Title :
New Face Recognition Method Based on DWT/DCT Combined Feature Selection
Author :
Yu, Ming ; Yan, Gang ; Zhu, Qing-wen
Author_Institution :
Sch. of Comput. Sci., Hebei Univ. of Technol., Tianjin
Abstract :
A new face recognition method is proposed based on DWT/DCT combined feature selection. The combination of the DWT and the DCT is used to extract features of face images. This reduces the dimension of the original face image and preserves the property of data distribution in the feature subspace. Then the support vector machine (SVM) based on the structural risk minimization principle is used to classify these feature vectors. The new strategy is tested on ORL face databases and the results demonstrate that it performs very well compared with other approaches
Keywords :
discrete cosine transforms; discrete wavelet transforms; face recognition; feature extraction; image classification; risk analysis; support vector machines; visual databases; DWT/DCT combined feature selection; ORL face databases; discrete cosine transform; discrete wavelet transform; face image feature extraction; face recognition method; feature vector classification; structural risk minimization principle; support vector machine; Data mining; Discrete cosine transforms; Discrete wavelet transforms; Face recognition; Feature extraction; Image databases; Risk management; Support vector machine classification; Support vector machines; Testing; Face recognition; binary tree; discrete cosine transform; discrete wavelet transform; feature extraction; support vector machine;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258432
