Improved edge detection algorithm for canny operator
Yibo Li, Bailun Liu
Abstract
Canny edge detection algorithm is widely used in many fields.but the problem of noise pollution in the actual working environment, the effect of image edge detection is susceptible to the pepper salt noise, and the results of Canny algorithm detect fault and lost edge details. In order to remove pepper salt noise from the image and extract edge information of the area of interest from the image, an image edge detection algorithm based on improving Canny operator is proposed. The proposed algorithm designs a novel filter to replace the Gaussian filter in the traditional algorithm to filter the pepper and salt noise in the picture. The original algorithm uses only a gradient template in both horizontal and vertical directions in calculating the image gradient, while the improved algorithm adds the gradient templates in both 45°and 135°. Finally, the maximum inter-class variance method is adopted to determine the optimal threshold when making the high and low threshold connection. It can be seen that in edge detecting the image with pepper salt noise, the proposed algorithm can effectively filter the pepper salt noise in the picture, and the edge detection results are more accurate without losing detail.