Title :
A multi-resolutional face verification system via filter-based integration
Author :
Han, Chin-Chuan ; Tsai, Chang-Lung
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Chung-Hua Univ., Hsinchu, Taiwan
Abstract :
The authors build up a face verification system via multi-resolutional features to identify individuals. In such a system, three fold requirements, including personalization, integration, and adaptive thresholding, should be considered in order to to achieve more accuracy. In order to satisfy the above requirements, R personal feature spaces, an optimal positive Boolean function, and an automatically determined threshold value are obtained from the training samples of a specified individual. Some experimental results are conducted to show the validity of the approaches
Keywords :
Boolean functions; biometrics (access control); face recognition; adaptive thresholding; filter-based integration; integration; multi-resolutional face verification system; multi-resolutional features; optimal positive Boolean function; personal feature spaces; personalization; threshold value; training samples; Authentication; Biometrics; Boolean functions; Charge coupled devices; Charge-coupled image sensors; Computer science; Covariance matrix; Eigenvalues and eigenfunctions; Filters; Matrix decomposition;
Conference_Titel :
Security Technology, 2001 IEEE 35th International Carnahan Conference on
Conference_Location :
London
Print_ISBN :
0-7803-6636-0
DOI :
10.1109/.2001.962845
