Improved non-classical receptive field-based bionic contour detection method

Abstract

The invention aims to provide an improved non-classical receptive field-based bionic contour detection method. The method comprises the following steps of A, inputting a to-be-detected image subjectedto grayscale processing; B, presetting a Gabor filtering function containing multiple direction parameters, performing classical receptive field stimulus response on each pixel point in the to-be-detected image, wherein a corresponding direction serves as an optimal direction of the pixel point; C, building an inhibitory kernel function by utilizing a log function, building a distance weight function through the inhibitory kernel function, and performing convolution on the classical receptive field stimulus response of the pixel point and the distance weight function of the pixel point to obtain inhibitory response of the pixel point; and D, subtracting a product of the inhibitory response of the pixel point and preset inhibitory intensity from the classical receptive field stimulus response of each pixel point, and performing calculation to obtain a final contour value of the pixel point. The detection method overcomes the defects of the prior art and has the characteristics of meeting spatial characteristics of visual receptive field and having a better detection effect.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a bionic contour detection method based on improved non-classical receptive fields. Background technique [0002] For non-classical receptive field regions, there are many models of different inhibition situations. The traditional butterfly suppression model, on the basis of the DoG suppression model, completes the suppression of background texture information by artificially limiting the areas of the side region and the end region; such a butterfly suppression kernel is manually divided into regions, First of all, it is necessary to divide the non-classical receptive field into the flank and top area by the alignment of ±45°, so as to obtain a butterfly-shaped inhibition model of the non-automatically delineated area. In the butterfly suppression model, the side region and the end region have different working rules, that is, the calculation of the side region suppression streng...

AI Technical Summary

Problems solved by technology

The traditional butterfly suppression model cannot realize the automatic division of the suppression area and the suppression model uses the optimal direction of the pixel to rotate reasonably, so the time cost of the entire contour detection process is greatly increased

Images