Biometrics and Bioinformatics

L. Latha ¹, U. Supriya ², S. Thangasamy ³

Affiliations
1 Kumaraguru College of Technology, Coimbatore, IN
2 Department of Computer Science and Engineering, KCT, IN
3 R & D, Kumaraguru College of Technology, IN

Abstract

In any multimodal biometric system, an effective fusion method is necessary for combining information from various single modality systems. This requires that the scores from different modalities be in the same range so that they can be combined properly. Hence normalization techniques are needed for efficient fusion of scores. Performance of various normalization and fusion techniques are examined by using the five modalities namely iris, palm print, retina, ear and fingerprint. Particle swarm optimization technique is then applied on different fusion methods to optimize the fusion parameters such as threshold and weights and it shows improved recognition rates compared to the fusion of original scores. The results are experimentally verified and the performance graphs are plotted and better fusion method is recognized.

Keywords

Multimodal, Biometrics, Score Level Fusion, Optimization, Normalization.

Full Text

     

L. Latha ¹, S. Thangasamy ²

Affiliations
1 Kumaraguru College of Technology, Coimbatore, IN
2 Kumaraguru College of Technology, IN

Abstract

An efficient method for person authentication based on the retinal blood vessel pattern is presented in this paper. The method initially involves a segmentation process to identify blood vessel intersection points in the retina, then the generation of template consisting of the bifurcation points in the blood vessels and finally matching of the intersection points in two different patterns. This approach differs from previously known methods, in that it uses a retinal minucode centered feature extraction algorithm based on the bifurcation points present in retina. Then the number of matched blood vessel intersection points between the two patterns is used to quantify the degree of matching. The validity of our approach is verified with the experimental results obtained using the publicly available databases, namely DRIVE and STARE. We found that the proposed retinal recognition method gives 100% and 90.1% recognition rates respectively for the above databases.

Keywords

Blood Vessels, Bifurcation Points, Feature Extraction, Retinal Recognition.

Full Text