Research On Inner Knuckle Print Recognition Using Portable Devices

With the rapid development of mobile technology, identity recognition on portable devices has become more and more important. In this paper, we propose a novel biometric recognition method which is robust enough to operate under uncontrolled illumination, less constrained posture, and low image quality. Such robustness is crucial for its application on portable devices equipped with consumer-level cameras. We tackle this problem in two aspects. Firstly, we propose to identify the inner knuckle print(IKP) biometric feature, as its simple base geometry, as well as its simple structure in the feature. At the same time, it is hardly influenced by other biometric feature around itself. This character makes it more promising to reduce the influence of illumination and postures. Secondly, we propose a novel feature map based on spectrum analysis[1] and N-cut theory[2][3], which highlights the main structure of IKP to overcome the influence of variant illumination. Meanwhile we propose a context-based structure descriptor which could endure more deformations. To the best of our knowledge, our work is the first attempt to study the illumination invariance for the appearance-based low resolution hand biometrics. Previous work made assumption on the illumination conditions and hence less robust. Experimental results demonstrate that our method outperforms the state-of-the-art methods in terms of recognition accuracy, especially under uncontrolled lighting conditions.