互联网 qkzz.net
全刊杂志网:首页 > 女性 > 文章正文
刊社推荐

基于Gabor小波和模型自适应的鲁棒人脸识别方法林 劼 李建平


  摘 要:提出了一种基于gabor小波人脸特征和模型自适应算法的新鲁棒人脸识别方法。该方法在真实识别前,通过用与真实识别相同的环境条件下所获得的人脸图像数据对原始模型进行更新补偿,实现了模型自适应。该模型自适应更新算法是加性的,其具有较低的时间和空间复杂度。通过模型自适应更新,新方法可以有效地减少模型和识别数据间的失配,从而提高识别率。在at&t和mitcbcl人脸数据库上的测试结果表明,该方法是有效的。

  关键词:模型补偿; 人脸识别; 模型自适应; gabor; 联想记忆模型

  中图分类号:tp39141 文献标志码:a

   文章编号:10013695(2008)09286804

  robust face recognition by gabor features and model adaptation

  lin jie, li jianping

   (school of computer science & engineering, university of electronic science & technology of china, chengdu610054, china)

  abstract:this paper proposed a robust face recognition algorithm based on gabor wavelet representations and model adaptation. the models used in this work were from linear associative memory method and fast compensated by adaptively learning from the given facial data, which were obtained in same condition as testing. the proposed adaptation algorithm is incremental. it has low time and space complexity. by compensating models, this method can efficiently reduce the mismatch between models and testing data, substantially improving the performance of classifier. the new recognition method was tested using two widely used face datasets:at&t and mitcbcl face database. results indicate that the algorithm is effective. and due to the computational simplicity, the algorithm is also efficient.

......
很抱歉,暂无全文,若需要阅读全文或喜欢本刊物请联系《计算机应用研究》杂志社购买。
欢迎作者提供全文,请点击编辑
分享:
 

了解更多资讯,请关注“木兰百花园”
分享:
 
精彩图文


关键字
支持中国杂志产业发展,请购买、订阅纸质杂志,欢迎杂志社提供过刊、样刊及电子版。
关于我们 | 网站声明 | 刊社管理 | 网站地图 | 联系方式 | 中图分类法 | RSS 2.0订阅 | IP查询
全刊杂志赏析网 2017