Facial Classification using Artificial Neural Network Techniques
Changes in illumination condition, pose, facial expression and others are challenging task in recognizing face images. Solving these problems requires a feature extractor that can generate distinct features for each class of image as well as classifier that able to recognize and classify the face image precisely. This paper presents a facial recognition system using Artificial Neural network (ANN) techniques namely Radial basis function and Feed forward neural networks. Invariant continuous orthogonal moment that is Zernike moment (ZM) at order 2 to 12 is used to extract 47 features which are the inputs to the neural network. The experiments were carried out on the database face images from the AT&T Laboratories Cambridge University consisting of 40 distinct subjects of 10 non-similar images each. For some subjects, the images were taken at different times, varying the lighting, facial expressions (open/closed eyes, smiling/not smiling), facial details (with and without spectacles) and different face scale. From the experiments, Radial basis function outperforms feed forward in terms of percentage classification. However the classification error of feed forward neural network is below 5％.
Artificial neural network Radial Basis function feed forward invariant continuous orthogonal moment Zernike moments
Noraini A. J. Fatimah Z. Norzilah R.
Department of System Engineering Faculty of Electrical Engineering Universiti Teknologi MARA 40450 Shah Alam Malaysia
国际会议
2010 International Conference on Signal and Information Processing(2010年IEEE信号与信息处理国际会议 ICSIP2010)
长沙
英文
219-224
2010-12-14（万方平台首次上网日期，不代表论文的发表时间）