[1]LIU Yong-mei,DAI Li-jie.An improved method of Kmeans image segmentation based on spatial position information[J].CAAI Transactions on Intelligent Systems,2010,5(1):67-69.
Copy

An improved method of Kmeans image segmentation based on spatial position information

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 5 Number of periods: 2010 1 Page number: 67-69 Column: 学术论文—机器学习 Public date: 2010-02-25
Title:
An improved method of Kmeans image segmentation based on spatial position information
Author(s):
LIU Yong-mei;  DAI Li-jie
School of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
Keywords:
Kmeans clustering;  image segmentation;  spatial position information
CLC:
TP391
DOI:
-
Abstract:
Kmeans clustering is an effective algorithm for image segmentation, which attempts to separate objects of interest from their background. Traditional Kmeans clustering algorithms use the visual similarity measures of pixels in the feature space to determine which segmentation region the pixels belong to. Because of the complexity of natural images, neighboring pixels with different visual features, which should be treated as part of the same object, may end up in separate regions. As a result, it is hard to get satisfactory results when depending only on visual features. A spatially constrained image segmentation algorithm was therefore developed. It improved on the Kmeans clustering algorithm by adding a corrective step, the application of positional information from neighboring pixels. Experiments showed that the algorithm is effective.
References:
［1］章毓晋. 图像工程［M］. 北京：清华大学出版社，2000：7375.
［2］ZHOU Junni，CAO Jianzhong，LIU Bo，et al．New image segmentation methods based on regionally minimal cost watershed transform［J］．Acta Photonica Sinica， 2005， 34(1)： 142145.
［3］DORIN C，VISVANATHAN R，PETER M．Kernelbased object tracking［J］．IEEE Transactions on Pattern Analysis and Machine Intelligence， 2003， 25(5)： 564577.
［4］CHEN Qiuxiao，CHEN Shupeng，ZHOU Chenghu．Segmentation approach for remote sensing images based on local homogeneity gradient and its evaluation［J］．Journal of Remote Sensing， 2006， 10(3)： 357365.
［5］LI Huihui，GUO Lei，LIU Hang．A region based remote sensing image fusion method［J］．Acta Photonica Sinica， 2005， 34(12)： 19011905.
［6］刘金梅,赵春晖.组合均值平移和区域合并的图像分割算法［J］.哈尔滨工程大学学报, 2008, 29(10): 11261130.
?LIU Jinmei, ZHAO Chunhui. Image segmentation with mean shift and region merging methods［J］. Journal of Harbin Engineering University,2008, 29(10): 11261130.
?［7］张海军，王春光，翟改霞.用小波分析进行基于遗传算法的2DMBV图像分割［J］.自动化技术与应用， 2008, 27(4): 1518, 23.
?ZHANG Haijun,WANG Chunguang,ZHAI Gaixia. ZDMBV image segmentation based on gentic algorithm with wavelet analysis［J］.Techniques of Automation and Applications, 2008， 27(4): 1518, 23. 
［8］刘健庄，涂予青.使用高效C均值聚类算法的图像阈值化方法［J］. 电子科学学刊， 1992, 14(4): 424427.
LIU Jianzhuang,TU Yuqing. Thresholding of images using an efficient Cmean clustering algorithm［J］.Journal of Electronics, 1992, 14(4): 424427.
［9］杨淑莹. 图像模式识别——VC+〖KG-*1/3〗+技术实现［M］. 北京：清华大学出版社， 2005： 202205.
Similar References:

Memo

-

Last Update: 2010-03-31

Copyright © CAAI Transactions on Intelligent Systems