Which Features Are More Correlated to Illuminant Estimation: A Composite Substitute

Yunhui Luo,Qing Wang,Xingguang Wang

doi:10.3390/app12031175

Yunhui Luo, Qing Wang + Show 1 more

Open Access

https://doi.org/10.3390/app12031175

Copy DOI

Abstract

Computational color constancy (CCC) is to endow computers or cameras with the capability to remove the color bias effect caused by different scene illuminations. The first procedure of CCC is illuminant estimation, i.e., to calculate the illuminant color for a given image scene. Recently, some methods directly mapping image features to illuminant estimation provide an effective and robust solution for this issue. Nevertheless, due to diverse image features, it is uncertain to select which features to model illuminant color. In this research, a series of artificial features weaved into a mapping-based illuminant estimation framework is extensively investigated. This framework employs a multi-model structure and integrates the functions of kernel-based fuzzy c-means (KFCM) clustering, non-negative least square regression (NLSR), and fuzzy weighting. By comparing the resulting performance of different features, the features more correlated to illuminant estimation are found in the candidate feature set. Furthermore, the composite features are designed to achieve the outstanding performances of illuminant estimation. Extensive experiments are performed on typical benchmark datasets and the effectiveness of the proposed method has been validated. The proposed method makes illuminant estimation an explicit transformation of suitable image features with regressed and fuzzy weights, which has significant potential for both competing performances and fast implementation against state-of-the-art methods.

Highlights

The human vision system possess an innate “color constancy” capability, i.e., to dismount effects from the illuminant color and perceive the true color of an object [1,2].computers and imaging signal processors in vision applications do not have this capability if not to perform specific algorithms
Gray world (GW) [4,5], White patch (WP) [6], Shades of gray (SoG) [7], Gray edge (GE) [8], etc., belong to the first group—statistics-based methods, which take account of some image statistical features that are kept consistent in the image captured under canonical illuminating environments
(1) We develop an approach to estimate illuminant color, which includes kernel-based fuzzy c-means clustering (KFCM), optimization-based model regression, and fuzzy weighting combination

Summary

Introduction

The human vision system possess an innate “color constancy” capability, i.e., to dismount effects from the illuminant color and perceive the true color of an object [1,2].computers and imaging signal processors in vision applications do not have this capability if not to perform specific algorithms. The unitary algorithms (i.e., the first two groups) just use a single strategy for illuminant estimation by assuming some color distribution features or learning general models from the training dataset, while the combination methods integrate the estimates from unitary algorithms into a single, final estimate. All these three groups of estimation methods usually suffer from either estimation accuracy, or computational efficiency, and result in better performances just for some specific image scenes.

Methods

Results

Discussion

Conclusion