Iris recognition based on a novel variation of local binary pattern

Abstract In this paper, an efficient method based on a novel variation of local binary pattern (LBP), average local binary pattern (ALBP), is proposed for iris recognition, which is less sensitive to histogram equalization and parameters’ selection and has low computation complexity. Center pixel an...
Ausführliche Beschreibung

Abstract In this paper, an efficient method based on a novel variation of local binary pattern (LBP), average local binary pattern (ALBP), is proposed for iris recognition, which is less sensitive to histogram equalization and parameters’ selection and has low computation complexity. Center pixel and its neighborhood are the crucial elements involved in basic LBP. ALBP places high value on the significance of center pixel, while nearly all other variations of LBP have been focusing on the selection of neighborhood. Four candidates for the modification of the center pixel are elected and validated, respectively. In the proposed framework, the valid iris region firstly is localized and then normalized into a uniform rectangular. Then the normalized iris is chopped into several sub-images, and ALBP operator is applied to each sub-image to obtain individual histogram feature. Every histogram feature is then concatenated to form a global iris feature vector. Nearest neighbor classifier and support vector machine are employed to validate the recognition performance. Experimental results on CASIA-IrisV4 (including CASIA-Iris-Interval and CASIA-Iris-Thousand) and UBIRIS.V1 database show that our method achieves competitive recognition performance (optimal recognition rate is %$99.91\,\%%$) compared with other methods using the same databases. Ausführliche Beschreibung