摘要
人脸检测广泛应用到人脸识别、数字视频处理、安全访问控制、视觉监测、基于内容的检索等领域.比较众多人脸检测算法,文章提出了一种改进的基于Adaboost算法的人脸检测算法.该算法的核心是肤色分割结合基于Adaboost算法的人脸检测.首先,对彩色图像进行肤色分割,通过肤色区域的大小和长宽比等规则去除部分类肤色区域,得到可疑的人脸区域.其次,基于Adaboost算法的灰度特征得到最终的人脸.通过大量彩色图像的实验,证实了该方法的准确性和鲁棒性.
Face detection has been widely used in many fields,such as face recognition,digital video processing,security access control,visual surveillance,content-based retrieval,and so on.Compared to many face detection methods,this paper proposed an improved face detection approach,which is based on the Adaboost algorithm and skin segmentation.Based on the color information,the skin regions are segmented from the color image.Some skin-like regions are eliminated by the size and aspect ratio of the region to obtain ...
出处
《电子器件》
CAS
2007年第5期1716-1719,共4页
Chinese Journal of Electron Devices
基金
上海市教委与教育发展基金曙光项目(04CX72
05AZ38)