Regionalized fuzzy C-means algorithm for segmentation of color remotesensing image

被引：0

作者：

Zhao, Quan-Hua ^{[1
]}

Li, Hong-Ying ^{[1
]}

Li, Yu ^{[1
]}

机构：

[1] School of Geomatics,, Liaoning Technical University,, Fuxin

来源：

Kongzhi yu Juece/Control and Decision | 2015年 / 30卷 / 09期

关键词：

Fuzzy C-means; Regionalized segmentation; Remote sensing segmentation; Voronoi tessellation;

D O I：

10.13195/j.kzyjc.2014.0848

中图分类号：

学科分类号：

摘要：

The improvement in spatial resolution of high resolution remote sensing images increases the internal spectral variability of each land cover class and induces geometric noise caused by tiny targets on it, so pixed based FCM and its improved algorithms can not overcome the difficulties during segmentation. Therefore, a regionalized fuzzy C-means (RFCM) algorithm is proposed for high resolution remote sensing image segmentation. By Voronoi tessellation, the image domain is partitioned into Voronoi polygons to fit the shapes of objects with the polygons. On the basis of the domain partition, the FCM's objective function is defined for the segmentation of high resolution remote sensing image. Test results show that the proposed algorithm is capable of segmenting high resolution remote sensing image with higher accuracy than the FCM and the enhanced FCM algorithm (EFCM). ©, 2015, Northeast University. All right reserved.

引用

页码：1706 / 1710

页数：4

共 13 条

[1]

Benediktsson J.A., Chanussot J., Moon W.M., Very high-resolution remote sensing: Challenges and opportunities, Proc of the IEEE, 100, 6, pp. 1907-1910, (2012)

[2]

Bruzzone L., Carlin L., A multilevel context-based system for classification of very high spatial resolution images, IEEE Trans on Geoscience and Remote Sensing, 44, 9, pp. 2587-2600, (2006)

[3]

Pham D.L., Spatial models for fuzzy clustering, Computer Vision and Image Understand, 84, 2, pp. 285-297, (2001)

[4]

Zedeh L., Fuzzy sets, Information Control, 8, 3, pp. 338-353, (1965)

[5]

Han M., Shen L.H., Case-based reasoning nased on FCM and neural network, Control and Decision, 27, 9, pp. 1421-1424, (2012)

[6]

He Z.H., Lei Y.J., Research on intuitionistic fuzzy C-means clustering algorithm, Control and Decision, 26, 6, pp. 847-850, (2011)

[7]

Cai W., Chen S., Zhang D., Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation, Pattern Recognition, 40, 3, pp. 825-838, (2007)

[8]

Xiao M.S., Lu Y., Zeng R., Research on image reconstruction by fcm of weighted characteristic, Control and Decision, 24, 12, pp. 1917-1920, (2009)

[9]

Chatzis S.P., Varvarigou T.A., A fuzzy clustering approach toward hidden markov random field models for enhanced spatially constrained image segmentation, IEEE Trans on Fuzzy System, 16, 5, pp. 1351-1361, (2008)

[10]

Miyamoto S., Mukaidono M., Fuzzy C-means as a regularization and maximum entropy approach, Proc of 7th Int Fuzzy System Associate World Congrress, pp. 86-92, (1997)

← 1 2 →