This paper pertains to the recognition of human face within the color images. The proposed scheme used the clue of skin color to detect faces within the color images, and Mallat wavelet transform was applied to get the LL2 frequency subband image of the original faces, then, features were extracted from the raw data by using principal component analysis (PCA). These discriminative and low dimensional features achieved were fed to a support vector machines (SVMs) with polynomial kernel for the training and fuzzy theory was applied on multi-class classification to deal with the unclassifiable cases. Experiments were conducted using the indoors photographs and the results demonstrated that the proposed methodology was efficient for the frontal faces detection and recognition.
Face recognition in color images using principal component analysis and fuzzy support vector machines
01.01.2006
1141596 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Face Recognition Using Modular Principal Component Analysis and Support Vector Machines
British Library Conference Proceedings | 2006
|Support vector machines for face recognition
British Library Online Contents | 2001
|Face Recognition with Support Vector Machines: Global versus Component-based Approach
British Library Conference Proceedings | 2001
|