PROJECT TITLE:

Combining Left and Right Palmprint Images for More Accurate Personal Identification - 2015

ABSTRACT:

Multibiometrics will offer higher identification accuracy than single biometrics, therefore it is additional appropriate for a few real-world personal identification applications that need high-commonplace security. Among various biometrics technologies, palmprint identification has received a lot of attention as a result of of its good performance. Combining the left and right palmprint pictures to perform multibiometrics is straightforward to implement and can get higher results. However, previous studies failed to explore this issue comprehensive. During this paper, we proposed a novel framework to perform multibiometrics by comprehensively combining the left and right palmprint pictures. This framework integrated 3 kinds of scores generated from the left and right palmprint images to perform matching score-level fusion. The primary 2 sorts of scores were, respectively, generated from the left and right palmprint images and can be obtained by any palmprint identification technique, whereas the third reasonably score was obtained employing a specialised algorithm proposed during this paper. As the proposed algorithm fastidiously takes the nature of the left and right palmprint pictures into account, it can properly exploit the similarity of the left and right palmprints of the same subject. Moreover, the proposed weighted fusion scheme allowed good identification performance to be obtained in comparison with previous palmprint identification strategies.