基于深度学习的银行客户身份识别算法研究  

Research on bank customer identification system based on deep learning

作　　者：冮震 曲娜 胡从强 GANG Zhen;QU Na;HU Congqiang(School of Safety Engineering,Shenyang Aerospace University,Shenyang 110136,China)

机构地区：[1]沈阳航空航天大学安全工程学院,沈阳110136

出　　处：《青岛理工大学学报》2023年第1期147-152,共6页Journal of Qingdao University of Technology

基　　金：国家自然科学基金资助项目(61901283)。

摘　　要：为提高银行传统柜面现金区的客户身份识别效率和准确率,改变现有的人工加外拍设备识别方式,提出一种基于改进的VGGNet16与DenseNet融合的客户身份识别系统。该系统利用现金区内现有的安防摄像头来采集客户实时图像,运用深度学习的VGGNet16与DenseNet融合人脸识别算法对客户在人脸数据库中进行人证比对,以此达到客户身份识别的效果。对该系统进行应用表明,该系统能够利用现有设备资源,提高客户身份识别效率和准确率。In order to improve the efficiency and accuracy of customer identification in the traditional cash area of banks, and to change the existing manual and external camera identification methods, a customer identification system based on the improved VGGNet16 and DenseNet integration is proposed in this study. The system utilizes the existing security cameras in the cash area to collect real-time images of customers, and compares the customer’s personal identification in the face database to achieve the effect of customer identification with the deep learning VGGNet16 and DenseNet fusion face recognition algorithm. The application of the system shows that the system can improve the efficiency and accuracy of customer identification by using the existing equipment resources.

关 键 词：人证比对 人脸识别 深度学习 银行业务 人脸数据库 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]