FINGERPRINT LIVENESS DETECTION VIA GLOBAL FEATURE ENCODING WITH VISION TRANSFORMERS
INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 16.04.2026 · 10 (04) · 1-9
DOI: 10.55041/ijsrem60406 ↗Kurz gefasst
Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 16.04.2026. Verfasst von MD.Salman Pasha und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Fingerprint Liveness Detection (FLD) is crucial for securing biometric systems by identifying fake fingerprints made from materials like silicone, gelatine, and latex. To reduce complexity and computational cost, a lightweight deep learning framework is proposed that efficiently captures both fine ridge-level details and global texture features. The system relies solely on fingerprint images, ensuring hardware simplicity and easy deployment without additional biometric inputs. It uses an optimized architecture with advanced training techniques to improve accuracy and performance. As a result, the model achieves strong generalization and reliable performance in real-world applications. Keywords: FLD, CNN, Spoof Detection, Biometric Authentication
Zitieren
APA
Pasha, M., Rajesh, D., Shirisha, K., & Bas, K. J. (2026). FINGERPRINT LIVENESS DETECTION VIA GLOBAL FEATURE ENCODING WITH VISION TRANSFORMERS. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem60406
Vancouver
Pasha M, Rajesh D, Shirisha K, Bas KJ. FINGERPRINT LIVENESS DETECTION VIA GLOBAL FEATURE ENCODING WITH VISION TRANSFORMERS. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem60406
BibTeX
@article{Pasha2026,
author = {Pasha, MD.Salman and Rajesh, Dr.A. and Shirisha, K.Venkata and Bas, Kadamanchi Jyothi},
title = {FINGERPRINT LIVENESS DETECTION VIA GLOBAL FEATURE ENCODING WITH VISION TRANSFORMERS},
journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
year = {2026},
volume = {10},
number = {04},
pages = {1--9},
doi = {10.55041/ijsrem60406}
}
EUVIMED