2019219-1
研究与开发
基于拟合型弱分类器的 AdaBoost 算法
宋鹏峰,叶庆卫,陆志华,周宇
(宁波大学信息科学与工程学院,浙江 宁波 315211)
摘 要:针 对 AdaBoost 算法通过最小化训练错误率来选择弱分类器造成的精度不佳问题以及单阈值作为弱分
类器训练过程较慢难以收敛问题,提出了一种基于拟合型弱分类器的 AdaBoost 算法。首先针对每个特征,在
特征值与标记值之间建立映射关系,引入最小二乘法求解拟合多项式函数,并转换成离散分类值,从而获得
弱分类器。其次从获得的众多弱分类器中,选择分类误差最小的弱分类器作为本轮迭代的最佳弱分类器,构
成新的 AdaBoost 强分类器。与传统训练算法相比,极大地减少了待选弱分类器的个数。选取 UCI 数据集和
MIT 人脸图像数据库进行实验验证,相较于传统 Discrete-AdaBoost 算法,改进算法的训练速度提升了一个数
量级,人脸检测率可达 96.59%。
关键词:AdaBoost;拟合型;最小二乘法;弱分类器
中图分类号:TP391.4
文献标识码:A
doi: 10.11959/j.issn.1000−0801.2019219
AdaBoost algorithm based on fitted weak classifier
SONG Pengfeng, YE Qingwei, LU Zhihua, ZHOU Yu
College of Information Science and Engineering, Ningbo University, Ningbo 315211, China
Abstract: AdaBoost algorithm was proposed to minimize the accuracy caused by weak classifiers by minimizing the
training error rate, and the single threshold was weaker and difficult to converge. The AdaBoost algorithm based on
the fitted weak classifier was proposed. Firstly, the mapping relationship between eigenvalues and marker values was
established. The least squares method was introduced to solve the fitting polynomial function, and the continuous fit-
ting values were converted into discrete categorical values, thereby obtaining a weak classifier. From the many classi-
fiers obtained, the classifier with smaller fitting error was selected as the weak classifier to form a new AdaBoost
strong classifier. The UCI dataset and the MIT face image database were selected for experimental verification.
Compared with the traditional Discrete-AdaBoost algorithm, the training speed of the improved algorithm was in-
creased by an order of magnitude. And the face detection rate can reach 96.59%.
Key words: AdaBoost, fitting type, least squares, weak classifier
收稿日期:2019−03−09;修回日期:2019−09−12
基金项目:国家自然科学基金资助项目(No.51675286,No.61071198)
Foundation Items: The National Natural Science Foundation of China (No.51675286, No.61071198)