| 一种基于AdaBoost的快速动态人脸检测算法 |
| |
| 引用本文： | 邓亚峰,苏光大,傅博. 一种基于AdaBoost的快速动态人脸检测算法[J]. 计算机工程, 2006, 32(11): 222-224 |
| |
| 作者姓名： | 邓亚峰 苏光大 傅博 |
| |
| 作者单位： | 清华大学电子工程系,北京,100084 |
| |
| 摘 要： | 提出了一种结合人脸检测和跟踪的快速动态人脸检测算法。在层次型AdaBoost检测算法的基础上，结合提出的一种基于线性预测的人脸跟踪算法来缩小搜索空间，使得检测速度提高到24ms／帧。还设计了一种结合层次型AdaBoost算法、负样本反馈方式和利用权值缩减训练时间的检测器训练方法，可以方便地应用于物体检测技术上。
|
| 关 键 词： | 人脸检测 人脸跟踪 人脸识别 |
| 文章编号： | 1000-3428（2006）11-0222-03 |
| 收稿时间： | 2005-07-06 |
| 修稿时间： | 2005-07-06 |
An Algorithm of Fast Face Detection in Video Based on AdaBoost |
| |
| DENG Yafeng,SU Guangda,FU Bo. An Algorithm of Fast Face Detection in Video Based on AdaBoost[J]. Computer Engineering, 2006, 32(11): 222-224 |
| |
| Authors: | DENG Yafeng SU Guangda FU Bo |
| |
| Affiliation: | Department of Electronic Engineering, Tsinghua University, Beijing 100084 |
| |
| Abstract: | A fast face detection algorithm in video integrated with tracking is designed. It uses a cascade-structured face detector trained with AdaBoost to detect face. Integrated with a linear face tracker, searching region and rescaling levels of the detector are reduced, and thus detection speed is accelerated. It also designs a classifier training method integrated with AdaBoost, bootstrapping and weight-trimming, which can be easily used in object detection. |
| |
| Keywords: | Face detection Face tracking Face recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
