局部二元Haar特征Kadane多阈值AdaBoost面部分类识别  

Kadane Multi Threshold AdaBoost Classifier with Haar Feature Local Binary Pattern for Face Recognition

作　　者：杨秋芬[1,2] 桂卫华[1] 胡豁生[1] 余妹兰[3] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083 [2]湖南广播电视大学理工教学部,长沙410004 [3]湖南安全技术职业学院电气与信息工程系,长沙410151

出　　处：《小型微型计算机系统》2016年第11期2582-2587,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金重点项目(51037004)资助;国家自然科学基金项目(51077097)资助;湖南省科技厅资助项目(2015ZK3071)资助

摘　　要：针对面部分类检测识别过程中,存在的纹理形状特征表征及分类识别算法精度不高的问题,提出一种基于局部二元Haar特征表示的Kadane优化多阈值AdaBoost面部分类识别算法.首先,利用图像局部二元模式对传统的Haar特征表达形式进行改进,提高图像模型的纹理形状特征表达能力;其次,针对单阈值弱学习算法不能充分利用局部二元Haar特征信息,造成分类精度较低的问题,提出基于Kadane优化的多阈值AdaBoost分类器,实现局部二元Haar特征表示下的面部高精度识别;最后,通过实验对比显示,所提算法的面部有效识别率可达90%以上,要优于选取的对比算法.Aiming at the problem of feature representation and low accuracy of classification and recognition of face classification, a new algorithm called kadane multi threshold AdaBoost classifier with haar feature local binary pattern for face recognition is proposed. Firstly,it use the local binary pattern model to improve the traditional Haar features, which could improve the texture shape feature of the image model, and improve the robustness of the model to the illumination and so on; Secondly, for the single threshold weak learning algorithm can not make full use of local two yuan Haar feature information,resulting in lower classification accuracy,here pro-posed the multi threshold Kadane based on AdaBoost optimization, which achieve the high accuracy of the face recognition;Finally, through the experimental comparison,the proposed algorithm has a better recognition rate of more than 90%, which is better than the selection of the contrast algorithm.

关 键 词：局部二元特征 HAAR特征 ADABOOST分类器 Kadane优化 面部识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]