Illumination insensitive eigenspaces
- 13 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 233-238
- https://doi.org/10.1109/iccv.2001.937523
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.Keywords
This publication has 14 references indexed in Scilit:
- Separating reflections and lighting using independent components analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Robust recognition of scaled eigenimages through a hierarchical approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- In search of illumination invariantsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Eigenhill vs. eigenface and eigenedgePattern Recognition, 2001
- Robust Recognition Using EigenimagesComputer Vision and Image Understanding, 2000
- Appearance-based object recognition using optimal feature transformsPattern Recognition, 2000
- What Is the Set of Images of an Object Under All Possible Illumination Conditions?International Journal of Computer Vision, 1998
- On Photometric Issues in 3D Visual Recognition from a Single 2D ImageInternational Journal of Computer Vision, 1997
- Steerable wedge filters for local orientation analysisIEEE Transactions on Image Processing, 1996
- Illumination planning for object recognition using parametric eigenspacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994