Approaching the Computational Color Constancy as a Classification Problem through Deep Learning

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.

This is a preprint of an article accepted for publication in Pattern Recognition, ELSEVIER

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Improving neural networks by preventing co-adaptation of feature detectors
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Color Constancy by Learning to Predict Chromaticity from Luminance

Cited by in corpus (8)

• Sensor-Independent Illumination Estimation for DNN Models
• INTEL-TUT Dataset for Camera Invariant Color Constancy Research
• The Cube++ Illumination Estimation Dataset
• Offset equivariant networks and their applications
• Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network
• Local Area Transform for Cross-Modality Correspondence Matching and Deep Scene Recognition
• OOOE: Only-One-Object-Exists Assumption to Find Very Small Objects in Chest Radiographs
• DeepIlluminance: Contextual Illuminance Estimation via Deep Neural Networks