(Publisher of Peer Reviewed Open Access Journals)

International Journal of Advanced Computer Research (IJACR)

ISSN (Print):2249-7277    ISSN (Online):2277-7970
Volume-2 Issue-7 December-2012
Full-Text PDF
Paper Title : Design of Face Recognition System by Using Neural Network with Discrete Cosine Transform and Principal Component Analysis
Author Name : Rohit Jain, Rajshree Taparia
Abstract :

This research paper deals with the implementation of face recognition system using neural network Importance of face recognition system has speed up in the last few decades. A face recognition system is one of the biometric information processing. The developed algorithm for the face recognition system formulates an image-based approach, which uses the Two-Dimensional Discrete Cosine Transform (2D-DCT) for image compression and the Self- Organizing Map (SOM) Neural Network for recognition purpose, simulated in MATLAB. By using 2D-DCT we extract image vectors and these vectors becomes the input to neural network classifier, which uses self-organizing map, algorithm to recognize familiar faces (trained) and faces with variations in expressions, illumination changes, tilt of 5 to 10 degrees. Again face Recognition system is developed with principal component analysis (PCA) instead of Two Dimensional Discrete Cosine Transform (2D-DCT) and self-Organizing Map (SOM) Neural Network for recognition purpose. The crux of proposed algorithm is its beauty to use unsupervised single neural network as classifier.

Keywords : Artificial Neural Network, Self-Organizing map, Two dimensional discrete cosine transform, Principal component analysis, unsupervised.
Cite this article : Rohit Jain, Rajshree Taparia, " Design of Face Recognition System by Using Neural Network with Discrete Cosine Transform and Principal Component Analysis " , International Journal of Advanced Computer Research (IJACR), Volume-2, Issue-7, December-2012 ,pp.66-69.