基于AdaBoost算法的易拉罐检测方法

Pop can detection based On AdaBoost

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.