An effective information detection algorithm for low-light images based on the visual perception characteristics of the human eye

To solve the problems of low contrast and less effective information of the low-light images, we proposed an effective information detection algorithm based on the visual perception characteristics of the human eye. First, the original image is double-sided filtered to reduce noise and edge preservation. Then, it is converted into the YUV color gamut, and the brightness mapping function is designed to map the brightness channel Y. During the specific mapping process, the overall dark image and the chiaroscuro image are classified according to the brightness variance of the whole image. Different brightness function mappings are designed for each image according to the visual perception characteristics of the human eye so as to realize adaptive brightness enhancement. Experimental results show that the proposed algorithm outperforms the existing algorithms in terms of subjective human eye experience, compared with histogram equalization and the MSR algorithm. It improves the PSNR (peak signal-to-noise ratio), SSIM (structural similarity index metric), and UQI (universal quality index) image quality evaluation indexes by 19.40, 1.17, and 0.77, respectively.