Evaluating color texture descriptors under large variations of controlled lighting conditions

TL;DR

This paper compares various color texture descriptors, including traditional and neural network features, to assess their robustness under large variations in lighting conditions using a new comprehensive food texture database.

Contribution

It provides an extensive evaluation of texture features with and without color normalization under diverse lighting variations, highlighting their relative robustness.

Findings

Neural network features show higher robustness to lighting changes.

Color normalization improves descriptor stability under varying conditions.

Traditional statistical descriptors are less effective under large lighting variations.

Abstract

The recognition of color texture under varying lighting conditions is still an open issue. Several features have been proposed for this purpose, ranging from traditional statistical descriptors to features extracted with neural networks. Still, it is not completely clear under what circumstances a feature performs better than the others. In this paper we report an extensive comparison of old and new texture features, with and without a color normalization step, with a particular focus on how they are affected by small and large variation in the lighting conditions. The evaluation is performed on a new texture database including 68 samples of raw food acquired under 46 conditions that present single and combined variations of light color, direction and intensity. The database allows to systematically investigate the robustness of texture descriptors across a large range of variations of imaging conditions.