A Method for Enforcing Integrability in Shape from Shading Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape and motion from image streams under orthography: a factorization method
International Journal of Computer Vision
On Photometric Issues in 3D Visual Recognition from aSingle 2D Image
International Journal of Computer Vision
Linear Object Classes and Image Synthesis From a Single Example Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
What Is the Set of Images of an Object Under All Possible Illumination Conditions?
International Journal of Computer Vision
International Journal of Computer Vision
The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations
IEEE Transactions on Pattern Analysis and Machine Intelligence
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose
IEEE Transactions on Pattern Analysis and Machine Intelligence
Symmetric Shape-from-Shading Using Self-ratio Image
International Journal of Computer Vision
Incremental Singular Value Decomposition of Uncertain Data with Missing Values
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Face Identification by Fitting a 3D Morphable Model Using Linear Shape and Texture Error Functions
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Learning bilinear models for two-factor problems in vision.
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Eigen Light-Fields and Face Recognition Across Pose
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
The CMU Pose, Illumination, and Expression (PIE) Database
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Journal of Cognitive Neuroscience
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition under arbitrary illumination using illuminated exemplars
Pattern Recognition
Illumination-robust face recognition using ridge regressive bilinear models
Pattern Recognition Letters
Facial Shape-from-shading and Recognition Using Principal Geodesic Analysis and Robust Statistics
International Journal of Computer Vision
Identity Management in Face Recognition Systems
Biometrics and Identity Management
Probabilistic identity characterization for face recognition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Illuminating light field: image-based face recognition across illuminations and poses
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
A novel illumination normalization method for face recognition
IWBRS'05 Proceedings of the 2005 international conference on Advances in Biometric Person Authentication
Class dependent factor analysis and its application to face recognition
Pattern Recognition
Real-time face detection and recognition on LEGO mindstorms NXT robot
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
| Hi-index | 0.00 |
Recognition under illumination variations is a challenging problem.The key is to successfully separate the illumination source fromthe observed appearance. Once separated, what remains is invariantto illuminant and appropriate for recognition. Most current effortsemploy a Lambertian reflectance model with varying albedo fieldignoring both attached and cast shadows, but restrict themselves byusing object-specific samples, which undesirably deprives them ofrecognizing new objects not in the training samples. Using rankconstraints on the albedo and the surface normal, we accomplishillumination separation in a moregeneral setting, e.g., withclass-specific samples via a factorization approach. In addition,we handle shadows (both attached and cast ones) by treating them asmissing values, and resolve the ambiguities in the factorizationmethod by enforcing integrability. As far as recognition isconcerned, a bootstrap set which is just a collection of 2D imageobservations can be utilized to avoid the explicit requirement that3D information be available. Our approaches produce goodrecognition results as shown in our experiments usingthe PIEdatabase.