Application of Improved Canny Algorithm in Image Edge Detection

To solve the problems of poor denoising effect and limited threshold accuracy in traditional Canny algorithm, an improved Canny algorithm is proposed in this paper. Firstly, an image preprocessing method based on hybrid filtering is developed. On the basis of Gaussian filtering, the adaptive median filtering is adopted to denoise the image, and homomorphic filtering is used to enhance the high frequency information of image in the frequency domain. Besides, Sobel operator is used instead of Roberts operator to calculate the gradient amplitude and direction of the image. Finally, an iterative threshold selection method combining MEM and Otsu is proposed. After obtaining the high and low thresholds by MEM and Otsu respectively, the optimal threshold is calculated using iterative algorithm, which can improve the accuracy and adaptability of threshold. It is proved that the proposed algorithm can preserve the image details while ensuring the denoising effect, and the detected edges have better connectivity and smoothness.