摘要
针对视频监控中的高维度和复杂环境的困难,文章提出一种基于主成份分析与Adaboost的视频人脸检测算法.该方法先使用PCA方法对特征空间进行降维,并以PCA特征建立误分率最小化弱分类器,最后使用Adaboost算法提升弱分类器性能,将所有已训练的弱分类器联合成一个强分类器.实验证明,在正面人脸样本和具有复杂表情变化的人脸测试集上,该方法可以得到很好的检测结果.
For difficulties of high dimensions and complex environment in video surveillance, the paper proposes a face detection method based on PCA incorporating with Adaboost. Firstly, PCA is used to reduce image feature space. Then, the weak classifiers are constructed on PCA features according to the minimum error rate. Finally, the Adaboost algorithm combines all trained weak classifiers into a strong classifier in order to improve the recognition rate. The experiment results show that the method has good performance in frontal face and different expressions samples.
出处
《杭州师范大学学报（自然科学版）》
CAS
2009年第2期144-147,共4页
Journal of Hangzhou Normal University(Natural Science Edition)
基金
国家自然科学基金项目(60773051)
浙江省自然科学基金项目(Y107631)
浙江省科技计划项目(8C23033)
浙江省科技厅新苗计划项目(2008R40G2150179)
