首页> 外国专利> METHOD AND APPARATUS FOR DETECTING CLASSIFIER HAVING TEXTURE INFORMATION OF FACE, METHOD AND APPARATUS FOR RECOGNIZING FACE USING STATISTICAL CHARACTER OF THE TEXTURE INFORMATION

METHOD AND APPARATUS FOR DETECTING CLASSIFIER HAVING TEXTURE INFORMATION OF FACE, METHOD AND APPARATUS FOR RECOGNIZING FACE USING STATISTICAL CHARACTER OF THE TEXTURE INFORMATION

机译:用于检测具有面部纹理信息的分类器的方法和装置,利用纹理信息的统计特征识别面部的方法和装置

摘要

The invention relates to the field of mode identification technique, especially a human face identification method based on statistical texture analysis, combined with human face identification, mode identification, image processing and statistical learning techniques. The invention advances a truly original texture analyzing method, firstly decomposing a to-be-analyzed object into plural overlapped subobjects, then adopting multiscale wavelet to make í‹structural elementíŒ analysis and extraction on the to-be-analyzed subobjects; adopts statistical means to make mode classification on each subobject, i.e. each subobject generates a weak classifier; and finally adopts Bayesian network to model the relation between weak classifiers.
机译:本发明涉及模式识别技术领域,尤其涉及一种基于统计纹理分析,结合人脸识别,模式识别,图像处理和统计学习技术的人脸识别方法。本发明提出了一种真正原始的纹理分析方法,首先将待分析的对象分解为多个重叠的子对象,然后采用多尺度小波对待分析的子对象进行“结构元素”分析和提取。采用统计手段对每个子对象进行模式分类,即每个子对象生成一个弱分类器;最后采用贝叶斯网络对弱分类器之间的关系进行建模。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号