基于AdaBoost算法的易拉罐检测方法  

Pop can detection based On AdaBoost

作　　者：肖仁锋[1] 

机构地区：[1]济南职业学院计算机系,山东济南250103

出　　处：《河北省科学院学报》2014年第3期1-5,共5页Journal of The Hebei Academy of Sciences

摘　　要：提出了基于Adaboost算法的易拉罐检测方法。易拉罐检测器的训练,是基于AdaBoost算法思想,分别使用Haar特征、LBP特征对易拉罐图像进行特征提取,并对两者训练检测器的过程差异及最终效果作出比较。实验证明,基于AdaBoost算法训练的易拉罐检测器,检测率高且速度快。A method of pop-cans detection is proposed based on AdaBoost technique. The training of detector are based on the thought of AdaBoost, and uses Haar, LBP to extract the feature of pop-cans image. And the difference of training process and final result are com- pared. Experiment shows that the algorithm has high detection rate and speed.

关 键 词：ADABOOST算法 HAAR特征 LBP特征 检测器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]