Approaching the computational color constancy as a classification problem through deep learning

DOI10.1016/J.PATCOG.2016.08.013MaRDI QIDQ2289609zbMATH OpenOpenAlexFDO

Authors Seoung Wug Oh, Seon Joo Kim

Publication date 23 January 2020

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1608.07951

zbMATH Keywords

machine learningconvolutional neural networkillumination estimationcomputational color constancywhite balancing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Machine vision and scene understanding (68T45)

Abstract: Computational color constancy refers to the problem of computing the illuminant color so that the images of a scene under varying illumination can be normalized to an image under the canonical illumination. In this paper, we adopt a deep learning framework for the illumination estimation problem. The proposed method works under the assumption of uniform illumination over the scene and aims for the accurate illuminant color computation. Specifically, we trained the convolutional neural network to solve the problem by casting the color constancy problem as an illumination classification problem. We designed the deep learning architecture so that the output of the network can be directly used for computing the color of the illumination. Experimental results show that our deep network is able to extract useful features for the illumination estimation and our method outperforms all previous color constancy methods on multiple test datasets.

Recommendations

• A new colour constancy algorithm based on automatic determination of gray framework parameters using neural network
• Machine learning approach to color constancy
• Automatic color constancy algorithm selection and combination
• Neural network for color constancy
• Generalized gamut mapping using image derivative structures for color constancy

Cites work

• Automatic color constancy algorithm selection and combination
• Computational Color Constancy: Survey and Experiments
• Evaluating Combinational Illumination Estimation Methods on Real-World Images
• Generalized gamut mapping using image derivative structures for color constancy
• Improving Color Constancy Using Indoor–Outdoor Image Classification
• Visualizing data using t-SNE

Cited in

(8)

• Generalized gamut mapping using image derivative structures for color constancy
• Machine learning approach to color constancy
• A new colour constancy algorithm based on automatic determination of gray framework parameters using neural network
• Investigation of color constancy with a neural network
• A Data Set for Camera-Independent Color Constancy
• Computer Vision - ECCV 2004
• Computational Color Constancy: Survey and Experiments
• Automatic color constancy algorithm selection and combination

Describes a project that uses

Uses Software

• t-SNE

This page was built for publication: Approaching the computational color constancy as a classification problem through deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2289609)