Related Experiment Video
Updated: Jul 13, 2026
10:14
Chromatographic Fingerprinting by Template Matching for Data Collected by Comprehensive Two-Dimensional Gas Chromatography
Published on: September 2, 2020
Alignment-free cancelable fingerprint templates based on local minutiae information
Chulhan Lee1, Jeung-Yoon Choi, Kar-Ann Toh
1Biometrics Engineering Research Center, School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, Korea.
Summary
This study introduces a novel cancelable biometrics method for fingerprint templates that eliminates the need for image alignment. The new approach enhances security by generating unique, non-invertible templates, improving biometric system robustness.
Area of Science:
- Biometrics and Security
- Computer Science
- Pattern Recognition
Background:
- Cancelable biometrics offers a solution for replacing compromised biometric templates by transforming raw biometric data.
- Existing methods for cancelable fingerprint templates often require accurate alignment between enrolled and query templates.
- Alignment dependency limits the practical application and robustness of current cancelable biometric systems.
Purpose of the Study:
- To propose a novel method for generating cancelable fingerprint templates that does not require image alignment.
- To develop a system that enhances security by creating non-invertible and revocable biometric templates.
- To preserve geometric relationships between templates after transformation for efficient matching.
Main Methods:
- A rotation and translation invariant value is computed for each minutia using local orientation information.
- Two changing functions utilize the invariant value to generate unique translational and rotational movements for minutiae in the cancelable template.
- The method ensures that transformed templates retain original geometric relationships, enabling alignment-free matching.
Main Results:
- The proposed method successfully generates cancelable fingerprint templates without requiring alignment.
- Experimental evaluation demonstrated that verification accuracy is maintained with transformed templates.
- Changeability analysis showed controllable dissimilarities between original and transformed templates, and between differently transformed templates.
Conclusions:
- The developed method provides a robust and secure approach to cancelable biometrics for fingerprint recognition.
- The alignment-free nature of the transformed templates simplifies matching and enhances practical usability.
- Performance and changeability are interdependent and can be managed through parameter tuning, offering a flexible security solution.
