基于嵌入式的自动人脸识别系统研究

摘要

In order to improve face recognition and detection rate, based on skin color and Adaboost algorithm, face detection, feature extraction and recognition are studied. Moreover, an automatic face recognition scheme based on the embedded system is designed. The real pictures are tested with face recognition system on TQ2440 embedded development platform. Testing result shows that the face recognition system is effective.%为了提高人脸识别的速度和检测率,基于肤色与Adaboost算法的人脸检测、特征提取与识别,给出嵌入式平台的自动人脸识别系统的完整设计方案.基于TQ2440嵌入式开发平台实现该系统,结合现场采集的图片进行人脸识别测试,测试结果表明该系统检测速度快,检测率高.