Multibiometric Database Retrieval Method Based on Index Code

Multibiometrics use of multiple biometric sources for human recognition, mitigates some of the limitations of unimodal biometric systems by increasing recognition accuracy, imparting fault-tolerance, and enhancing security. These databases are used extensively, thereby requirement of efficient technique for searching and retrieving relevant identities from large biometric database. Searching out a biometric information for associate degree identity is usually done by comparing the probe(input) image against every stored identity in the database and generating a ranked list of candidate identities. thorough matching against an large range of identities will increase the latency of the system and should additionally reduce the accuracy of identification. index code is obtained by computing match scores between a biometric input images and fixed set of reference images. Candidate identities are retrieved supported the similarity between the index code of the probe image and people of the identities within the info. we have propose a technique for generating fixed-length codes for classification biometric databases . The proposed technique is extended to retrieve pertinent identities from multimodal databases. New representation schemes that allow quicker search and, therefore, shorter response time are required. Keywords— Biometrics, Feature Extraction, Image Retrieval, Indexing, Pattern Matching