Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{181933,
        author = {Maheshwari Mahesh Vidhate and Gayatri namdev taur and Sheetal Shrikant Shevkari},
        title = {Deep Learning Meets Biometrics: A Comparative Study of Modern Identification Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {545-552},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181933},
        abstract = {Biometric identification has become an essential component of security and authentication systems. Traditional biometric approaches have been enhanced significantly with the rise of deep learning, leading to improved accuracy, robustness, and efficiency. This paper provides a comparative study of modern biometric identification techniques, including fingerprint recognition, facial recognition, iris scanning, and voice authentication, focusing on the impact of deep learning advancements. We analyze various deep learning architectures, compare their effectiveness across biometric modalities, and discuss challenges such as privacy concerns, adversarial attacks, and real-world implementation issues. The study concludes with future research directions and recommendations for optimizing biometric identification using deep learning.},
        keywords = {Biometric Identification, CNN, RNN, Feature Extraction, Pattern Recognition, Neural Networks, Biometric Security, Multi-Modal Biometrics.},
        month = {July},
        }