Hybrid Component-Based Face Recognition System

摘要: Face recognition system is a fast growing research field because of its potential as an eminent tool for security surveillance, human-computer interaction, identification declaration and other applications. techniques can be categorized into 3 categories namely holistic approach, feature-based hybrid approach. In this paper, component-based proposed. Linear discriminant analysis (LDA) used to extract the feature from each component. The outputs individual components are then combined give final output. Two methods obtain components, facial landmarks sub-images. It was found out that fusion does improve rate compared results From sub-image method, it seen size get smaller, tends increase but not always.