| 一种基于二值模式特征的人脸检测算法 |
| |
| 引用本文： | 左景龙,孙长银,杨万扣.一种基于二值模式特征的人脸检测算法[J].科技通报,2011,27(5):652-656. |
| |
| 作者姓名： | 左景龙 孙长银 杨万扣 |
| |
| 作者单位： | 东南大学自动化学院,南京,210096 |
| |
| 基金项目： | 国家自然科学基金资助项目(61005008,90820009) |
| |
| 摘 要： | 提出了一种改进的基于多区块局部二值模式(MB-LBP)特征的人脸检测算法.算法针对Ad aBoost算法训练过程中出现的权值分布扭曲的现象,对样本权值的更新规则进行了调整.实验结果表明,该方法有效地缩短了训练时间,而且避免了权值扭曲的现象.算法在保证检测率的同时降低了误检率.
|
| 关 键 词： | 人脸检测 MB-LBP特征 AdaBoost 权值调整 |
A Face Detection Algorithm based on MB-LBP Features |
| |
| ZUO Jinglong,SUN Changyin,YANG Wankou.A Face Detection Algorithm based on MB-LBP Features[J].Bulletin of Science and Technology,2011,27(5):652-656. |
| |
| Authors: | ZUO Jinglong SUN Changyin YANG Wankou |
| |
| Institution: | ZUO Jinglong,SUN Changyin,YANG Wankou (School of Automation,Southeast University,Nanjing 210096,China) |
| |
| Abstract: | In this paper,an improved face detection method called MBLBP-AdaBoost algorithm which based on Multiblock Local Binary Patterns(MB-LBP)features is presented.And aimed at the phenomenon of weights distortions in training process of AdaBoost algorithm,the algorithm of sample weights updated rules have been adjusted.Ours experimental results show that the new method can effectively shorten the training time,and avoids the phenomenon of weights distortions.The algorithm reduce false alarm rate while holding a h... |
| |
| Keywords: | face detection MB-LBP feaures AdaBoost weights updated |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
