中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
机构
采集方式
内容类型
发表日期
学科主题
筛选

浏览/检索结果: 共3条,第1-3条 帮助

条数/页: 排序方式:
Robust tracking based on local structural cell graph 期刊论文  OAI收割
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2015, 卷号: 31
作者:  
Fan, Heng;  Xiang, Jinhai;  Liao, Honghong;  Du, Xiaoping
收藏  |  浏览/下载:26/0  |  提交时间:2016/04/20
Face Recognition by Exploring Information Jointly in Space, Scale and Orientation 期刊论文  OAI收割
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 卷号: 20, 期号: 1, 页码: 247-256
作者:  
Lei, Zhen;  Liao, Shengcai;  Pietikainen, Matti;  Li, Stan Z.
收藏  |  浏览/下载:25/0  |  提交时间:2015/11/08
Assessment of color image fusion algorithms based on quaternion singular value decomposition (EI CONFERENCE) 会议论文  OAI收割
MIPPR 2009 - Remote Sensing and GIS Data Processing and Other Applications: 6th International Symposium on Multispectral Image Processing and Pattern Recognition, October 30, 2009 - November 1, 2009, Yichang, China
作者:  
Wang Y.;  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y.
收藏  |  浏览/下载:23/0  |  提交时间:2013/03/25
In this paper  a new approach to objectively assess the performance of image fusion algorithms is proposed. It is based on the quaternion representation for the structural information of color images. Quaternions are used to encode the pixels of a color image into a quaternion matrix. Local variance of the luminance layer of color image is taken as the real part of a quaternion  then the three RGB channels of the color image are encoded into the three imaginary parts of the quaternion. The angle between the singular value feature vectors of the quaternion matrices corresponding to the source image and the fused image is used to measure the structural similarity of them. Different weight is given to the source images by using variance. The experiment results show that the proposed assessment method is consistent with the HVS. The color information of a color image can be fully used by this method. It can give an accurate assessment result for each fusion algorithm by using the source images and the fused image. 2009 Copyright SPIE - The International Society for Optical Engineering.