文献类型：期刊文献

英文题名：Constrained low-rank gamut completion for robust illumination estimation

作者：Zhou, Jianshen[1];Yuan, Jiazheng[2,3];Liu, Hongzhe[2]

第一作者：Zhou, Jianshen

通讯作者：Zhou, JS[1]

机构：[1]Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing, Peoples R China;[2]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China;[3]Beijing Union Univ, Comp Technol Inst, Beijing, Peoples R China

第一机构：Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing, Peoples R China

通讯机构：[1]corresponding author), Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing, Peoples R China.

年份：2017

卷号：56

期号：2

外文期刊名：OPTICAL ENGINEERING

收录：;EI(收录号：20170803372823);Scopus(收录号：2-s2.0-85013187928);WOS:【SCI-EXPANDED(收录号:WOS:000397206800003)】；

基金：This paper was supported by the following projects: the National Natural Science Foundation of China (Nos. 71373023, 61372148, and 61571045), Beijing Natural Science Foundation (Nos. 4152016 and 4152018), Beijing Advanced Innovation Center for Imaging Technology (BAICIT-2016002), and the National Key Technology R&D Program (2014BAK08B02 and 2015BAH55F03).

语种：英文

外文关键词：color constancy; illumination estimation; low rank

摘要：Illumination estimation is an important component of color constancy and automatic white balancing. According to recent survey and evaluation work, the supervised methods with a learning phase are competitive for illumination estimation. However, the robustness and performance of any supervised algorithm suffer from an incomplete gamut in training image sets because of limited reflectance surfaces in a scene. In order to address this problem, we present a constrained low-rank gamut completion algorithm, which can replenish gamut from limited surfaces in an image, for robust illumination estimation. In the proposed algorithm, we first discuss why the gamut completion is actually a low-rank matrix completion problem. Then a constrained low-rank matrix completion framework is proposed by adding illumination similarities among the training images as an additional constraint. An optimization algorithm is also given out by extending the augmented Lagrange multipliers. Finally, the completed gamut based on the proposed algorithm is fed into the support vector regression (SVR)-based illumination estimation method to evaluate the effect of gamut completion. The experimental results on both synthetic and real-world image sets show that the proposed gamut completion model not only can effectively improve the performance of the original SVR method but is also robust to the surface insufficiency in training samples. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)