摘要
OpenBR——开源生物识别系统,是一个可以提供快速高效开发环境的系统。正是因为它是一个用于研究新方法、改进现有算法、对接商业系统、测试识别性能并且可以自动部署生物系统的框架才使得应用此方法实现面部识别成为可能。对利用OpenBR提供的生物识别算法设计工具,经过正脸检测、规范化、特征描述、特征提取、特征对比匹配等一系列步骤对图片数据进行处理,最后将得到的匹配分数经过决策算法成为通过人脸识别实现身份识别的依据进行了研究。通过实验结果得出设计的决策算法可以得到90%以上识别率。可以应用于考勤、驾驶员身份识别等领域。
OpenBR——Open Source Biometric Recognition, originated within the MITRE corporation.It is a framework for investigating new modalities,improving existing algorithms,interfacing with commercial systems,measuring recogni-tion performance,and deploying automated biometric systems.The project is designed to facilitate rapid algorithm proto-typing,and features a mature core framework,flexible plugin system,and support for open and closed source develop-ment.Off-the-self algorithm are also available for specific modalities including Face Recognition, Age Estimation and Gender Estimation.The research content is to complete personal identity verification by using facial recognition model which based on OpenBR.Rapid and efficient development is necessary for modern development,with OpenBR is a very powerful assistant.Application of OpenBR to achieve identification system is a typical demonstration of using biometric framework which gets a nice result.
出处
《长春理工大学学报(自然科学版)》
2017年第5期49-53,76,共6页
Journal of Changchun University of Science and Technology(Natural Science Edition)
关键词
人脸识别
决策设计
OpenBR
OpenBR
facial recognition
decision-making