Aiming at the problems of over enhancement, color distortion, and severe loss of details that are prone to occur when traditional histogram equalization algorithms are used for dark image enhancement, a dynamic histogram equalization based optimization method for dark image enhancement algorithm is proposed. Firstly, the bilateral filtering algorithm is used to filter out the noise contained in the image and ensure that the edge features of the image are not lost; Secondly, the denoised dark image is subjected to color channel splitting, and adaptive segmentation points for each channel histogram are calculated to achieve adaptive histogram splitting. Based on this, a dynamic histogram equalization algorithm is obtained to adjust the brightness of the image; Then, the Multi-scale Retinex with Color Restoration (MSRCR) algorithm is used to perform multi-scale Retinex processing on each channel image, enhancing local detail information and achieving color restoration of the image; Finally, the improved Gamma correction algorithm is applied to enhance the contrast of the entire image and achieve dark light image enhancement. The experimental results show that the algorithm can enhance dark light images, resulting in full color, rich layers, clear and distinguishable details and edge information, and significantly improved image quality.
带色彩恢复的多尺度视网膜增强(Multi ⁃scale retinex with color restoration,MSRCR)算法通过模拟人眼对光线的处理机制,对图像进行多尺度的Retinex滤波处理,并在此基础上引入颜色恢复功能,以保持图像色彩的自然性。本文利用MSRCR算法处理去噪以及亮度调整后的暗光图像,达到图像细节增强以及色彩恢复的目的。MSRCR算法的处理公式为:
LiangLi-ming, ZhuChen-kun, YangYuan, et al. Cross-level feature adaptive fusion network for low-light image enhancement[J]. Chinese Journal of Liquid Crystals and Displays, 2024, 39(6): 856-866.
FengXin, WangSi-ping, ZhangZhi-xian, et al. Dark light image enhancement network for machine vision perception[J]. Application Research of Computers, 2024, 41(6): 1910-1915.
WangDeng-fei, SuHong-sheng, ChenGuang-wu, et al. Real time low light enhancement method of TEDS images based on focused linear attention Retinexformer[J]. Journal of Railway Science and Engineering, 2024, 21(11): 4840-4850.
LuLu, JiangXin, YangJin-cheng, et al. Adaptive guided filtering based infrared image detail enhancement[J]. Chinese Journal of Liquid Crystals and Displays, 2022, 37(9): 1182-1189.
MiaoZuo-hua, ZhuLiang-jian, ZhaoCheng-cheng, et al. Image enhancement of low-light parking space based on Retinex[J]. Automotive Engineering,2023, 45(6): 989-996.
[15]
WangY, XieW, LiuH. Low-light image enhancement based on deep learning: a survey[J]. Optical Engineering, 2022, 61(4): 1-20.
JiangJu-lang, LiuGuo-ming, ZhuZhu, et al. Dynamic multi-histogram equalization based on fast fuzzy clustering[J]. Acta Electronica Sinica, 2022, 50(1): 167-176.
HeZhi-bo, ZengXiang-jin, DengChen, et al. Infrared image enhancement based on local entropy-local contrast and dual-area histogram equalization[J]. Infrared Technology, 2023, 45(6): 598-604.
GuWen-juan, DengCan, WeiJin, et al. Low-light image enhancement based on the fusion of Bilateral filter MSR and AutoMSRCR[J]. Optics and Precision Engineering, 2023, 31(24): 3606-3617.
GuoCheng, HuXiao-ping, PengXiang-qian, et al. Improved MSRCR algorithm for backlight image enhancement of transparent objects[J]. Chinese Journal of Sensors and Actuators,2024, 37(4): 645-651.