[1]刘辉,徐晨,曹文明.基于Clifford代数的多光谱图像边缘检测[J].东南大学学报(自然科学版),2012,42(2):244-248.[doi:10.3969/j.issn.1001-0505.2012.02.010]
 Liu Hui,Xu Chen,Cao Wenming.Edge detection of multispectral image based on Clifford algebra[J].Journal of Southeast University (Natural Science Edition),2012,42(2):244-248.[doi:10.3969/j.issn.1001-0505.2012.02.010]
点击复制

基于Clifford代数的多光谱图像边缘检测()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
42
期数:
2012年第2期
页码:
244-248
栏目:
计算机科学与工程
出版日期:
2012-03-20

文章信息/Info

Title:
Edge detection of multispectral image based on Clifford algebra
作者:
刘辉 徐晨 曹文明
深圳大学信息工程学院,深圳 518000
Author(s):
Liu Hui Xu Chen Cao Wenming
College of Information Engineering, Shenzhen University, Shenzhen 518000, China
关键词:
多光谱图像 边缘检测 Clifford代数 Clifford梯度 图像融合
Keywords:
multispectral image edge detection Clifford algebra Clifford gradient image fusion
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2012.02.010
摘要:
为了充分利用多光谱图像不同图层之间的关联性,采用Clifford代数描述多光谱图像.在Clifford代数空间中,定义了多光谱图像的Clifford微分与Clifford梯度.在此基础上,提出了一种新的多光谱图像边缘检测与融合算法.该算法首先计算出各像素点的Clifford梯度,进而得到Clifford梯度范数; 然后以此为依据,判断像素点是否为边界点,从而得到多幅边缘检测图像; 最后,将这些图像融合,便可得到最终的边缘图像.与基于最大熵的多光谱图像边缘检测算法的比较结果表明,算法由于利用了多光谱图像不同图层之间的关联性,因而可以更好地保留边缘信息,获得更完整的边缘检测效果.
Abstract:
In order to make a full use of the connection among different layers of a multispectral image, the Clifford algebra is used to describe the multispectral image. The Clifford derivative and the Clifford gradient of the multispectral image are defined in the Clifford algebra space. Then a new edge detection and fusion algorithm is proposed by analyzing the edge detection and fusion of the multispectral image. In the algorithm, the Clifford gradient for each pixel in the image is computed and the corresponding Clifford normal number is obtained. Whether a pixel is the edge pixel is then judged with the normal number, and several edge detection images are obtained. Finally, the last edge image is deduced by fusing these edge detection images. The comparison results between the proposed algorithm and the edge detection algorithm based on the maximal entropy show that by taking full advantage of the connection among different layers of the multispectral image, the proposed algorithm can keep more integrated edge information of the multispectral image and obtain more complete edges.

参考文献/References:

[1] Landgrebe D.Information extraction principles and methods for multispectral and hyperspectral image data,information processing for remote sensing [M].Singapore:World Scientific Publishing Co.,Pte.Ltd.,1999:3-36.
[2] Mazzoni D,Garay M J,Davies R,et al.An operational MISR pixel classifier using support vector machines [J].Remote Sensing of Environment,2007,107(1/2):149-158.
[3] Manian V,Vasquez R.Multiresolution edge detection algorithm applied to SAR images [J].IEEE Transactions on Geoscience and Remote Sensing Symposium,1999,2:1291-1293.
[4] Rydberg A,Borgefors G.Extracting multispectral edges in satellite images over agricultural fields [C] //Proceedings of 1999 International Conference on Image Analysis and Processing.Venice,Italy,1999:786 -791.
[5] Ruzon M A,Tomasi C.Edge,junction and corner detection using color distributions [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(11):1281-1295.
[6] Trahanias P E,Venetsanopoulos A N.Color edge detection using vector order statistics [J].IEEE Transactions on Image Processing,1993,2(2):259-264.
[7] Economou G,Fotinos A,Fotopoulos S.Color image edge detection based on nonparametric density estimation [C] //Proceedings of 2001 International Conference on Image Processing.Thessaloniki,Greece,2001:922-925.
[8] Younan N H,Ponnala K,Alapati N.Edge detection in multispectral imagery via maximum entropy [EB/OL].(2005-08)[2011-10-10].http://www.isprs.org/publications/related/ISRSE/html/papers/550.pdf.
[9] Theoharatos C,Tsagaris V,Economou G,et al.Edge detection of multispectral images using nonparametric local density estimation [C] //Proceedings of the IASTED International Conference on Signal Processing,Pattern Recognition,and Applications.Rhodes,Greece:ACTA Press,2003:42-47.
[10] 徐晨,刘辉,欧阳春娟,等.多光谱图像Clifford拟微分算子及应用[J].中国科学:信息科学,2011,41(12):1423-1435.
  Xu Chen,Liu Hui,Ouyang Chunjuan,et al.Theory and application of Clifford pseudo-differential operator on multispectral image [J].Scientia Sinica:Informationis,2011,41(12):1423-1435.(in Chinese)
[11] Batard T,Saint-Jean C,Berthier M.A metric approach to nD images edge detection with Clifford algebras [J].Journal of Mathematical Imaging and Vision,2009,33(3):296-312.
[12] Xu C,Liu H,Cao W M,et al.Multispectral image edge detection via Clifford gradient [J].Sci China Inf Sci,2012,55:260-269.
[13] Burlakov M P.Clifford structures on manifolds [J].Journal of Mathematical Sciences,1998,89(3):1311-1333.
[14] 曹文明,冯浩.仿生模式识别与信号处理的几何代数方法 [M].北京:科学出版社,2010:84-121.
[15] Graham F.Multispectral image database [EB/OL].(2008-07-23)[2011-10-10].http://www.uea.ac.uk/cmp/research/graphicsvisionspeech/colour/data-code/multispectral-image-db.

相似文献/References:

[1]王培珍,陈维南.一种基于融合技术的图像边缘检测方案[J].东南大学学报(自然科学版),2001,31(6):78.[doi:10.3969/j.issn.1001-0505.2001.06.019]
 Wang Peizhen,Chen Weinan.A New Edge Detection Technique Based on Data Fusion[J].Journal of Southeast University (Natural Science Edition),2001,31(2):78.[doi:10.3969/j.issn.1001-0505.2001.06.019]
[2]崔力,浩明.基于视觉注意机制的图像质量评价[J].东南大学学报(自然科学版),2012,42(5):854.[doi:10.3969/j.issn.1001-0505.2012.05.011]
 Cui Li,Hao Ming.Image quality assessment based on visual attention mechanism[J].Journal of Southeast University (Natural Science Edition),2012,42(2):854.[doi:10.3969/j.issn.1001-0505.2012.05.011]

备注/Memo

备注/Memo:
作者简介: 刘辉(1977—), 男, 博士生; 曹文明(联系人), 男, 博士, 教授, wmcao@szu.edu.cn.
基金项目: 国家自然科学基金资助项目(61070087)、深圳市基础基金资助项目(JC201005800305280570A, JC201105080030534011A).
引文格式: 刘辉,徐晨,曹文明.基于Clifford代数的多光谱图像边缘检测[J].东南大学学报:自然科学版,2012,42(2):244-248. [doi:10.3969/j.issn.1001-0505.2012.02.010]
更新日期/Last Update: 2012-03-20