Probabilistic Visual Learning for Object Representation
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
From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Journal of Cognitive Neuroscience
Face recognition under varying lighting conditions using self quotient image
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Object recognition based on photometric alignment using ransac
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Combination of projectional and locational decompositions for robust face recognition
AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures
Hi-index | 0.00 |
This paper discusses Gaussian decomposition of facial images for robust recognition. While it cannot sufficiently extract an effective component, it can decompose an image into two effective components, the filtered image and its residual. The Gaussian component represents rough information for a lighting condition and small individuality. The residual represents individuality and the other information including small noise. The two components complement each other and they are evaluated independently in the framework of eigenface method. The image decomposition can also collaborate with parallel partial projections for robust recognition.