摘要
基于AdaBoost的人脸检测算法在层出不穷的算法中处于十分重要的地位。该算法使用Haar-like特征提取图像的人脸特征,采用积分图快速计算特征数值,依据加权投票的方式挑选出弱分类器并将其构造成强分类器,有效提高分类器的检测速度。这种算法具有高速、高精度以及高稳定性的特点,总体性能良好。
The face detection algorithm based on AdaBoost is very important among the endless stream of algorithms. The algorithm uses Haar-like feature to extract the face features of images, and uses the integral graph to quickly calculate the feature values, and then it selects the weak classifier according to weighted voting method and constructs it into a strong one which could effectively improve the detection speed of the classifier. This algorithm has the characteristics of high speed, high precision and high stability, and the overall performance is good.
引文
[1]Freund,Y.Boosting a Weak Learning Algorithm by Majority.Information and Computation,1995,121(2):256-285
[2]Lang Li-Ying,Gu Wei-Wei.Improved Face Detection Algorithm Based on AdaBoost.International Conference on Electronic Computer Technology,Feb.2009:183-186.
[3]Viola P,Jones M.Robust Real-Time Object Dection.IEEE ICCV Workshop on Statistical and Computational Theories of Vision.Vancouver,2001.
[4]Li,S.Z.,Long Zhu,S.Z.,Zhenqiu Zhang,S.Z.,Hongjiang Zhang,S.Z.Learning to Detect Multi-View Faces in Real-Time.Proceedings 2nd International Conference on Development and Learning,2002:172-177.
[5]Le,Duy-Dinh,Satoh,Shin’ichi.Ent-Boost:Boosting Using Entropy Measures for Robust Object Detection.Pattern Recognition Letters,2007,28(9):1083-1090.
[6]Songyan Ma,Lu Bai.A Face Detection Algorithm Based on AdaBoost and New Haar-like Feature.IEEE International Conference on Software Engineering and Service Science,Aug.2016:651-654.
[7]Ming-Hsuan Yang,Kriegman,D.J.,Ahuja,N.Detecting Faces in Images:A Survey.IEEE Transactions on Pattern Analysis and Machine Intelligence,Jan.2002,24(1):34-58.
[8]Ge Wei,Han Chunling,Quan Wei.Face Detection in Complex Background Based on AdaBoost Algorithm and YCbCr Skin Color Model.14 December 2015,9813.