Personal verification using ear and palm-print biometrics

This paper presents a multimodal biometric identification system based on new features extraction of palm and ear. We describe a new biometric approach to personal identification using robust pattern recognition Each element of this set is a complex feature obtained by combining position- and scale-tolerant edge detectors over neighboring positions and multiple orientations. Our system¿s architecture is motivated by a quantitative model of visual cortex, with fusion applied at the matching-score level. The identification process can be divided into the following phases: capturing the image; pre-processing; extracting and normalizing the palm and ear; feature extraction; matching and fusion; and finally, a decision based on the k-NN and SVM classifiers. The system was tested on a database of 600 people (300 palm and 300 ear images). The experimental results showed the effectiveness of the system in terms of the recognition rate (100 percent).