|
|||||
|
|
| 低分辨率人脸序列的超分辨率重构识别 | |
| 引用本文： | 张地,何家忠,彭宏.低分辨率人脸序列的超分辨率重构识别[J].韶关学院学报,2007,28(6):32-35. |
| 作者姓名： | 张地 何家忠 彭宏 |
| 作者单位： | 1. 韶关学院,计算机系,广东,韶关,512005;华南理工大学,计算机学院,广东,广州,510641 2. 韶关学院,计算机系,广东,韶关,512005 3. 华南理工大学,计算机学院,广东,广州,510641 |
| 摘 要： | 针对低分辨率人脸序列的识别这一问题,提出了一种超分辨率重构识别算法.该算法利用低分辨率序列中所提供的关于同一人脸的不同信息,先重构出一幅具有更高分辨率的人脸图像,然后再进行基于Gabor特征的人脸识别.实验结果表明,该算法能够显著提高人脸识别率. |
| 关 键 词： | 超分辨率 图像重构 人脸识别 |
| 文章编号： | 1007-5348（2007）06-0032-04 |
| 修稿时间： | 2007-03-22 |
Face super-resolution reconstruction and recognition from low-resolution image sequences |
|
| ZHANG Di,HE Jia-zhong,PENG Hong.Face super-resolution reconstruction and recognition from low-resolution image sequences[J].Journal of Shaoguan University(Social Science Edition),2007,28(6):32-35. | |
| Authors: | ZHANG Di HE Jia-zhong PENG Hong |
| Institution: | 1.Department of Computer,Shaoguan University,Shaoguan 512005,Guangdong,China;2.College of Computer,South China University of Technology,Guangzhou 510641,Guangdong,China |
| Abstract: | The recognition rate of normal face recognition algorithms drops dramatically when the resolution of face is too low.In this paper,a new hybrid face recognition algorithm is proposed to tackle the problem of face recognition from low resolution image sequences.The proposed approach first constructs a highresolution face image by fully utilizing the sub-pixel information provided in the low-resolution sequences,and then performs Gabor feature based recognition.Experimental results are also provided to demonstrate the effectiveness of the proposed algorithm. |
| Keywords: | super-resolution image reconstruction face recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |