深度融合的指纹识别算法拒真率仿真数据

本项目开展高效安全的指纹识别算法研究。传统的结构特征点算法的优点是识别效果非常稳定，因为由纹理走势推测出的结构特征点具有非常高的稳定性和特异性，不会随着使用环境和手指干湿特性的变化而变化，传统的算法不容易被错误的图像攻击。然而，在当下传感器小型化的趋势下，传统的特征点算法碰到了图像小而无特征的尴尬境地，其识别效果随着指纹传感器采集面积的减小而急剧下降。项目提出一个优势互补的深度融合算法：利用传统纹理特征算法的结构特征稳定性降低甚至杜绝异物攻击，同时保留图像算法多特征点的特性以有效识别使小面积指纹。新算法实现了识别效果（高通过率，低误识率）和安全性的最优化。This project conducts research on efficient and secure fingerprint recognition algorithms. Traditional structural minutiae-based algorithms feature highly stable recognition performance, as the structural minutiae derived from fingerprint ridge flow patterns possess exceptional stability and specificity, remaining unaffected by changes in usage environments or the dry/wet state of fingers. Moreover, such traditional algorithms are less susceptible to spoofing attacks via counterfeit fingerprint images. However, amid the ongoing trend of fingerprint sensor miniaturization, traditional minutiae-based algorithms face the dilemma of small-sized fingerprint images lacking sufficient valid features, with their recognition performance declining sharply as the acquisition area of the fingerprint sensor shrinks. This project proposes a deep fusion algorithm with complementary advantages: it leverages the high stability of structural features from traditional texture-based fingerprint algorithms to reduce or even eliminate spoofing attacks from foreign objects, while retaining the multi-minutiae extraction capability of image-based algorithms to effectively recognize small-area fingerprint images. The proposed novel algorithm optimizes both recognition performance (high genuine acceptance rate, low false acceptance rate) and security.

搜集汇总

背景与挑战

背景概述

该数据集聚焦于指纹识别算法的拒真率仿真，旨在通过深度融合传统结构特征点算法与图像算法，提升识别效果和安全性。它针对传感器小型化带来的挑战，优化算法以降低误识率并增强抗攻击能力。