Title :
Combined local features selection for face recognition based on Naïve Bayesian classification
Author :
Ouarda, Wael ; Trichili, Hanene ; Alimi, Adel M. ; Solaiman, Basel
Author_Institution :
Res. Groups on Intell. Machines, Nat. Sch. of Eng. of Sfax, Sfax, Tunisia
Abstract :
Face recognition is a very popular biometric solution in the literature. Several solutions are presented to meet the needs of individual´s verification or identification. There are three types of face recognition approaches: local, global and hybrid. In this paper, we proposed a local approach for face recognition based on combined features selection methods like Genetic algorithm, Gramdt Shmidt algorithm, mRmR features selection algorithm and naïve Bayesian classifier. Our proposed approach will be compared with some face recognition systems based on global features. A comparative study is given in this paper based on Recognition rates and Execution times. Our Face recognition system, which is based on naïve Bayesian classifier and tested on ORL face database, has showed 78.75% recognition rate and interesting execution times compared to global approaches.
Keywords :
Bayes methods; face recognition; feature selection; genetic algorithms; image classification; Gramdt Shmidt algorithm; ORL face database; biometric solution; execution times; genetic algorithm; global face recognition; global features; hybrid face recognition; individual identification; individual verification; local face recognition; local features selection; mRmR features selection algorithm; naïve Bayesian classification; recognition rates; Bayes methods; Databases; Eyebrows; Face; Face recognition; Image recognition; Principal component analysis; Bayesian Classifier; Execution times; Face recognition; Features selection; Geometric Distances; Recognition rates;
Conference_Titel :
Hybrid Intelligent Systems (HIS), 2013 13th International Conference on
Conference_Location :
Gammarth
Print_ISBN :
978-1-4799-2438-7
DOI :
10.1109/HIS.2013.6920489