Increasing the Efficiency of Iris Recognition Systems by Using Multi-Channel Frequencies of Gabor Filter

Abstract

Abstract -Iris recognition is considered to be the most accurate biometric technology when compared to other technologies commercially in use today. This is because the false match and the false non-match errors are very small, which implies a very high accuracy. Iris recognition has found considerable successes in aviation security for passenger screening and immigration control, banks, financial institutions [6]. The iris recognition system proposed in this paper consists of an automatic segmentation system that localizes the circular iris and pupil region. The extracted iris region is then normalized into a rectangular block with constant dimensions to account for imaging inconsistencies. Finally, the phase data from 2D Gabor filters is extracted and quantized to four levels to encode the unique pattern of the iris into a bit-wise biometric template. The performance of the iris recognition systems highly depends on the accuracy of the localization process by excluding the unwanted parts (eyelids, eyelashes and reflections). In this paper, we test a new technique for increasing the performance of the iris recognition system by using multi-channel frequencies of Gabor filter. The proposed technique shows a significant improvement in the recognition accuracy.