基于ARM的嵌入式人脸识别系统设计

Design of Embedded Face Recognition System Based on ARM

由于新冠状病毒爆发的影响,人脸识别技术因其不需要直接接触、友好快捷等特点,得到广泛关注。本文提出并搭建了一种以i.MX6ULL为硬件平台的嵌入式人脸识别系统,通过摄像头进行图像采集,将采集到的图像转化为数字信号传输给主控芯片;主控芯片接收到数据后,经预处理、人脸检测、人脸提取与特征降维、人脸识别等处理过程后,得到识别结果;最后识别结果通过显示屏进行输出。经测试表明,在实验室等人员较少、人员变动较小的场景下,该系统成功满足了身份验证的基本需求,具有较高的识别速度和较高的准确率。

Due to the impact of the new coronavirus outbreak, face recognition technology has received widespread attention due to its features such as no direct contact, friendliness and speed. This paper proposes and builds an embedded face recognition system based on i.MX6 ULL as the hardware platform, which collects images through a camera, converts the collected images into digital signals and transmits them to the main control chip;after the main control chip receives the data After preprocessing, face detection, face extraction and feature reduction, face recognition and other processing processes, the recognition result is obtained;the final recognition result is output through the display screen. Tests have shown that the system successfully meets the basic requirements of identity verification, with high recognition speed and high accuracy in scenarios where there are fewer personnel and small changes in personnel such as laboratories.