Image edge detection method

Abstract

The invention discloses an image edge detection method in the field of image detection. The method comprises the following steps of: acquiring an image by using a camera and then calculating gradient amplitude and direction by using a method for calculating first-order partial derivative difference of x direction and y direction in 12 neighborhood pixels, thereby suppressing noise in the image and preventing edge blur of the image; then establishing a mapping relation between inverse difference moment characteristic values of a gray level co-occurrence matrix and Gaussian space factors as well as thresholds, adaptively varying the Gaussian space factors and high and low thresholds of edge detection to guarantee continuous extraction of image edge points; and finally detecting the image edge points according to a non-local maximum inhibition principle, thereby improving accuracy of image edge detection.

Description

Technical field: [0001] The invention relates to image edge detection in the field of automation, in particular to a method for image edge detection, which is suitable for image texture feature analysis, image segmentation, and graphic feature extraction in the field of computer vision. Background technique: [0002] In order to improve the performance of image edge detection, Canny proposed in 1986 that an excellent edge detection operator should meet the following three criteria (John CANNY. A computational approach to edge detection [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1986, 8 (6): 679~698): (1) Good signal-to-noise ratio, that is, the probability that a non-edge point is misjudged as an edge point or an edge point is misjudged as a non-edge point is low, so that the output signal-to-noise ratio reaches (2) Good positioning performance, that is, the detected image edge point should be in the center of the actual image edge as much as possible; (3) Un...

AI Technical Summary

Problems solved by technology

However, the algorithm has the following three main disadvantages: (1) Canny operator only calculates the gradient amplitude by finding the mean value of finite difference in the 2×2 neighborhood. Although the edge location is accurate, the anti-noise ability is poor; (2) In the process of non-maximum value suppression, the Canny algorithm uses the gradient value of eight neighboring pixels to judge whether the current point has a local maximum value, which will affect the accuracy of edge detection; (3) the high and low thresholds of the Canny algorithm are both It is fixed, and the high and low thresholds are completely dependent on manual settings, so its degree of automation is low

Images