删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

基于局部正脸合成和两阶段表示的三阶段人脸识别算法

本站小编 Free考研考试/2021-12-21
本文二维码信息
二维码（扫一下试试看！）
基于局部正脸合成和两阶段表示的三阶段人脸识别算法
Three-Phase Face Recognition Algorithm via Locally Frontal Face Synthesis and Two-Phase Face Recognition
投稿时间：2014-04-28
DOI：10.15918/j.tbit1001-0645.2017.06.016
中文关键词:人脸识别正脸合成稀疏表示
English Keywords:face recognitionfrontal face synthesissparse representation
基金项目:国家自然科学基金资助项目（61175096，60940024）
作者单位
赵清杰北京理工大学计算机学院, 智能信息技术北京市重点实验室, 北京 100081
齐惠北京理工大学计算机学院, 智能信息技术北京市重点实验室, 北京 100081
张雨北京理工大学计算机学院, 智能信息技术北京市重点实验室, 北京 100081
王浩北京理工大学计算机学院, 智能信息技术北京市重点实验室, 北京 100081
摘要点击次数:1069
全文下载次数:1130
中文摘要:
基于两阶段表示的人脸识别算法（TPTSR）识别率高，并且对遮挡、噪声等干扰鲁棒，但是当人脸姿态有较大变化时，TPTSR算法的识别率会明显下降.针对这一问题，提出基于局部正脸合成和TPTSR的三阶段人脸识别算法：第一个阶段，正脸合成阶段，利用提出的正脸合成算法和视点库，将偏转角度较大的测试样本合成相应的正脸，作为新的测试样本；第二个阶段，样本筛选阶段，选择出对最新的测试样本最具表示能力的M个训练样本；第三个阶段，决策识别阶段，用这M个训练样本做人脸识别.通过与经典算法的对比实验证明，提出的3PTSR人脸识别算法能有效解决多姿态人脸识别问题.
English Summary:
Two-phase test sample representation algorithm (TPTSR), which is robust to interference such as occlusion and noise, performs well in face recognition without pose variation. However, its recognition rate will decline when the face pose varies dramatically. To solve this problem, a three-phase test sample representation algorithm was proposed. The first was frontal face synthesizing was a frontal face with small horizontal deflection angle was synthesized using view-library and proposed frontal face synthesizing algorithm. Thus, a frontal face was synthesized as the new test sample. The second was training sample selecting phase, M training samples that make the most contribution were selected to represent the new test sample. The third was decision and recognition phase, a face was recognized using the M training samples. Experiments on some publicly available face recognition benchmarks demonstrate that the proposed 3PTSR algorithm outperforms the state-of-the-art methods in challenging conditions, especially for the face with various poses.
查看全文查看/发表评论下载PDF阅读器
相关话题/北京 智能 测试 中文 信息

Free考研考试FreeKaoYan.Com
欢迎来到Free考研考试，"为实现人生的Free而奋斗"

© 2020 FreeKaoYan! . All rights reserved.