Open Access Open Access  Restricted Access Subscription or Fee Access

A Biometric Solution of Education Environment Using Face Recognition System

A. Dahmouni, K. El Moutaouakil, K. Satori

Abstract



During the last years, several biometric modalities are coming back into the education field. They are mainly employed to automatically control and supervise the school. In this paper, we ensure the previous tasks by using a new face recognition system. Which combines the Local Gradient Probabilistic Pattern (LGPP) with the two Dimensional Wavelet Transform (2DDWT). Firstly, the almost homogeneous areas and the peaks areas are separate according to LGPP confidence interval based on local statistical moments. Secondly, the obtained images are decomposed using 2DDWT in the approximate (LL) sub-band and three details (HL, LH, HH) sub-bands. The approximate sub-band will be used later as reduced face features. Thereafter, the two- dimensional subspace methods, 2DPCA and 2DLDA, are used to extract the final features vector. Finally, Support Vector Machine (SVM) algorithms are used to classify features dataset. The experimental results on ORL and Yale standard databases prove the effectiveness of the proposed system.

Keywords


Education, LBP, LGPP, 2DDWT, 2DPCA, 2DLDA, SMO and LIBSVM.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.