掌纹鉴别自动性能评估  

Automatic performance evaluation of palmprint recognition

作　　者：齐振宇[1] 许静[1] 李吉屹[1] 史广顺[1] 

机构地区：[1]南开大学信息学院机器智能研究所,天津300071

出　　处：《计算机工程与应用》2007年第28期214-216,239,共4页Computer Engineering and Applications

基　　金：天津市科技公关计划(the Key Technologies R&D Program of Tianjin City;China under Grant No.043185111- 15)。

摘　　要：研究关于掌纹鉴别系统的性能评测问题,设计并实现了一个用于性能评测的自动测试系统(ASPE),此系统采用的是掌纹识别系统的处理核心。同时还提出了一种基于特征点(终点和分叉点)的评测方法和用于量化评估的俩个主要指标-召回率和准确率.此系统可以直接在样张上显示标准特征点和提取特征点,方便开发人员的对比并发现问题,从速度和精确度的测试结果看出自动的性能评测在效率和准确上都大大超过了人工测试。This paper is concerned with the performance evaluation of palmprint recognition systems.We have designed and implemented an Automatic System for Performance Evaluation（ASPE）,which adopts the process kernel of palm recognition.We have also proposed a performance evaluation method based on minutiae,which are essentially terminations and bifurcations of the ridge lines that constitute a palmprint pattern.In this paper we define two evaluation indexes：recall and accuracy.The system can display the minutia in the image directly and output the two rates in the EXCEL form.The test result of speed and precise shows that automatic evaluation outperforms manual evaluation dramatically both in terms of efficiency and robustness.

关 键 词：自动评测系统 性能评测 标准特征点 提取特征点 召回率 准确率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]