The Improved Canny Edge Detection Algorithm Based on an Anisotropic and Genetic Algorithm

Edge detection plays a crucial role in image processing. This paper proposes an improved Canny edge detection algorithm to deal with existing problems in traditional algorithms. Firstly, we use the anisotropic filter to denoise original grayscale images. This method can effectively suppress noise and preserve the edge feature. Secondly, the paper searches optimizing high and low thresholds used in Canny operator utilizing genetic algorithm based on the Otsu evaluative function to avoid human factors. In our experiment, we got the optimizing value (227, 84), and the interclass variance (3833) for image Lena. Compared with the traditional operator, this improved algorithm can reduce the false positive rate and improve the accuracy of detection. Meanwhile, the experiment shows that the algorithm is also robust in pedestrian detection.