Illumination insensitive eigenspaces

Abstract

Variations in illumination can have a dramatic effect on the appearance of an object in an image. In this pa- per we propose how to deal with illumination variations in eigenspace methods. We demonstrate that the eigenimages obtained by a training set under a single illumination con- dition (ambient light) can be used for recognition of objects taken under different illumination conditions. The major idea is to incorporate a set of gradient based$lter banks into the eigenspace recognition framework. This can be achieved since the eigenimage coeficients are invariant for linearly3ltered images (input and eigenimages). To achieve further illumination insensitivity we devised a robust proce- dure for coeficient recovery. The proposed approach has been extensively evaluated on a set of 2160 images and the results were compared to other approaches.