非接触式自动反馈虹膜捕获设计.pdfVIP

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 57, NO. 7, JULY 2008 1369 Contactless Autofeedback Iris Capture Design Xiaofu He, Jingqi Yan, Guangyu Chen, and Pengfei Shi, Senior Member, IEEE Abstract—Automated iris recognition is one of the most reliable explored the requirements on the iris image acquisition sys- biometrics in terms of identification and verification performance. tem, and several implementations have already been put into One of the major challenges for automated iris recognition is to commercial practice [12]–[16]. These commercial systems are capture a high-quality image of the iris since system performance is greatly affected by poor-quality imaging. This paper describes expensively designed and do not provide iris acquisition inter- the design and implementation of a high-quality imaging device face for research purpose. Moreover, most of these products for iris acquisition, which consists of the following four parts: need the user’s cooperation. The user can voluntarily adjust 1) capture unit; 2) illumination unit; 3) feedback unit; and the distance to realize the exact focus of the iris image via 4) pitching outfit. Using the proposed device for iris acquisition, real-time feedback of the captured iris image through a voice it is feasible to obtain real-time, high-quality iris images, given the notification of the device. To some extent, this interactive mode fact that it is also user friendly. Recognition experiments in an iris database that contains 6550 images captured by the new device are demands cooperation from