| 一种Adaboost快速训练算法 |
| |
| 引用本文： | 钱志明,徐丹.一种Adaboost快速训练算法[J].计算机工程,2009,35(20):187-188. |
| |
| 作者姓名： | 钱志明 徐丹 |
| |
| 作者单位： | 1. 云南大学信息学院计算机系,昆明,650091;楚雄师范学院,楚雄,675000
2. 云南大学信息学院计算机系,昆明,650091 |
| |
| 基金项目： | 国家自然科学基金资助项目 |
| |
| 摘 要： | 为解决基于Adaboost算法的人脸检测训练耗时的问题，提出一种Adaboost快速训练算法。基于原算法，在训练中使用序列化表格选取弱特征，在一轮训练结束后不进行样本权值更新，直接在已选分类器的基础上利用直方图统计的方法进行下一轮训练。实验证明该算法有较高的训练效率。
|
| 关 键 词： | 人脸检测 分类器 训练算法 |
| 修稿时间： | |
Fast Adaboost Training Algorithm |
| |
| QIAN Zhi-ming,XU Dan.Fast Adaboost Training Algorithm[J].Computer Engineering,2009,35(20):187-188. |
| |
| Authors: | QIAN Zhi-ming XU Dan |
| |
| Affiliation: | (1. Dept. of Computer, School of Information Science and Engineering, Yunnan University, Kunming 650091;2. Chuxiong Normal University, Chuxiong 675000) |
| |
| Abstract: | In order to solve the problem of long training time in face detection with Adaboost algorithm, this paper presents a fast Adaboost training algorithm. Based on original Adaboost, it uses the serialization table to select weaker classifier in training process. After a round of training, it does not update the sample weights but does the next round training by using histogram statistics, which is based on the selected classifier. Experimental result show that the algorithm gains higher training efficiency. |
| |
| Keywords: | face detection classifier training algorithm |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
|
