Color constancy using CNNs
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21607508,p. 81-89
Abstract
In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods. The network consists of one convolutional layer with max pooling, one fully connected layer and three output nodes. Within the network structure, feature learning and regression are integrated into one optimization process, which leads to a more effective model for estimating scene illumination. This approach achieves state-of-the-art performance on a standard dataset of RAW images. Preliminary experiments on images with spatially varying illumination demonstrate the stability of the local illuminant estimation ability of our CNN.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Computational Color Constancy: Survey and ExperimentsIEEE Transactions on Image Processing, 2011
- Color Constancy Using Natural Image Statistics and Scene SemanticsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Generalized Gamut Mapping using Image Derivative Structures for Color ConstancyInternational Journal of Computer Vision, 2008
- A Spatially Variant White-Patch and Gray-World Method for Color Image Enhancement Driven by Local ContrastIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Bayesian color constancy revisited2008
- Color constancy based on local space average colorMachine Vision and Applications, 2008
- Edge-Based Color ConstancyIEEE Transactions on Image Processing, 2007
- Using High-Level Visual Information for Color Constancy2007
- Color by correlation: a simple, unifying framework for color constancyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- A novel algorithm for color constancyInternational Journal of Computer Vision, 1990