Education, Science, Technology, Innovation and Life
Open Access
Sign In

Fingerprint Image Invariant Feature Extraction Algorithm

Download as PDF

DOI: 10.23977/meet.2019.93705


Jinghong Xu, Xinyou Dong

Corresponding Author

Jinghong Xu


Fingerprint based authentication systems play a vital role in identifying an individual. The existing systems depend on specific feature points. Designing a reliable fingerprint authentication system is very challenging, since not all fingerprint information is available. Further, the information obtained is not always accurate due to cuts, scars, sweat, distortion and various skin conditions. Moreover, feature detection and description algorithms are typically computationally intensive, which prevents them from achieving the speed of sight real-time performance. In addition, algorithms differ in their capabilities and some may favor and work better given a specific type of input compared to others. As such, it is essential to compactly report their pros and cons as well as their performances. This paper provides a comprehensive overview on the state-of-the-art and recent advances in feature detection and description algorithms. It compares, reports and discusses their performance and capabilities. And then the Maximally Stable Extremal Regions algorithm is selected to extract the fingerprint features. The result shows that the feature points of fingerprint image are rotation, scale and affine invariant.


Fingerprint Authentication, Local Features, Mser, Detectors, Descriptors

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.