Generalized quotient image
2004
173 citations
Abstract
We present a unified framework for modeling intrinsic properties of face images for recognition. It is based on the quotient image (QI) concept, in particular on the existing works of QI, spherical harmonic, image ratio and retinex. Under this framework, we generalize these previous works into two new algorithms: (1) non-point light quotient image (NPL-QI) extends QI to deal with non-point light sources by modeling non-point light directions using spherical harmonic bases; (2) self-quotient image (S-QI) extends QI to perform illumination subtraction without the need for alignment and no shadow assumption. Experimental results show that our algorithms can significantly improve the performance of face recognition under varying illumination conditions.
Keywords
QuotientShadow (psychology)Point (geometry)Artificial intelligenceImage (mathematics)Face (sociological concept)SubtractionComputer visionComputer scienceMathematicsAlgorithmArithmeticGeometryPure mathematics
Affiliated Institutions
Related Publications
Image Super-Resolution Via Sparse Representation
This paper presents a new approach to single-image super-resolution, based on sparse signal representation. Research on image statistics suggests that image patches can be well-...
Publication Info
- Year
- 2004
- Type
- article
- Volume
- 2
- Pages
- 498-505
- Citations
- 173
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
173
OpenAlex
Cite This
Haitao Wang,
S.Z. Li,
Yangsheng Wang
(2004).
Generalized quotient image.
, 2
, 498-505.
https://doi.org/10.1109/cvpr.2004.1315205
Identifiers
- DOI
- 10.1109/cvpr.2004.1315205