Modeling Colors of Single Attribute Variations with Application to Food Appearance

TL;DR

This paper analyzes how single-source variations affect object colors in images, revealing planar subspaces in RGB and applying this to food appearance for tasks like recognition and segmentation.

Contribution

It introduces a geometric analysis of color variations under single-source changes and demonstrates its effectiveness in food image recognition and segmentation.

Findings

Colors lie on a planar subspace in RGB

Linear or polynomial curves effectively model color variations

Inter-image color sub-spaces are robust under consistent illumination

Abstract

This paper considers the intra-image color-space of an object or a scene when these are subject to a dominant single-source of variation. The source of variation can be intrinsic or extrinsic (i.e., imaging conditions) to the object. We observe that the quantized colors for such objects typically lie on a planar subspace of RGB, and in some cases linear or polynomial curves on this plane are effective in capturing these color variations. We also observe that the inter-image color sub-spaces are robust as long as drastic illumination change is not involved. We illustrate the use of this analysis for: discriminating between shading-change and reflectance-change for patches, and object detection, segmentation and recognition based on a single exemplar. We focus on images of food items to illustrate the effectiveness of the proposed approach.