| 基于AdaBoost和遗传算法的快速人脸定位算法 |
| |
| 引用本文： | 唐旭晟,欧宗瑛,苏铁明,华顺刚.基于AdaBoost和遗传算法的快速人脸定位算法[J].华南理工大学学报(自然科学版),2007,35(1):64-69. |
| |
| 作者姓名： | 唐旭晟 欧宗瑛 苏铁明 华顺刚 |
| |
| 作者单位： | 大连理工大学,精密与特种加工教育部重点实验室,辽宁,大连,116023 |
| |
| 基金项目： | 大连理工大学交叉学科基金资助项目(光电子 X2006) |
| |
| 摘 要： | 针对采用AdaBoost算法构建人脸检测器时存在的特征冗余问题,提出了一种新的快速人脸定位算法.首先用AdaBoost算法选取类Haar小波特征(称作AdaHaar特征),然后用遗传算法在低维的AdaHaar特征空间进一步优选,消除冗余并得到相应的权系数,最终的人脸检测器由这些优选的弱分类器及其相应权系数线性组合而成.实验结果表明,采用文中算法训练的人脸检测器在检测正确率、检测速度及占用内存等方面的性能都得到了改善.
|
| 关 键 词： | 人脸检测 人脸识别 AdaBoost算法 遗传算法 特征选取 模式识别 |
| 文章编号： | 1000-565X（2007）01-0064-06 |
| 修稿时间： | 2005-12-14 |
Fast Human Face-Detecting Algorithm Based on AdaBoost and Genetic Algorithm |
| |
| Tang Xu-sheng,Ou Zong-ying,Su Tie-ming,Hua Shun-gang.Fast Human Face-Detecting Algorithm Based on AdaBoost and Genetic Algorithm[J].Journal of South China University of Technology(Natural Science Edition),2007,35(1):64-69. |
| |
| Authors: | Tang Xu-sheng Ou Zong-ying Su Tie-ming Hua Shun-gang |
| |
| Institution: | Key Laboratory for Precision and Non-Traditional Machining Tech. of the Ministry of Education, Dalian Univ. of Tech. , Dalian 116023, Liaoning, China |
| |
| Abstract: | A novel fast human face-detecting algorithm is proposed to overcome the redundancy in the construction of human face detector by AdaBoost algorithm.In the investigation,AdaBoost algorithm is first used as a feature selector to select the Haar-like wavelet features,namely AdaHaar features.Then,the selected low-dimension AdaHaar features are further selected to optimally remove the redundancy and to obtain the corresponding weights.Finally,a human face detector is linearly aggregated by the selected features and the weights.Experimental results show that the proposed human face detector can accurately and fast locate face with low memory cost. |
| |
| Keywords: | human face detection human face recognition AdaBoost algorithm genetic algorithm feature extraction pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
