Investigation on automated surveillance monitoring for human identification and recognition using face and iris biometric

Abstract

Nowadays, Biometric system automatically identifies the unique feature of an individual for better evaluation and verification in recognition systems. Face and iris recognition in biometric identification systems is considered as most accurate procedure with higher recognition rate. CCTV surveillance plays a major role in human recognition and identification with the help of intelligent systems. The biometric system combined with CCTV output analyzes the data with/without human intervention. This paper presents an approach of human identification with recognition using facial and iris biometric from lower resolution images. Also, Lower resolution in image clarity is a major constraint in recognizing the individuals from distance with biometric values. To overcome problem in individual recognizing, the combination of Gabor and Legendre filter is combined. The use of hybrid log-Gabor–Legendre (LGL) filter improves the recognition pattern of face and iris in multi-spectral images. After log Gabor–Legendre filtration, two new techniques such as phase quadrant method for iris and LGBPHS method for face are used to improve recognition pattern. Hence, a framework comprising of feature recognition using LGL filter and similarity comparison using score level fusion is proposed. A series of stages enhances well the recognition performances using the proposed solution. Experiments established the validity against existing linear techniques for facial and iris image recognition pattern from CCTV cameras for automated human identification and verification.