| 基于改进PLSA分类器的目标分类算法 |
| |
| 引用本文： | 赵宏伟,陈霄,龙曼丽,袁世培.基于改进PLSA分类器的目标分类算法[J].吉林大学学报(工学版),2012(Z1):231-235. |
| |
| 作者姓名： | 赵宏伟 陈霄 龙曼丽 袁世培 |
| |
| 作者单位： | 吉林大学计算机科学与技术学院;吉林大学公共外语教育中心 |
| |
| 基金项目： | 国家自然科学基金项目(61101155);吉林省科技发展计划项目(20101504) |
| |
| 摘 要： | 通过SIFT描述目标特征,利用Bag-of-words模型将目标特征构建为codebook,通过PLSA分类器对目标进行分类,根据PLSA分类学习过程中存在迭代复杂的问题,将贝叶斯分类器中的直接统计方法替换PLSA中最大似然估计,为PLSA提供足够的先验知识,减少学习过程中迭代次数,实验结果表明,相比于传统PLSA分类算法,本文方法检测结果较为准确,算法切实可行。
|
| 关 键 词： | 计算机应用 SIFT描述 Bag-of-words PLSA 贝叶斯分类器 目标分类 |
Object classification algorithm based on improved PLSA |
| |
| ZHAO Hong-wei,CHEN Xiao,LONG Man-li,YUAN Shi-pei.Object classification algorithm based on improved PLSA[J].Journal of Jilin University:Eng and Technol Ed,2012(Z1):231-235. |
| |
| Authors: | ZHAO Hong-wei CHEN Xiao LONG Man-li YUAN Shi-pei |
| |
| Affiliation: | 1(1.Department of Computer Science and Technology,Jilin University,Changchun 130012,China;2.School of Foreign Language Education,Jilin University,Changchun 130012,China) |
| |
| Abstract: | The feature of object is described by SIFT.According to Bag-of-words model,Codebook is make from the features representation.Finally,classify the object by method of PLSA.Due to the iteration of complex issue in the learning process of the PLSA classification,direct statistical method in Bayesian classifier replaces the maximum likelihood estimates in PLSA,Thus provide sufficient prior knowledge for PLSA and reduce the number of iterations in the learning process.Experimental results show that the proposed method is more effective than the traditional method for object detection,and that is valid and feasible. |
| |
| Keywords: | |
| 本文献已被 CNKI 等数据库收录！ |
|
