摘要
针对因图像背景复杂、光照变化及面部旋转等因素的影响,使复杂背景下人脸检测难度大、速度慢和准确率低的问题,使用Adaboost算法进行人脸检测,并在OpenCV上实现其检测过程。分别对具有面部旋转和复杂背景的图像进行了人脸检测实验,其检测准确率分别为85%和99%,平均检测时间分别是16.67 ms/张和76 ms/张。实验结果表明,该算法能在复杂背景下准确、快速地实现人脸检测,且能满足人脸识别系统实时性的要求。
Because of the influence of complex image background,illumination changes,facial rotation and some other factors,face detection in complex background is much more difficult,lower accuracy and slower speed.Adaboost algorithm was used for face detection,and the test process in OpenCV was implemented.Face detection experiments were performed on images with facial rotation and complex background.The detection accuracy rate was 85％ and 99％ respectively,the average detection time of each picture was 16.67 ms and 76 ms.Experimental results show that the face detection algorithm can accurately and quickly realize face detectionin in complex background,and can satisfy the requirements of real-time face recognition system.
出处
《吉林大学学报（信息科学版）》
CAS
2014年第5期539-544,共6页
Journal of Jilin University（Information Science Edition）
基金
吉林省科技发展计划基金资助项目(20120434)
作者简介
于微波（1970-）,女,长春人,长春工业大学副教授,硕士生导师,主要从事智能仪器与智能控制研究,（Tel）86-18686689201（E-mail）yu_weibo@126.com.
