CN103440642A - Image strong and weak edge detection method based on spatio-temporal information responded by dot matrix nerve cells - Google Patents

Abstract

The invention relates to an image strong and weak edge detection method based on spatio-temporal information responded by dot matrix nerve cells. Firstly, a multi-direction Log-Gabor filtering result of an image in a view is utilized and edge information of the image is reconstructed; a reconstruction result serves as input of the dot matrix nerve cells; time in releasing action potentials of all the nerve cells is recorded to form a time matrix; a constructed reception field window slides on the time matrix, the improved variance is calculated according to a time order of all time elements and a center point of the window undergoes assignment and thus, a variance matrix containing nerve cell responding time and the spatio-temporal information is obtained; afterwards, the reception field window continues sliding on the variance matrix, the side direction rejection characteristic of the nerve cells in space is achieved and an edge matrix is obtained; finally, the edge matrix is mapped into a result image inversely. According to the image strong and weak edge detection method based on the spatio-temporal information responded by the dot matrix nerve cells, the spatio-temporal information responded by the dot matrix nerve cells is taken into consideration, the edges of the image can be detected and additionally, a strong and week relationship of the edges can be effectively reflected.

Description

The strong and weak edge detection method of image based on dot matrix neuron response space time information

Technical field

The invention belongs to image processing field, relate to a kind of strong and weak edge detection method of image based on dot matrix neuron response space time information.

Background technology

The edge of image refers to the place of color or gray-scale value generation transition, it has reflected the main information of image usually, therefore effective detection of the strong and weak marginal information of image, process and other relevant tasks for follow-up image, such as pattern-recognition, target following etc. are most important.Traditional Image Edge-Detection adopts roberts operator constant gradient method to be processed image, can detect the strong edge of image, but usually can lose weak details, sometimes can produce over-segmentation to image again.

Summary of the invention

For the problems referred to above, the present invention proposes a kind of strong and weak edge detection method of image based on dot matrix neuron response space time information, recorded in the method neuron corresponding to each pixel discharge time first, utilize the order that in the receptive field window, each neuron discharges first, and extract the marginal information of image in conjunction with the spatial character of neuron lateral inhibition, finally not only can effectively detect the edge of image, and can be by the strong and weak Informational Expression at edge out.

The present invention is based on the strong and weak detection method in image border of dot matrix neuron response space time information, comprise the following steps:

Step (1) is carried out 8 direction Log-Gabor filter process to image, and angle is respectively θ _i(θ _i=22.5 ⁰* i, i=0,1 ..., 7), then according to the filtering marginal information of reconstructed image as a result.

Step (2) is input to the dot matrix neuron by the reconstruction result in step (1).

Step (3) is recorded each neuronic discharge time first, then obtains corresponding time matrix.

The receptive field window that step (4) is constructed one 3 * 3 slips over this time matrix, first the time element in this receptive field window is sorted, be weighted according to ranking results, calculate the improvement variance of discharge time first, and by its assignment the central element to the receptive field window.Successively each element in time matrix is carried out to identical processing, then obtain variance matrix.

Step (5) makes 3 * 3 receptive field window of structure in step (4) slip over above-mentioned variance matrix, neuron in the receptive field window is carried out to side direction to be suppressed to process, need to carry out successively identical processing to each element in variance matrix equally, then obtain matrix of edge.

Step (6) is mapped to the data inverse in matrix of edge 0～255 scope, afterwards it is shown as to image, and this image is the Image Edge-Detection result, and comprises strong and weak marginal information.

The characteristics that the present invention has are: the method considers temporal information that the dot matrix neuron discharges first and the spatial information of receptive field window, not only can detect the edge of image, and can provide the strong or weak relation of image border, be embodied in following some:

1. introduce the time encoding mechanism of visual cortex neuron discharge pulse for visual stimulus in rim detection, utilized dot matrix neuronic discharge time first of information.

2. consider the existence of visual cortex neuron receptive field in rim detection, utilized the receptive field window to form the regional area of rim detection.

3. introduced the neuronic lateral inhibition mechanism of visual cortex in rim detection, to each neuron establishment side in the receptive field window to rejection characteristic.

4. the method that the present invention adopts and the working mechanism of vision system meet more, and acquired results is compared and can be retained more detailed information with classic method, more can meet the subjective assessment of vision system.

5. the method acquired results that the present invention adopts can embody the strong and weak information of image border.

The accompanying drawing explanation

Fig. 1 is the inventive method process flow diagram.

Embodiment

Below in conjunction with accompanying drawing 1, the invention will be further described, and in the middle of Fig. 1, I_old (i, j) means original input picture; f _k(i, j) (k=0,1 ..., 7) for through the Log-Gabor wave filter, take angle as θ _i(θ _i=22.5 ⁰* i, i=0,1 ..., 7) filtered result; Neuron (i, j) means the dot matrix neuron used; T (i, j) means to record the time matrix of discharge time first after the dot matrix neuron models; D (i, j) means the variance matrix of processing through variance; F (i, j) means the matrix of edge after neuron side direction inhibiting effect; I_new (i, j) means final result images.

The concrete steps of the inventive method are:

Step (1) make original image I _ old (i, j) (i=1,2 ..., M; J=1,2 ..., N) by the Log-Gabor wave filter, carry out pre-service, obtaining angle is θ _i(θ _i=22.5 ⁰* i, i=0,1 ..., 7) 8 direction results, be designated as f _k(i, j) (k=0,1 ..., 7).Then utilize the marginal information of formula (1) reconstructed image:

$\mathrm{result}(i,j)=\underset{k=0}{\overset{7}{\mathrm{\Σ}}}{f}_k(i,j)(i=\mathrm{1,2},...,M;j=\mathrm{1,2},...,N)---\left(1\right)$

Step (2) structure dot matrix neuron Neuron (i, j) (i=1,2 ..., M; J=1,2 ..., N), the neuronic model of each dot matrix, suc as formula shown in (2), is input to dot matrix neuron Neuron (i, j) by the reconstruction result result (i, j) in step (1) and is processed.

$\left\{\begin{array}{c}\frac{\mathrm{dv}}{\mathrm{dt}}={0.04v}^2+5v+140-u+I_{\mathrm{ext}}\\ \frac{\mathrm{du}}{\mathrm{dt}}=a(\mathrm{bv}-u)\\ \mathrm{ifv}\≥v_{\mathrm{thresh}},\mathrm{thenv}\←u\←u+d\end{array}\right.---\left(2\right)$

Wherein, v is membrane potential of neurons, and u represents that neuron membrane recovers variable.I _extinput stimulus, i.e. corresponding reconstruction result result (i, j), a, b, c and d are model parameter, v _threshfor threshold value, be set to a=0.02, b=0.2, c=-65, d=6, v _thresh=30.If v is more than or equal to v _thresh, neuron is provided pulse, produces electric discharge, and v is reset to c simultaneously, and u is reset as u+d; Otherwise neuron is not provided pulse.

Step (3) record each dot matrix neuron Neuron (i, j) (i=1,2 ..., M; J=1,2 ..., discharge time first N), thus obtain a time matrix T (i, j) (i=1,2 ..., M; J=1,2 ..., N).

It is corresponding with 3 * 3 regional areas of time matrix T (i, j) that step (4) is constructed the receptive field window of 3 * 3, and time element corresponding in the receptive field window is carried out to ascending sort, is designated as Templet (i), i=1, and 2 ... 9.Then to the variance after the time element computed improved of this receptive field window, shown in (3).

$\left\{\begin{array}{c}\mathrm{average}=\left(\underset{i=1}{\overset{9}{\mathrm{\Σ}}}\mathrm{templet}\left(i\right)\right)/9\\ \mathrm{sum}=\underset{i=1}{\overset{9}{\mathrm{\Σ}}}[{(\mathrm{templet}\left(i\right)-\mathrm{average})}^2*e^{(-i)}]\end{array}\right.---\left(3\right)$

Average is the mean value of each time element in the receptive field window.Sum is the improvement variance of sequence after weighting of discharging first, the central point by its assignment to the receptive field window.The receptive field window is slipped over to time matrix T (i, j) successively, to each time element carry out same processing just obtain variance matrix D (i, j) (i=1,2 ..., M; J=1,2 ..., N).

Step (5) is utilized 3 * 3 receptive field window of step (4) structure, makes its 3 * 3 regional areas with variance matrix D (i, j) corresponding, in the receptive field window, according to formula (4), realizes that neuronic side direction suppresses machine-processed.

$w_0=\left\{\begin{array}{ccc}{w}_0*e^{-(w_0/w_1)},& \mathrm{if}& w_0>w_1\\ w_0*e^{(w_1/w_0)},& \mathrm{if}& w_0>w_1\\ w_0,& \mathrm{if}& w_0=w_1\end{array}\right.$ (4)

$w_1=\left\{\begin{array}{ccc}{w}_1=w_1*e^{(w_0/w_1)},& \mathrm{if}& w_0<w_1\\ w_1=w_1*e^{-(w_1*w_0)},& \mathrm{if}& w_0>w_1\\ w_1=w_1,& \mathrm{if}& w_0=w_1\end{array}\right.$

W ₀the central element in the receptive field window, w ₁represent the non-central element in the receptive field window.The receptive field window is slipped over to variance matrix D (i, j) successively, to each variance element carry out same processing just obtain matrix of edge F (i, j) (i=1,2 ..., M; J=1,2 ..., N).

Step (6) is mapped to the matrix of edge data inverse according to formula (5) 0～255 scope, and then it is shown as to image I _ new (i, j), is the testing result that comprises the strong and weak marginal information of image.

$I\_\mathrm{new}(i,j)=\frac{(F(i,j)-\min )}{(\max -\min )}*255---\left(5\right)$

Wherein min and max are respectively minimum value and the maximal value in matrix of edge F (i, j), the testing result at the strong and weak edge of I_new (i, j) presentation video.

In sum, the present invention has considered following factor: can lose detailed information a little less than some when (1) traditional edge detection method is processed image, or carry out over-segmentation, thereby can't tell original marginal information; (2) traditional edge detection method adopts the method for binaryzation to show image border usually, does not consider the strong or weak relation at edge; (3) traditional edge detection method adopts operator to carry out marginal information to obtain, do not consider the physiological property of vision system, and the result therefore drawn is difficult to be consistent with people's subjective assessment usually.Therefore, the present invention is based on the space time information of dot matrix neuron response, the strong and weak detection method in a kind of image border based on vision physiological is proposed, make the image after processing not only can retain more detailed information, and power that can the represent images edge, result can be consistent with people's subjective assessment.

Claims (1)

1. the strong and weak edge detection method of image based on dot matrix neuron response space time information, is characterized in that the method comprises the steps:

Step (1) is carried out 8 direction Log-Gabor filter process to image, and angle is respectively

, , then according to the filtering marginal information of reconstructed image as a result;

Step (2) is input to the dot matrix neuron by the reconstruction result in step (1);

Step (3) is recorded each neuronic discharge time first, then obtains corresponding time matrix;

The receptive field window that step (4) is constructed one 3 * 3 slips over above-mentioned time matrix, first the time element in this receptive field window is sorted, be weighted according to ranking results, calculate the improvement variance of discharge time first, and by its assignment the central element to the receptive field window; Successively each element in time matrix is carried out to identical processing, then obtain variance matrix;

Step (5) makes 3 * 3 receptive field window of structure in step (4) slip over above-mentioned variance matrix, neuron in the receptive field window is carried out to side direction to be suppressed to process, need to carry out successively identical processing to each element in variance matrix equally, then obtain matrix of edge;

Step (6) is mapped to the data inverse in matrix of edge 0～255 scope, afterwards it is shown as to image, and this image is the Image Edge-Detection result, and comprises strong and weak marginal information.

Images