当前位置: 首页 > 文章 > 一种用于监控系统中的人脸超分辨率图像重建方法 河北农业大学学报 2013,36 (6) 124-127
Position: Home > Articles > A face superresolution algorithm in video sequence of monitoring system Journal of Agricultural University of Hebei 2013,36 (6) 124-127

一种用于监控系统中的人脸超分辨率图像重建方法

作  者:
高冠东;刘菲;王晶;段庆;朱杰
单  位:
中央司法警官学院信息管理系
关键词:
超分辨率重建;块匹配;图像序列;监控系统
摘  要:
为了能够提高监控系统中模糊人脸视频的分辨率,从而用于案件取证及身份识别。利用监控系统中的人脸图像序列,提出了一种基于块匹配的人脸超分辨率图像重建方法,用于提高图像分辨率、获得清晰人脸图像。首先使用帧差法在图像序列中分割出人脸区域,然后在中间一帧图像中构建图像块,并与序列中其它图像相匹配,最后使用差值最小的匹配块融合并重建高分辨率人脸图像。经实验与其他现有算法比较的结果证明,本方法所得结果图像细节更清晰。
译  名:
A face superresolution algorithm in video sequence of monitoring system
作  者:
GAO Guan-dong;LIU Fei;WANG Jing;DUAN Qing;ZHU Jie;Department of information and Management,Central Institute for Correctional Police;
关键词:
superresolution reconstruction;;patch matching;;image sequence;;monitoring system
摘  要:
The resolution of face images usually need to be improved for crime detection,identity recognition and other fields in monitoring system.In this paper,a face superresolution algorithm based on patch reconstruction was presented to enlarge and make face image clear.The face images were segmented from the sequence by frame-difference method at first.Then,Patches were constructed in the middle frame of the sequence and matched with other frames.The matched patch that had minimum differences in one of other frames was used to reconstruct the high-resolution face image by fusion method.Experimental results showed that the proposed algorithm provided clearer and sharper details compared to the existing algorithms.

相似文章

计量
文章访问数: 8
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊