Paper Title
Soft Computing Approach To Multi-Modal Biometric System

Abstract
The increasing demand for high secure and reliable authentication schemes, led to improvement in unimodal biometric system and hence multimodal biometric system has emerged as a mean of more secure and reliable authentication scheme. This work examines the multimodal fusion of palmprint (principal lines) and fingerprint (minutiae points). After an introduction to theoretical principles, related works in palmprint, fingerprint, and fusion of palmprint and fingerprint are highlighted. The developed system modules include image acquisition, morphological stage, feature extraction stage, fusion stage and classification stage. The database is composed of 600 posed fingerprints, 120 posed palmprints and 6480 fused posed palmprints and fingerprints. The data were trained and tested with a variant of neural network back-propagation algorithm. Three thresholds were employed viz; 0.35, 0.65 and 0.95. The results showed that threshold 0.95 produced average accuracy of 98.3%, threshold 0.65 produced average accuracy of 5%, and threshold 0.35 produced average accuracy 16.4%. Index Words� Multimodal, Minutiae, Feature level fusion, Gabor filter, Crossing Number, Backpropagation Neural Network