The Application Study on the Improved Canny Algorithm for Edge Detection in Fundus Image

摘要

Edge detection is one of important contents in image procession. And Canny algorithm is the classic algorithm applied widely to the edge detection. Based on the defects of Canny edge detector, an improved Canny edge detector was presented to obtain thin and robust edge and implemented the algorithm in fundus image. Firstly, nonlinear diffusion filter was adopted to wipe of noise efficiently and kept the edge information of the image. Secondly, gradient calculation of pixel diagonal direction was considered in the calculation of neighborhood gradient amplitude which further repressed the impact of noise. Finally, by using average interclass variance, the self-adaptively double thresholds for different images were calculated. Aimed at the fundus image including noise, the experimental results show that the improved algorithm performs a better accuracy and precision than the classic Canny algorithm.