Vein recognition is becoming an effective method for personal recognition. Vein patterns lie under the skin surface of
human body, and hence provide higher reliability than other biometric traits and hard to be damaged or faked. This paper
proposes a novel vein feature representation method call orientation of local binary pattern (OLBP) which is an
extension of local binary pattern (LBP). OLBP can represent the orientation information of the vein pixel which is an
important characteristic of vein patterns. Moreover, the OLBP can also indicate on which side of the vein centerline the
pixel locates. The OLBP feature maps are encoded by 4-bit binary values and an orientation distance is developed for
efficient feature matching. Based on OLBP feature representation, we construct a hand vein recognition system
employing multiple hand vein patterns include palm vein, dorsal vein, and three finger veins (index, middle, and ring
finger). The experimental results on a large database demonstrate the effectiveness of the proposed approach.
In this work, an integrated contactless multiple hand feature acquisition system is designed. The system can capture
palmprint, palm vein, and palm dorsal vein images simultaneously. Moreover, the images are captured in a contactless
manner, that is, users need not to touch any part of the device when capturing. Palmprint is imaged under visible
illumination while palm vein and palm dorsal vein are imaged under near infrared (NIR) illumination. The capturing is
controlled by computer and the whole process is less than 1 second, which is sufficient for online biometric systems.
Based on this device, this paper also implements a contactless hand-based multimodal biometric system. Palmprint, palm
vein, palm dorsal vein, finger vein, and hand geometry features are extracted from the captured images. After similarity
measure, the matching scores are fused using weighted sum fusion rule. Experimental results show that although the
verification accuracy of each uni-modality is not as high as that of state-of-the-art, the fusion result is superior to most of
the existing hand-based biometric systems. This result indicates that the proposed device is competent in the application
of contactless multimodal hand-based biometrics.
A palmprint can be represented using different features and the different representations reflect the different characteristic of a palmprint. Fusion of multiple palmprint features may enhance the performance of a palmprint authentication system. This paper investigates the fusion of two types of palmprint information: the phase (called PalmCode) and the orientation (called OrientationCode). The PalmCode is extracted using the 2-D Gabor filters based algorithm and the OrientationCode is computed using several directional templates. Then several fusion strategies are investigated and compared. The experimental results show that the fusion of the PalmCode and OrientationCode using the Product, Sum and Weighted Sum strategies can greatly improve the accuracy of palmprint authentication, which is up to 99.6%.
Paimprint is a new biometric method to recognize a person. The most important feature of paimprint is the lines. In this paper, a set of line detector is devised for paimprint. There are two parameters in these detectors, one controls the smoothness and connection of the lines, the other controls the width of lines which can be detected. The lines in different directions are detected by corresponding direction detectors and then fused into one edge image. In training stage, the lines of the training samples are represented and stored with chain code. In the verification stage, the lines are matched using Hausdorif distance. Experimental results show the efficiency of this method.