Face recognition using fixed spread radial basis function neural network

• Main Authors: A Aziz, Khairul Azha, Hamzah, Rostam Affendi, Abdullah, Shahrum Shah, Mohd Jahari @ Mohd Johari, Ahmad Nizam, Damni, Siti Dhamirah ‘Izzati
• Format: Article
• Language: English
• Published: Penerbit Universiti Teknikal Malaysia Melaka 2011
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utem.edu.my/id/eprint/4421/2/recognition.PDF; http://eprints.utem.edu.my/id/eprint/4421/; https://jtec.utem.edu.my/jtec/article/view/426/295
• Institution: Universiti Teknikal Malaysia Melaka

This paper presents face recognition using spread fixed spread radial basis function neural network. Acquired image will be going through image processing process. General preprocessing approach is use for normalizing the image. Radial Basis Function Neural Network is use for face recognition and Support Vector Machine is used as the face detector. RBF Neural Networks offer several advantages compared to other neural network architecture such as they can be trained using fast two stages training algorithm and the network possesses the property of best approximation. The output of the network can be optimized by setting suitable values of the center and spread of the RBF but in this paper fixed spread is used as there is only one train image for every user and to limit the output value.