Fusion Net-3: Denoising Based Secured Biometric Authentication Using Fingerprints

Authors

  • Sreemol R Cochin University of Science and Technology
  • Dr. Santosh Kumar M.B Cochin University of Science and Technology
  • Dr. Sreekumar A Cochin University of Science and Technology

DOI:

https://doi.org/10.6977/IJoSI.202508_9(4).0007

Abstract

Background

Fingerprint-based authentication is a critical biometric approach for ensuring security and accuracy. Traditional methods often face challenges such as noise and suboptimal feature extraction.

Methods

The proposed model, Fusion Net-3, addresses these issues through two phases: Enrollment and Authentication. In the Enrollment phase, hand images are scanned and pre-processed using improved bilateral filtering optimized by the Seagull Optimization Algorithm. Contrast enhancement is applied using Histogram Equalization. Features are extracted based on shape and texture, and optimal features are selected using the Falcon Inspired Jackal Optimization algorithm, which combines Golden Jackal and Falcon optimization techniques. These features are fused using the Geometric mean and Ronald Fisher score.

In the Authentication phase, similar pre-processing, feature extraction, and selection methods are applied. Secure data transmission is achieved through the blockchain technology. The Fusion Net-3 model, integrating CNN, ResNet-50, and U-Net, is used to detect efficient fingerprints.

Findings

The model achieved an accuracy of 98.95% and a Mean Squared Error (MSE) of 2.34% when implemented on a Python platform.

Results

The Fusion Net-3 model demonstrated superior performance compared to existing methods, effectively enhancing authentication accuracy and security.

Conclusion

The novel Fusion Net-3 model significantly improves fingerprint-based authentication systems by addressing noise and optimizing feature extraction and selection, ensuring high accuracy and security.

Author Biographies

Dr. Santosh Kumar M.B, Cochin University of Science and Technology

IT

Dr. Sreekumar A, Cochin University of Science and Technology

Computer Applications

Downloads

Published

2025-08-15

Issue

Vol. 9 No. 4 (2025): International Journal of Systematic Innovation

Section

Regular full papers

License

Copyright in a work is a bundle of rights. IJoSI's, copyright covers what may be done with the work in terms of making copies, making derivative works, abstracting parts of it for citation or quotation elsewhere and so on. IJoSI requires authors to sign over rights when their article is ready for publication so that the publisher from then on owns the work. Until that point, all rights belong to the creator(s) of the work. The format of IJoSI copy right form can be found at the IJoSI web site.
The issues of International Journal of Systematic Innovation (IJoSI) are published in electronic format and in print. Our website, journal papers, and manuscripts etc. are stored on one server. Readers can have free online access to our journal papers. Authors transfer copyright to the publisher as part of a journal publishing agreement, but have the right to:
1.    Share their article for personal use, internal institutional use and scholarly sharing purposes, with a DOI link to the version of record on our server.
2.    Retain patent, trademark and other intellectual property rights (including research data).
3.    Proper attribution and credit for the published work.