Approaching the computational color constancy as a classification problem through deep learning
详细信息 查看全文
- 作者：Seoung Wug Oh sw.oh@yonsei.ac.kr" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Seon Joo Kim ; seonjookim@yonsei.ac.kr" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Computational color constancy ; White balancing ; Illumination estimation ; Machine learning ; Convolutional neural network
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：405-416
- 全文大小：4738 K
文摘
- •
A deep learning framework for the computational color constancy problem is proposed.
- •
Illumination is estimated by solving an illumination classification problem.
- •
Convolutional neural network is trained to solve the classification problem.
- •
The proposed method outperforms previous methods on multiple test datasets.