An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects： 1 Improvement for iris localization and 2 The improvement for both iris encoding and matching algorithms. In St...An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects： 1 Improvement for iris localization and 2 The improvement for both iris encoding and matching algorithms. In Step 1, the localization and shape of the pupil are roughly determined in iris image, which is used as prior knowledge to quickly locate the inner and outer boundary of iris from rough to fine scale. Eyelids, eyelashes areas and the spot in the pupil are automatically detected and removed to improve the localization accuracy. In Step 2, the possible noise from residual eyelashes is further filtered by selecting a ＂pure＂ iris area as a reference and making a validation judgment pixel-wise. Furthermore, the validation flag for each pixel is introduced into the iris encoding and matching computation, as a result, the rejection rate of iris recognition is reduced. Compared with Daugman algorithm, iris recognition test on collected human eye images shows that our proposed algorithm has an obvious improvement both on boosting the speed and reducing the rejection rate.展开更多
基金Supported by the National Natural Science Foundation of China(61367002)the Guangxi Key Laboratory of Automatic Detecting Technology and Instruments(YQ15108)+1 种基金the Guangxi Department of Education Foundation(KY2015YB111)the Innovation Team Foundation of Guilin University of Electronic Technology,the Foundation of Guangxi Experiment Center of Information Science,the Guangxi National Natural Science Foundation(2014GXNSFAA118302)
文摘An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects： 1 Improvement for iris localization and 2 The improvement for both iris encoding and matching algorithms. In Step 1, the localization and shape of the pupil are roughly determined in iris image, which is used as prior knowledge to quickly locate the inner and outer boundary of iris from rough to fine scale. Eyelids, eyelashes areas and the spot in the pupil are automatically detected and removed to improve the localization accuracy. In Step 2, the possible noise from residual eyelashes is further filtered by selecting a ＂pure＂ iris area as a reference and making a validation judgment pixel-wise. Furthermore, the validation flag for each pixel is introduced into the iris encoding and matching computation, as a result, the rejection rate of iris recognition is reduced. Compared with Daugman algorithm, iris recognition test on collected human eye images shows that our proposed algorithm has an obvious improvement both on boosting the speed and reducing the rejection rate.
