Title :
Cognitive Information Processing in Face Recognition
Author :
Tepvorachai, Gorn ; Papachristou, Chris ; Wolff, Frank ; Ewing, Robert
Author_Institution :
EECS Dept., Case Western Reserve Univ., Cleveland, OH
Abstract :
In the conventional eigen face method, the principle component analysis (PCA) algorithm associates the eigen vectors with the changes in illumination. In this paper, we propose an improvement of facial image association for face recognition using a cognitive processing model. This method is based on the notion of multiple-phase associative memory. The Essex face database is used to verify our model for facial image recognition and compare the results of face recognition with conventional eigen face method. The simulation results show that the proposed cognitive processing model approach results in better performance than that of the conventional eigen face approach; while the computational complexity remains of the same magnitude as that of the eigen face method.
Keywords :
content-addressable storage; eigenvalues and eigenfunctions; face recognition; feature extraction; image representation; neural nets; principal component analysis; Essex face database; cognitive information processing model; computational complexity; eigenface method; face recognition; facial image association; feature selection; image representation; multiple-phase neural network associative memory; principle component analysis algorithm; Algorithm design and analysis; Associative memory; Computational complexity; Computational modeling; Face recognition; Image databases; Image recognition; Information processing; Lighting; Principal component analysis;
Conference_Titel :
Aerospace and Electronics Conference, 2008. NAECON 2008. IEEE National
Conference_Location :
Dayton, OH
Print_ISBN :
978-1-4244-2615-7
Electronic_ISBN :
7964-0977
DOI :
10.1109/NAECON.2008.4806564