Palmprint recognition system on mobile devices with double-line-single-point assistance

摘要

Compared with other biometrics, palmprint has several advantages in authentication on mobile devices. However, some serious challenges severely restrict the development of palmprint recognition on mobile environments, such as various locations and gestures of hand, complex backgrounds, diverse illuminations, and limited hardware resource. In order to overcome the aforementioned problems, a novel assistant technique, named double-line-single-point (DLSP), is proposed in this paper for palmprint acquirement. The assistant graphics include two line segments and one point, which help users to locate their hands correctly and accurately. Region of interest (ROI) can be localized directly with DLSP even without any preprocessing, so false localization is overcome effectively, and the computation complexity is remarkably reduced, and the real-time performance is improved. Furthermore, users feel more comfort and freedom in DLSP than the existing assistant techniques for palmprint acquirement. Moreover, a judgment rule for palm existence is designed to overcome improper enrollments, which judges whether the users place their hands appropriately. A practical palmprint recognition system with DLSP is implemented on mobile platform. The experimental results on the database collected with the developed system confirm the effectiveness and advantages of our algorithm.