Total variation models for variable lighting face recognition
Top Cited Papers
- 24 July 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 28 (9) , 1519-1524
- https://doi.org/10.1109/tpami.2006.195
Abstract
In this paper, we present the logarithmic total variation (LTV) model for face recognition under varying illumination, including natural lighting conditions, where we rarely know the strength, direction, or number of light sources. The proposed LTV model has the ability to factorize a single face image and obtain the illumination invariant facial structure, which is then used for face recognition. Our model is inspired by the SQI model but has better edge-preserving ability and simpler parameter selection. The merit of this model is that neither does it require any lighting assumption nor does it need any training. The LTV model reaches very high recognition rates in the tests using both Yale and CMU PIE face databases as well as a face database containing 765 subjects under outdoor lighting conditionsKeywords
This publication has 38 references indexed in Scilit:
- Brightness perception,dynamic range and noise: a unifying model for adaptive image sensorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- A comparison of photometric normalisation algorithms for face verificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- The CMU Pose, Illumination, and Expression (PIE) databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Illumination normalization for robust face recognition against varying lighting conditionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- On the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian objectJournal of the Optical Society of America A, 2001
- A signal-processing framework for inverse renderingPublished by Association for Computing Machinery (ACM) ,2001
- The quotient image: class-based re-rendering and recognition with varying illuminationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992
- Scale-space and edge detection using anisotropic diffusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Image processing in the context of a visual modelProceedings of the IEEE, 1972