Title :
Hybrid GAs for Eigen-based facial recognition
Author :
Abegaz, Tamirat ; Dozier, Gerry ; Bryant, Kelvin ; Adams, Joshua ; Popplewell, Khary ; Shelton, Joseph ; Ricanek, Karl ; Woodard, Damon L.
Author_Institution :
North Carolina A&T State Univ., Greensboro, NC, USA
Abstract :
In this paper, we have performed an evaluation of genetic-based feature selection and weighting on the PCA-based face recognition. This work highlights the first attempt of applying Genetic Algorithm (GA) based feature selection on the Eigenface method. The results show that genetic-based feature selection reduces the number of features needed by approximately 50% while improving the identification accuracy over the baseline. Genetic-based feature weighting significantly improves the accuracy from an 87.14% to a 92.5% correct recognition rate.
Keywords :
eigenvalues and eigenfunctions; face recognition; feature extraction; genetic algorithms; principal component analysis; PCA-based face recognition; eigen-based facial recognition; eigenface method; genetic algorithm based feature selection; genetic-based feature selection reduction; genetic-based feature weighting; hybrid GA; identification accuracy; Face Recognition; Feature Selection; PCA; Steady State Genetic Algorithm;
Conference_Titel :
Computational Intelligence in Biometrics and Identity Management (CIBIM), 2011 IEEE Workshop on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-9899-4
DOI :
10.1109/CIBIM.2011.5949209
