| 基于Adaboost算法的人脸检测技术的研究与实现 |
| |
| 引用本文： | 张宁,李娜.基于Adaboost算法的人脸检测技术的研究与实现[J].现代电子技术,2011,34(14):4-6. |
| |
| 作者姓名： | 张宁 李娜 |
| |
| 作者单位： | 1. 华北电力大学电子与通信工程系,河北,保定,071003
2. 保定职业技术学院基础科学部,河北,保定,071003 |
| |
| 摘 要： | 人脸检测是人脸识别技术的基础，首先提出人脸检测系统的构成，分析Adaboost算法对图像进行人脸检测的基本原理。根据Adaboost算法形成了简单的矩形特征作为人脸特征，即Haar-like特征，然后由多个Haar-like特征相当于一个弱分类器，由多个弱分类器级联成为一个强的分类器，并将级联分类器用于动态人脸检测中，从截取的每一帧图像中进行检测。经过实验验证，采用这种方法和步骤进行人脸检测达到了比较好的精度和速度，N-I~T来的人脸识别提供了前提条件。
|
| 关 键 词： | 人脸检测 Adaboost算法 级联分类器 矩形特征 |
Research and Realization of Face Detection Technology Based on Adaboost Algorithm |
| |
| ZHANG Ning,LI Na.Research and Realization of Face Detection Technology Based on Adaboost Algorithm[J].Modern Electronic Technique,2011,34(14):4-6. |
| |
| Authors: | ZHANG Ning LI Na |
| |
| Affiliation: | ZHANG Ning1,LI Na2(1.Department of Electronics and Communication Engineering,North China Electric Power University,Baoding 071003,China,2.Basical Science Department,Baoding Vocational and Technical College,China) |
| |
| Abstract: | Face detection is the basis of face recognition.The structure of the face detection system is introduced and the basic principles of Adaboost algorithm is analyzed inthis paper.Based on Adaboost algorithm,a simple rectangular feature is formed as a facial feature,whch is Haar-like features.A weak classifier is formed by a number of Haar-like features,and multiple weak classifiers are cascaded into a strong classifier.The cascade classifier is used in dynamic face detection to detect faces captured from each... |
| |
| Keywords: | detection of human face Adaboost algorithm cascade classifier rectangle feature |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
