Abstract A methodology for determining the level of confidence of a sub-region in the overall classification of a given face image affected due to varying expressions, illuminations and partial occlusions is presented in this paper. The technique for obtaining the weights for each individual region of the test image is based on a measure of optical flow between that test image and a face model. Individual image regions or the modules are also assigned additional weights by arranging them in the order of their importance in classification. The approach presented is applicable mainly in scenarios where the number of samples in the training set is too little. A K-nearest neighbor distance measure is used in classifying each module of the test image after dimensionality reduction. A total score is calculated for each training class based on the classification result of each module and its associated weights. Considerable increase in recognition accuracy has been observed for PCA, LDA and ICA based linear subspace approaches when implemented using the proposed technique.
An Adaptive Weight Assignment Scheme in Linear Subspace Approaches for Face Recognition
Computer Vision – ACCV 2006 ; 7 ; 541-550
Lecture Notes in Computer Science ; 3852 , 7
2006-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Face Recognition , Test Image , Optical Flow , Face Image , Training Image Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
An Adaptive Weight Assignment Scheme in Linear Subspace Approaches for Face Recognition
British Library Conference Proceedings | 2006
|Unified Subspace Analysis for Face Recognition
British Library Conference Proceedings | 2003
|Random Sampling for Subspace Face Recognition
British Library Online Contents | 2006
|Nonparametric subspace analysis for face recognition
IEEE | 2005
|