ARCHIVES
VOL. 11, ISSUE 1 (2026)
An integrated data mining and knowledge discovery framework for feature optimization in fingerprint biometric authentication systems
Authors
Dr. Sureshbabu N
Abstract
Fingerprint biometric authentication systems
rely heavily on the extraction of discriminative features to achieve high
accuracy under varying imaging conditions. Traditional feature extraction
methods, which often utilize fixed or manually designed filters, may
inadequately address distortions, such as pressure variations, smudging, and
partial prints. This study presents an innovative Adaptive Feature Optimization
Framework (AFOF) that integrates data mining and knowledge discovery techniques
to dynamically select and optimize fingerprint features. The framework employs
a data-driven feature selection module, enhanced by knowledge-discovery
algorithms, to identify the most discriminative features for each fingerprint.
Experimental evaluations conducted on the FVC2002 and FVC2004 datasets
demonstrate that the proposed framework significantly improves recognition
accuracy and reduces the equal error rate (EER) compared with conventional
methods, while also decreasing computational complexity, thereby making it
suitable for real-time biometric applications.
Download
Pages:44-49
How to cite this article:
Dr. Sureshbabu N "An integrated data mining and knowledge discovery framework for feature optimization in fingerprint biometric authentication systems". International Journal of Advanced Research and Development, Vol 11, Issue 1, 2026, Pages 44-49
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.