Abstract

The quality problems of contactless fingerprint and palmprint samples due to sampling, itself and other factors lead to the decline of recognition efficiency. To improve the recognition efficiency, this paper proposed two kinds of fingerprint and palmprint image quality evaluation algorithms, LQA<sub>S</sub> and GQA<sub>L</sub>, based on SURF and ROI frequency domain intensity respectively, to evaluate the quality of target ROI from the local and global levels. Based on the evaluation algorithm, the contactless fingerprint and palmprint score-level fusion recognition was carried out, and the public reference data set was used for experimental verification. Through the analysis of the experimental data, it is proved that the contactless fingerprint and palmprint ROI quality evaluation algorithm can improve the accuracy of fingerprint and palmprint recognition, and the contactless fingerprint and palmprint fusion recognition accuracy based on this algorithm reaches 100%, which is superior to similar excellent methods in recent years.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call