Edge detection algorithm of plant leaf image based on improved Canny

Edge detection technology is a key technology in the field of image processing. Aiming at the problem that traditional Canny algorithm has poor adaptive ability and cannot effectively determine image edge, this paper proposes an improved Canny edge detection algorithm. The algorithm uses an improved filtering method to de-noise the image. Secondly, the four-direction gradient template is used to calculate the gradient amplitude. Finally, the high and low thresholds of images are obtained by image block processing combined with the maximum inter-class variance (Otsu) algorithm. The experimental results show that the improved Canny algorithm has good noise reduction performance and can detect the edge information of plant leaves more accurately.