基于公安交通管理业务人脸识别的关键测评技术研究

Research on Key Evaluation Technology of Face Recognition Based on Public Security Traffic Management Business

随着人脸识别技术的日趋完善,人脸识别技术被广泛应用于公安交通管理等多种重要场景中。尽管人脸识别技术已经取得了初步成效,但人脸识别算法好坏仍缺乏相应的权威测试与评价。用于于人脸模型训练、算法测试的人脸识别系统测试标准一般都关联相应的应用场景,由于缺乏系统化、标准化的面向公安交通管理邻域的人脸识别系统通用性能测试规范。因此,本文主要对公安交通管理的人脸识别场景进行了分析,旨在结合不同业务应用场景,根据行业内相关人脸识别相关规范,研究关键的测评技术方法及测评指标,搭建人脸识别各类场景测试库,从而进一步提高人脸识别系统在公安交通管理领域的应用成效。

The test criteria for face recognition system used in face model training and algorithm testing are generally related to the corresponding application scenarios,due to the lack of systematic and standardized general performance test criteria for face recognition system facing the public security traffic management neighborhood.This paper mainly analyzes the face recognition scenarios of public security traffic management,aiming at combining different business application scenarios,according to the relevant standards of face recognition in the industry,researching the key evaluation technology methods and evaluation indicators,and building the test database of various scenarios of face recognition,so as to further improve the application effect of face recognition system in the field of public security traffic management.