基于特征脸的Adaboost检测算法与识别应用研究  

Research on Adaboost Detection Algorithm and Recognition Application Based on Eigenface

作　　者：张飞[1] Zhang Fei(Anhui Radio and Television University Fuyang Branch,Fuyang,Anhui 236000,China)

机构地区：[1]安徽广播电视大学阜阳分校,安徽阜阳236000

出　　处：《大理大学学报》2022年第6期18-21,共4页Journal of Dali University

摘　　要：随着人工智能理论与技术的发展,人脸检测与识别作为计算机视觉重要的分支,近年来成为学术界研究的重点。研究和实现了Adaboost人脸检测算法和基于特征脸的人脸识别算法。利用结合Adaboost检测器级联的特性,引入基于梯度方向金字塔和支持向量机的人脸分类算法,去除了部分误检测的结果;引入基于肤色模型的分割算法,对人脸区域进行精确定位,并对第二代身份证、Feret人脸数据库以及互联网图片资源进行人脸识别实验。结果表明,算法对正面人脸效果显著,识别速度快,准确率高。With the development of artificial intelligence theory and technology,face detection and recognition,as an important branch of computer vision,has become the focus of academic research in recent years. This paper studies and implements the Adaboost face detection algorithm and the face recognition algorithm based on eigenfaces. Using the cascading characteristics of Adaboost detectors,a face classification algorithm based on gradient direction pyramid and support vector machine is introduced,which removes part of the false detection results;a segmentation algorithm based on the skin color model is introduced to accurately perform the face area. Face recognition are experimented on the second-generation ID card,Feret face database,and internet image resources. The results show that the algorithm has a significant effect on frontal faces,with fast recognition speed and high accuracy.

关 键 词：人脸检测 人脸识别 ADABOOST 梯度方向金字塔 支持向量机 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]