东北大学学报（自然科学版）

东北大学学报:自然科学版 ›› 2014, Vol. 35 ›› Issue (7): 955-959.DOI: 10.12068/j.issn.1005-3026.2014.07.010

• 信息与控制 • 上一篇    下一篇

基于混合蛙跳算法的长时间跨度人脸识别

李根，李文辉   

  1. (吉林大学 计算机科学与技术学院， 吉林 长春130012)
  • 收稿日期:2013-11-18 修回日期:2013-11-18 出版日期:2014-07-15 发布日期:2014-04-11
  • 通讯作者: 李根
  • 作者简介:李根(1982-)，男，吉林长春人，吉林大学博士研究生;李文辉(1961-)，男，吉林长春人，吉林大学教授，博士生导师.
  • 基金资助:
    吉林省科技发展计划重点项目(20120305);国家自然科学基金资助项目(60873147).

Long Time Span Face Recognition Based on SFLA

LI Gen， LI Wenhui   

  1. College of Computer Science and Technology， Jilin University， Changchun 130012， China.
  • Received:2013-11-18 Revised:2013-11-18 Online:2014-07-15 Published:2014-04-11
  • Contact: LI Wenhui
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

683

摘要： 面部特征中存在长时间不变特征和短时间不变特征，对两种特征分类，使用长时间不变特征完成长时间跨度人脸识别.首先以最佳覆盖为目标的特征对比方式，代替传统的以最佳划分为目标的特征对比方式，使用混合蛙跳算法实现特征对齐.然后根据时间段和特征值变化度计算每个对齐的特征点的权值和基准特征值，对长时间不变特征与短时间不变特征进行分类.在识别过程中，应用已识别的图像信息更新权值和基准特征值，进行长时间跨度的人脸识别.实验结果表明，该方法可以在以年为时间跨度的人脸识别过程中达到82%的识别率，优于其他算法.

关键词: 计算机应用, 混合蛙跳算法, 特征对齐, 人脸识别, 尺度不变特征变换

Abstract: The long time span invariable feature(LTSIF)and short time span invariable feature(STSIF)exist in face features. A method was proposed to classify the two types of features， then the LTSIF was used to recognize the long time span face image. First， the bestdivide method was replaced by the bestcoverage method to normalize the features based on shuffled frog leaping algorithm(SFLA). Second， the normalized featureweight and basevalue was calculated by the time span and the featurevariability to classify the LTSIF and STSIF. In the recognition process， the featureweight and basevalue were refreshed with the recognized face image to recognize the long time span face images. The results indicated that over 82% face images can be recognized by the proposed method in years’ time span， which was better than other algorithms.

Key words: computer application, SFLA(shuffled frog leaping algorithm), feature normalization, face recognition, SIFT(scale invariant feature transform)

中图分类号: