Reflectance-Based Segmentation Using Photometric and Illumination Invariants

In this paper we propose a three-stage algorithm to implement effective segmentation of an object's counterparts when illumination variance is present. A color constancy algorithm and color-based invariant parameters insensitive to a large set of different illumination conditions are used. Then reflectance images are considered after discarding the shadowing information present in the images. A color-based segmentation algorithm using Graph Cuts is applied to the reflectance images. Improvements in the segmentation are obtained after using these illumination invariants.