基于色彩空间分解的低照度图像增强方法  

Low-illumination Image Enhancement Method Based on Color Space Decomposition

作　　者：王鹏[1] 宋存利[1,2] 纪守用 WANG Peng;SONG Cunli;JI Shouyong(College of Software,Dalian Jiaotong University,Dalian 116028,China;Artificial Intelligence Key Laboratory of Sichuan Province,Zigong 643000,China)

机构地区：[1]大连交通大学软件学院,辽宁大连116028 [2]人工智能四川省重点实验室,四川自贡643000

出　　处：《计算机与网络》2021年第6期68-73,共6页Computer & Network

基　　金：人工智能四川省重点实验室开放基金项目(2020RYJ04);辽宁省自然科学基金资助项目(20180551020);辽宁省教育厅资助项目(JDL2019011)。

摘　　要：针对低照度图像增强问题,提出一种基于色彩空间分解的图像增强算法。为了实现图像亮度和色彩的解耦合,将图像进行HSV空间转换;利用中值滤波算法与Retinex算法融合以及基于OTSU处理的自适应局部直方图均衡化,分别实现了亮度分量的增强和饱和度分量的校正。分层图像合成、图像降噪处理和色彩空间的转换,确保增强图像色彩的均匀和清晰度的提高。实验结果与其他几种经典算法相比较,算法获得的增强图像细节方面更为丰富,图像的清晰度更高。Aiming at the problem of low-illumination image enhancement, an image enhancement algorithm based on color space decomposition is proposed. Firstly, in order to decouple the brightness and color of the image, the enhancement of the luminance component and the correction of the saturation component are realized by using the fusion method of median filter algorithm and Retinex algorithm and the adaptive local histogram equalization based on OTSU processing. Finally, the layered image synthesis, image noise reduction and color space conversion ensure the uniformity and clarity of the enhanced image. Compared with other classical algorithms, the experimental results show that the enhanced image obtained by this algorithm has richer detail and higher definition.

关 键 词：图像增强 RETINEX 中值滤波 直方图均衡化 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]