Title :
Transform Domain Two Dimensional and diagonal Modular Principal Component Analysis for facial recognition employing different windowing techniques
Author :
Chehata, Ramy C. G. ; Mikhael, Wasfy B. ; Abdelwahab, Moataz M.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of Central Florida, Orlando, FL, USA
Abstract :
Spatial domain facial recognition Modular IMage Principal Component Analysis (MIMPCA) has an improved recognition rate compared to the conventional PCA. In the MPCA, face images are divided into smaller sub-images and the PCA approach is applied to each of these sub-images. In this work, the Transform Domain implementation of MPCA is presented. The facial image has two representations. The Two Dimensional MPCA (TD - 2D - MPCA) and the Diagonal matrix MPCA (TD - Dia - MPCA). The sub-images are processed using both non-overlapping and overlapping windows. All the test results, for noise free and noisy images, using ORL, Yale and FERET databases achieved; 99.5%, 99.58% and 97.42% recognition accuracy respectively. Transform Domain implementations yield, computational and storage savings of at least 75% and 99.98%, respectively, compared to spatial domain. Sample results are given.
Keywords :
face recognition; principal component analysis; visual databases; 2D-MPCA; FERET databases; MIMPCA; ORL databases; Yale databases; dia-MPCA; diagonal matrix MPCA; diagonal modular principal component analysis; modular image principal component analysis; nonoverlapping windows; spatial domain facial recognition; transform domain two dimensional principal component analysis; two dimensional MPCA; windowing techniques;
Conference_Titel :
Circuits and Systems (MWSCAS), 2013 IEEE 56th International Midwest Symposium on
Conference_Location :
Columbus, OH
DOI :
10.1109/MWSCAS.2013.6674845