Modified Image Based Approach and Neural Networks For Face Recognition

摘要

Recognition of people is a big challenging problem. Face recognition is one of them and up to date. Face recognition is a task that humans perform routinely in our daily lives. The large availability of powerful and low-cost and embedded computing systems is created. Automatic processing of digital images in a number of applications, including biometric authentication, surveillance, human computer interaction, and multimedia management. Implementation in automatic face recognition follows naturally. The face recognition technique has several advantages over other biometric modalities such as fingerprint and iris: besides being natural and nonintrusive, the most important advantage of face is that it can be captured at a distance and in a covert manner. In this paper, we proposed multilevel technique for human face recognition and we use the neural network techniques to train the data. In the last we evaluate the performance rate and compared to existing techniques.