 2007-07-17 Eastman Kodak Company System and method for estimating, synthesizing and matching noise in digital images and image sequences
KR101055355B1 (en) * 2003-08-20 2011-08-09 톰슨 라이센싱 Artifact Reduction Method and Decoding Device for Video Streams
US8484001B2 (en) * 2003-08-26 2013-07-09 Voyant Health Ltd. Pre-operative medical planning system and method for use thereof
US7680356B2 (en) * 2003-10-14 2010-03-16 Thomson Licensing Technique for bit-accurate comfort noise addition
US7440559B2 (en) * 2003-10-22 2008-10-21 Nokia Corporation System and associated terminal, method and computer program product for controlling the flow of content
JP3924286B2 (en) * 2003-10-31 2007-06-06 Ｔｄｋ株式会社 Manufacturing method of multilayer ceramic electronic component
US7346109B2 (en) * 2003-12-23 2008-03-18 Genesis Microchip Inc. Motion vector computation for video sequences
US8087058B2 (en) * 2004-01-19 2011-12-27 Comcast Cable Holdings, Llc HDTV subscriber verification
US20050209983A1 (en) * 2004-03-18 2005-09-22 Macpherson Deborah L Context driven topologies
US7093939B2 (en) * 2004-04-05 2006-08-22 Nextscan, Inc. High-speed continuous linear film transport system
US7196317B1 (en) * 2005-03-25 2007-03-27 Virginia Tech Intellectual Properties, Inc. System, device, and method for detecting perturbations
US7727624B2 (en) * 2005-11-22 2010-06-01 Rensselaer Polytechnic Institute Super-compressible carbon nanotube films and micro-bundles
JP5205042B2 (en) 2006-12-20 2013-06-05 株式会社半導体エネルギー研究所 Method for manufacturing semiconductor device
CN103193221B (en) * 2007-05-17 2014-12-31 株式会社钟化 Graphite film and manufacturing method thereof
US8120960B2 (en) * 2007-11-07 2012-02-21 Spansion Israel Ltd. Method and apparatus for accessing a non-volatile memory array comprising unidirectional current flowing multiplexers
US8698087B2 (en) * 2008-11-03 2014-04-15 The Trustees Of The University Of Pennsylvania Limited angle tomography with time-of-flight PET
KR20120037454A (en) * 2009-07-08 2012-04-19 톰슨 라이센싱 Method and system for color correction for three-dimensional(3d) projection
US8229344B1 (en) * 2009-08-26 2012-07-24 Bae Systems Information And Electronic Systems Integration Inc. RF communication receiver vulnerability assessment
US8217248B1 (en) * 2010-01-08 2012-07-10 Roberto Feliciano Ligature

Also Published As

Publication number Publication date
US20130230238A1 (en) 2013-09-05
US7672541B2 (en) 2010-03-02
MXPA04006562A (en) 2006-03-08
AU2003202211A2 (en) 2003-07-24
US9773314B2 (en) 2017-09-26
US7486842B2 (en) 2009-02-03
US20060072850A1 (en) 2006-04-06
WO2004059574A2 (en) 2004-07-15
US20080137979A1 (en) 2008-06-12
US20140363077A1 (en) 2014-12-11
US8094972B2 (en) 2012-01-10
US20100150469A1 (en) 2010-06-17
JP2005515527A (en) 2005-05-26
JP4606025B2 (en) 2011-01-05
US8401337B2 (en) 2013-03-19
AU2003202211A1 (en) 2003-07-24
AU2003202211B2 (en) 2008-12-11
CA2472524C (en) 2011-06-21
WO2004059574A3 (en) 2004-12-09
US20080056614A1 (en) 2008-03-06
US20030128280A1 (en) 2003-07-10
EP1468570A1 (en) 2004-10-20
US7092584B2 (en) 2006-08-15
US7272268B2 (en) 2007-09-18
US9104938B2 (en) 2015-08-11
US20120106870A1 (en) 2012-05-03
US20150348268A1 (en) 2015-12-03
US8818088B2 (en) 2014-08-26
EP1468570A4 (en) 2015-01-07
WO2003058976A1 (en) 2003-07-17

Similar Documents

Publication Publication Date Title
CA2472524A1 (en) Registration of separations
US7672507B2 (en) Image processing methods and systems
CN109741356B (en) Sub-pixel edge detection method and system
JP5703312B2 (en) Efficient scale space extraction and description of feature points
CN103543394A (en) Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment
CN104867137B (en) A kind of method for registering images based on improvement RANSAC algorithms
CN104008542B (en) A kind of Fast Corner matching process for specific plane figure
KR20040035593A (en) Local constraint for motion matching
CN111161222B (en) Printing roller defect detection method based on visual saliency
CN108876723A (en) A kind of construction method of the color background of gray scale target image
JP2009086926A (en) Image recognition method and device
CN106022337B (en) A kind of planar target detection method based on continuous boundary feature
CN112017223A (en) Heterologous image registration method based on improved SIFT-Delaunay
CN105869122A (en) Image processing method and apparatus
CN108335268A (en) A method of the coloured image deblurring based on blind deconvolution
CN109063537B (en) Hyperspectral image preprocessing method for unmixing of abnormal small target
CN110717910A (en) CT image target detection method and CT scanner
CN113011417B (en) Target matching method based on intersection ratio coverage rate loss and repositioning strategy
CN114283157A (en) Ellipse fitting-based ellipse object segmentation method
JP4248947B2 (en) Image color reduction device, image color reduction method, and image color reduction program
KR102119138B1 (en) Bayesian based image restoration method for camera
CN112419407A (en) Cloud cluster displacement vector calculation method and device based on cloud cluster edge identification
CN111209835B (en) Improved SURF mobile robot image matching method
KR101664868B1 (en) Compensation method and apparatus for depth image based on outline
CN117710287A (en) Material detection method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
EEER Examination request
MKEX Expiry

Effective date: 20230106