A scaled multi gradient edge detection algorithm for infrared image detection
Qiang Gao, Xinxin Lv, Xiao Yi Yu · 2017
The paper applies a scaled multi-gradient edge detection algorithm to infrared criminal investigation images to extract the edge of the targets. It uses eight orientation detection templates to process the original image, which can reduce the lack of the edge details and improve the accuracy of edge extraction. Then using Otsu to scale the gradient information extracted from the former step, which can avoid the overflow of the gradient information. After the scaling process, the method which threshold value is used to obtain binary images will not be applied to gradient information processing. Then edge images are obtained. Proved by the experiments, the algorithm can achieve the decrease in the edge deletion for the edges whose gray scale changes are not fierce, and a great advance in the continuity and smoothness of edges. Not only the algorithm is simulated, but also the effect of edge extraction is quantitatively analyzed.