Infrared Image Enhancement Algorithm based on Weighted Guided Filtering
Jiawei Luo, Yanmei Zhang
Abstract
Aiming at the problems of blurred details and over enhancement in traditional infrared image enhancement algorithms, an infrared image enhancement method based on guided weighted image filtering is proposed. Firstly, the gradient difference between the pixels around the image is used to find the isolated noise and the median filter is used to filter it; Then, the weighted guided image filter is used to decompose the image to obtain the basic component and detail component. The Contrast Limited Adaptive Histogram Equalization (CLAHE) is used to equalize the stretched contrast in the basic layer, and the nonlinear function is used to enhance and suppress the noise in the detail layer; Finally, different levels of results are fused to obtain contrast and detail enhanced infrared images. This method is used to simulate many groups of infrared images of different scenes, and compared with many enhancement methods. The results show that the proposed method has better results in infrared image detail and contrast enhancement.