嵌入式人脸识别系统设计与实现

Design and implementation of embedded face recognition system

本文是基于S5PV210嵌入式平台设计实现的人脸识别系统。在嵌入式设备上设计人脸识别系统不仅需要考虑识别的准确率,还需要考虑设备周围的环境变化对人脸识别的干扰。系统中采用Adaboost算法依据人眼部的haar特征检测人脸。通过LBP纹理特征提取结合SVM识别分类的方法识别人脸。经过系统测试,系统的识别率以及对光照变化的鲁棒性满足了一般的人脸识别身份认证的需求。

A face recognition system based on the S5 PV210 embedded platform is designed and implemented in this paper.Designing a face recognition system on an embedded device requires not only considering the recognition accuracy,but also estimating the influence of environmental changes around the device on the face recognition.In the system,the Adaboost algorithm is used to detect the human face based on the haar feature of the human eye,and human face is identified by a method of LBP texture feature extraction combined with SVMrecognition classification.After system testing,the recognition rate of the system and the robustness to changes in lighting could effectively satisfy the needs of general face recognition authentication.