文献类型：期刊文献

英文题名：Non-Uniform Illumination Underwater Image Enhancement via Minimum Weighted Error Entropy Loss

作者：Ma, Haiping[1];Sun, Shengyi[1];Ye, Senggang[1];Jiang, Zheheng[2]

机构：[1]Shaoxing Univ, Dept Elect Engn, Shaoxing 312000, Zhejiang, Peoples R China;[2]Univ Lancaster, Dept Comp & Commun, Lancaster LA1 4YW, England

年份：2023

卷号：30

起止页码：1187

外文期刊名：IEEE SIGNAL PROCESSING LETTERS

收录：SCI-EXPANDED(收录号：WOS:001064498300001)、、EI(收录号：20233614686586)、Scopus(收录号：2-s2.0-85169698934)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61640316, and in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LY19F030011.

语种：英文

外文关键词：Lighting; Reflectivity; Training; Image enhancement; Image decomposition; Generative adversarial networks; Entropy; Underwater image enhancement; non-uniform illumination; minimum error entropy; shot noise; generative adversarial network (GAN)

外文摘要：An effective enhanced unsupervised network based on minimum weighted error entropy (MWEE) loss is proposed for underwater image enhancement, which is one of the most challenging issues in computer vision. First, by the inspiration of Retinex theory, an underwater image is decomposed into non-uniform illumination and reflectance with shot noise. Then non-uniform illumination is modeled as an independent and piecewise identical (IPI) distribution, and shot noise in reflectance is seen as a single non-Gaussian distribution. Next, taking advantage of these two distributions, the MWEE criterion and its special case as training losses are embedded into a generative adversarial network (GAN) for piecewise uniformization of illumination and reflectance denoising. Experiments on underwater image enhancement datasets show the network enhanced by the proposed method obtains superior performance, and exhibits higher naturalness and better visual quality than several existing approaches.