Modeling Colors of Single Attribute Variations with Application to Food Appearance
This work addresses the problem of robust color modeling for computer vision applications, particularly in food appearance analysis, but it is incremental as it builds on existing subspace and curve-fitting methods.
The paper tackles the problem of modeling color variations in images where objects or scenes are subject to a dominant single-source variation, such as intrinsic or extrinsic factors, by observing that quantized colors often lie on planar subspaces in RGB space, with linear or polynomial curves capturing these variations effectively. It applies this analysis to tasks like discriminating shading-change vs. reflectance-change for patches, and object detection, segmentation, and recognition based on a single exemplar, demonstrating effectiveness on food images.
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.