超低功耗指纹传感器指纹图像分辨率测试数据

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 minutiae-based structural algorithms exhibit highly stable recognition performance, as the structural minutiae inferred from fingerprint texture trends possess extremely high stability and specificity, remaining unaltered despite variations in usage environments and the dry/wet states of fingers. Additionally, such traditional algorithms are less vulnerable to spoofing attacks via fake fingerprint images. However, under the current trend of miniaturized fingerprint sensors, traditional minutiae-based algorithms face a critical dilemma: small-collection-area fingerprint images often lack sufficient valid minutiae, resulting in a sharp decline in recognition performance as the acquisition area of fingerprint sensors decreases. To address this issue, this project proposes a deeply fused algorithm that leverages complementary strengths: it adopts the structural stability of traditional texture feature algorithms to reduce or even eliminate foreign object spoofing attacks, while retaining the multi-minutiae extraction capability of image-based algorithms to effectively recognize small-area fingerprint images. The proposed novel algorithm achieves optimal balance between 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

该数据集包含用于测试超低功耗指纹传感器指纹图像分辨率的测试数据，旨在支持高效安全的指纹识别算法研究。它针对传统算法在传感器小型化趋势下的局限性，提出深度融合算法以优化识别效果和安全性，数据量为6.08MB，包含12个文件。