PERFORMANCE ANALYSIS OF HUMAN FACE RECOGNITION
Authors/Creators
- 1. *1Department of Computer Science, SSESA's, Science College, Congress Nagar, Nagpur (MS), India, 2Associate Professor, Department of Electronics & Computer Science, RTMNU, Nagpur (MS), India
Description
Human Face recognition is one of the most important and challenging research area in computer vision and pattern recognition. It has potential applications in different aspects of day-to-day life. To identify the human face image by matching the main features of face image is one of the hot topics in biometrics. This paper discusses the feature extraction techniques for human face recognition and performance analysis with other methods. For that purpose we used different distance metrics such as Euclidian distance, City block distance and Chess board distance. The proposed method test image features are compared with training face features using distance metrics. The experimentation is performed on JAFEE and Face94 face databases. Here two hundred images from two databases are taken and calculates the correct and wrong recognitions of human face. The obtained results compared with other methods on same databases. The proposed method is promising to achieve good performance in human face recognition.