Related Experiment Videos
A new algorithm for distorted fingerprints matching based on normalized fuzzy similarity measure
Xinjian Chen1, Jie Tian, Xin Yang
1Center for Biometrics and Security Research, Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China. xjchen@fingerpass.net.cn
Summary
This study introduces a novel normalized fuzzy similarity measure (NFSM) algorithm to effectively address nonlinear distortions in fingerprint matching. NFSM demonstrates superior performance and reliability compared to traditional methods for deformed fingerprints.
Area of Science:
- Biometrics
- Computer Science
- Pattern Recognition
Background:
- Nonlinear distortions pose significant challenges in accurate fingerprint matching.
- Existing algorithms struggle to maintain robustness against these deformations.
Purpose of the Study:
- To propose and evaluate a novel algorithm, the normalized fuzzy similarity measure (NFSM), for robust fingerprint matching.
- To enhance the accuracy and reliability of fingerprint identification in the presence of nonlinear distortions.
Main Methods:
- Developed a two-step algorithm involving robust global alignment using local topological structure matching.
- Introduced the normalized fuzzy similarity measure (NFSM) for computing similarity between template and input fingerprints.
- Evaluated the algorithm on the FVC2004 fingerprint databases.
Main Results:
- The proposed NFSM algorithm demonstrated reliable and effective performance in matching fingerprints with nonlinear distortions.
- NFSM achieved considerably higher matching scores compared to conventional algorithms for deformed fingerprints.
- Experimental results validated the robustness of the local topological structure matching in global alignment.
Conclusions:
- The normalized fuzzy similarity measure (NFSM) is a reliable and effective solution for fingerprint matching under nonlinear distortions.
- NFSM significantly improves matching accuracy for deformed fingerprints.
- The algorithm offers a promising advancement in biometric security and identification systems.