3D Information in Palmprint

Abstract

Palmprint has been proved to be one of the most unique and stable biometrics characteristics. Almost all the current palmprint recognition techniques capture the two-dimensional image of the palm surface and use it for feature extraction and matching. Although two-dimensional palmprint recognition can achieve high accuracy, the two-dimensional palmprint images can be easily counterfeited and much three-dimensional depth information is lost in the imaging process. This chapter explores a three-dimensional palmprint recognition approach by exploiting the three-dimensional structural information of the palm surface. The structured-light imaging is used to acquire the three-dimensional palmprint data, from which several types of unique features, including Mean Curvature Image, Gauss Curvature Image and Surface Type, are extracted. A fast feature matching and score level fusion strategy are proposed for palmprint matching and classification. With the established three-dimensional palmprint database, a series of verification and identification experiments is conducted to evaluate the proposed method. The results demonstrate that three-dimensional palmprint technique has high recognition performance. Although its recognition rate is a little lower than two-dimensional palmprint recognition, three-dimensional palmprint recognition has higher anti-counterfeiting capability and it is more robust to illumination variations and serious scrabbling in the palm surface. Meanwhile, by fusing the two-dimensional and three-dimensional palmprint information, much higher recognition rate can be achieved.