Robust biometric authentication based on feature extracted from visual ventral stream

In this Paper, We use a set of the applicability features inspired by the visual Cortex. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edge-detectors over neighboring positions and multiple orientations. Two standard classifiers KNN and SVM are then trained over a training set and then compared over a separate test set. A multimodal biometric system consolidates the evidence presented by multiple biometric sources and typically provides better recognition performance compared to systems based on a single biometric modality. So we use combination of Face, Ear and Palm characteristic to individual's authentication. In fusion stage we use matching-score level. Experimental results showed 96% accuracy rate on ORL Face database and 94% accuracy rate on USTB Ear database and 96.6% accuracy rate on POLYU Palm database; however we achieve 100% accuracy rate on multimodal biometric.