Real Time Face Recognition

Abstract

Texture is the surface property that is used to identify and recognize objects. Texture identification and recognition is extensively opted in many real time applications like biomedical and aerial image analysis, airport security, person identity verification and so on. Local binary pattern (LBP) texture method is used for feature extraction method for face recognition. The basic LBP is elongate to expedite the analysis of texture using multiple scales by combining neighborhoods with different sizes. Many models proposed for texture analysis which are derivatives of LBP. The derivatives of LBPs are centre symmetric local binary pattern, advanced local binary pattern(ALBP), local texture pattern (LTP),local binary pattern variance(LBPV), dominant local binary pattern. Local binary pattern and its derivatives performance has been compared. Local binary pattern ,eigenface,and fisher face results also compared. The above three methods are implemented in hardware (Raspberry pi 3 model B). The real-time face recognition challenges such as illumination variation and facial expression variations are ranked by different LBP-based models. The above experiments were conducted on the ORL, YALE, PIE database.