Fused Index Code Based Multibiometric Pattern Retrieval Security System

Abstract

Biometric authentication has been receiving extensive attention over the past decade with increasing demands in automated personal identification. Biometrics is to identify individuals using physiological or behavioral characteristics, such as fingerprint, face, iris, retina, palm-print, etc. Among all the biometric techniques, fingerprint and face recognition [1] is the most popular methods and is successfully used in many applications.Biometric identification system have huge underlying biometric database. In this large identification system, the goal is to determine the identity of a subject from a large set of users already enrolled in biometric database. Though the state-ofart biometric identification algorithm work well for small database in terms of accuracy and response time but fail to scale well for large databases.Classification and indexing can be used to filter the search space during identification process. Classification is procedure where data points are placed into different groups called classes, based on therequantitive information and already classified data points.In identification, the class of query biometric is first identified and then it is compared to each biometric present in the class. In indexing, feature extraction techniques are used and assigned the index value to them using different indexing techniques. The given query is only compared to templates which have comparable index.In this paper we propose an indexing technique for multimodal database which is capable of reducing the response time of biometric identification systems by reducing the search space during identification.