Recognition of Fingerprint Biometric Verification System Using Deep Learning Model
Lists
Only you see this
Abstract
This paper focus on Recognition of Fingerprint biometric verification system using deep learning. This paper provides the comparative analysis of different deep learning models for the enhance the performance of fingerprint recognition, that follows some key phases like data analysis, data preprocessing, classification, and feature extraction also evaluates the performance of according to accuracy measures. This research presents a results of a YOLO-based fingerprint detection approach that outperforms competing methods. Before improving the YOLO network structure, a fingerprint feature dataset was created, which included four thousands of annotated fingerprint photos. The fingerprint feature points were densely distributed, and the dataset was rather small. Findings demonstrate that while the detection speed remains largely similar, the mAP0.5 value increases from 93.0% to 97.4% when compared to the FP-YOLO (Fingerprint- YOLO)) model of the other models. FP-YOLO stands out with an exceptional accuracy achievement of 97.4<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>, outstanding its counterparts by a significant margin.
BibTeX
@misc{khare2025recognition,
author = {Pranav Khare and Sahil Arora and Sandeep K. S. Gupta},
title = {{Recognition of Fingerprint Biometric Verification System Using Deep Learning Model}},
year = {2025},
doi = {10.2139/ssrn.5264614},
howpublished = {SSRN},
}Loading related content...