抗外点干扰的鲁棒AdaBoost分类器构建方法-计算机工程与应用.pdf

132 2018 ，54（7 ） Computer Engineering and Applications 计算机工程与应用 ⦾模式识别与人工智能⦾ 用 抗外点干扰的鲁棒AdaBoost 分类器构建方法 应 曹万鹏，罗云彬，史 辉 与 CAO Wanpeng, LUO Yunbin, SHI Hui 程 g 北京工业大学 未来网络创新中心，北京 100124 r 工 o Advanced Innovation Center for Future Internet Technology, Beijing University of Technology, Beijing 100124, China . 机 j a CAO Wanpeng, LUO Yunbin, SHI Hui. Robust AdaBoost classifier construction method against outlier interference. e Computer Engineering and Applications, 2018, 54 （7 ）：132-137. 算 c 计 . Abstract ：Taking this reason that AdaBoost is sensitive to outliers, robust AdaBoost classifier is constructed against outlier w interference using Ransac. Different from the other weak classifier sample weighting and controlling method in AdaBoost, w Ransac is employed and introduced to the process of classifier model construction to overcome the drawbacks of the existing w AdaBoost weak classifier weighting algorithms. Meanwhile, the adverse affection of outliers can be effectively eliminated by virtue of the Ransac algorithm ’s strong ability in removing outliers. Through above strategy, the classifier degradation is able to be avoided. Finally, in the validation experiment, the designed classifier model is applied in the handwriting samples classification including some outliers. The experimental results show its validity. Key words ：AdaBoost classifier; Ransac algorithm; sample weighting; classification 摘 要：根据AdaBoost 算法易受外点影响这一缺陷，提出一种利用Ransac 算法实现抗外点干扰的鲁棒AdaBoost 分 类器构建方法。不同于其他AdaBoost 算法在分类器构建中单纯使用样本加权或权值控制的手段，该算法将Ransac 算法引入AdaBoost 分类器模型构建