An Improved Algorithm for Diverse AdaBoostSVM

摘要：

In order to improve the training convergence speed and detection accuracy of Diverse AdaBoostSVM, an improved algorithm is proposed according to the asymmetry in face detection. In the algorithm, the weight of each weak learner, which represents importance of each weak learner, is determined by the error rate and the recognition capability of the weak learner for the face samples. The results of the experiments show that the proposed algorithm could improve the training convergence speed and the detection accuracy in face detection.

作者: Song Guo Guochang Gu Haibo Liu Jing Shen Changyou Li

作者单位: School of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China School of Aerospace, Harbin Institute of Technology, Harbin 150001, China

会议类型: 国际会议

会议名称: The Second International Joint Conference on Computational Science and Optimization(CSO 2009)(2009 国际计算科学与优化会议)

会议地点: 三亚

会议语种:英文

页码: 839-842

在线出版日期: 2009-04-24（万方平台首次上网日期，不代表论文的发表时间）