The conventional JSEG algorithm has a powerful detection capability on the homogeneity of regional texture features because it combines the spectral information with image texture features during the segmentation. However, the conventional JSEG method is not very accurate for the target edge localization in segmentation results. To solve this problem, this paper proposes an improved segmentation method of remotely sensed image based on JSEG algorithm and fuzzy c-means (FCM) with spatial constraints. Firstly, the FCM clustering method based on spatial neighborhood terms is used to replace the traditional HCM clustering method in the quantization step. Then the region growing method is applied to segment the class diagram after FCM clustering. Finally, the proposed method uses the improved regional merger approach to merger the over divided region after segmentation. According to the J index, the proposed algorithm is improved by 31% and 12% compared with the traditional JSEG segmentation method and improved by 17% and 8% compared with the FNEA segmentation algorithm for aerial image and the SPOT 5 image. The experimental results show that the proposed segmentation algorithm has good noise immunity because of the fuzzy clustering of spatial constraints and can extract the edge of the target more accurately.
Y.F.Zhong, B.Zhao and L.P.Zhang, Multiagent object-based classifier for high spatial resolution imagery, IEEE Transaction on Geoscience and Remote Sensing52(2) (2014), 841–857.
2.
H.M.Gao, Y.Yang, C.M.Li, H.Zhou and X.Y.Qu, Joint alternate small convolution and feature reuse for hypersectral image classification, ISPRS International Journal of Geo-Information7(349) (2018), 1–21.
3.
X.Wang, S.Q.Shen and C.Ning, Multi-class remote sensing object recognition based on discriminative sparse representation, Applied Optics55(6) (2016), 1381–1394.
4.
J.Q.Gao, L.Z.Xu and F.C.Huang, A spectral–textural kernel-based classification method of remotely sensed images, Neural Comput & Applic27(2) (2016), 431–446.
5.
A.Y.Shi, G.R.Gao and S.H.Shen, Change detection of bitemporal multispectral images based on FCM and D-S theory, Eurasip Journal on Advances in Signal Processing (2016), 96–96.
6.
Y.Zheng, J.Yang and Y.Zhou, Unsupervised segmentation on image with JSEG using soft class map, Lecture Notes in Computer Science3177 (2004), 197–202.
7.
Y.C.Chang, D.J.Lee and Y.G.Wang, Color-Texture segmentation of medical images based on local contrast information, IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (2007), 488.
8.
C.Wang, W.Xu and X.F.Pei, An unsupervised multi-scale segmentation method based on automated parameterization, Arabian Journal of Geosciences9(15) (2016), 651.
9.
J.Michel and D.Youssefi, Stable mean-shift algorithm and its application to the segmentation of arbitrarily large remote sensing images, IEEE Transactions on Geoscience and Remote Sensing53(2) (2015), 952–964.
10.
G.Poggi, G.Scarpa and J.B.Zerubia, Supervised segmentation of remote sensing images based on a tree-structured MRF model, IEEE Transactions on Geoscience and Remote Sensing43(8) (2005), 1901–1911.
11.
M.Baatz and A.Schpe, Multiresolution segmentation: An optimization approach for high quality multi-scale image segmentation, Wichmann, Heidelberg, Germany, 2000.
12.
Y.Deng and C.Kenney, Peer group filtering and perceptual color image quantization, Proceedings of IEEE International Symposium on Circuits and Systems4 (1999), 21–24.
13.
Y.Zheng and J.Yang, Unsupervised segmentation on image with JSEG using soft class map, Intelligent Data Engineering and Automated Learning–IDEAL Springer Berlin Heidelberg, 2004, pp. 197–202.
14.
Y.C.Chang, J.K.Archibald and Y.G.Wang, Texture-based color image segmentation using local contrast information, Computational Intelligence and Bioinformatics and Computational Biology4(5) (2007), 488–493.
15.
K.S.Komati, E.O.T.Salles and M.Sarcinelli Filho, Fractal-JSEG: JSEG using an homogeneity measurement based on local fractal descriptor, 22nd Brazilian Symposium on Computer Graphics and Image Processing, 2009, pp. 253–260.
16.
K.S.Komati and E.O.TSalles, Unsupervised color image segmentation based on local fractal descriptor and J-images, Proceedings of the 2010 IEEE International Conference on Industrial Technology, 2010, pp. 303–308.
17.
K.S.Komati, E.O.T.Salles and M.Sarcinelli Filho, Unsupervised color image segmentation based on local fractal dimension, Proceedings of the 17th International Conference on Systems, Signals and Image Processing, 2010, pp. 243–246.
18.
L.Z.Xu, X.F.Li and S.X.Yang, Intelligent information processing and system optimization, Intelligent Automation and Soft Computing17(7) (2011), 829–833.
19.
X.L.Zhang and P.F.Xiao, Toward evaluating multiscale segmentations of high spatial resolution remote sensing images, IEEE Transactions on Geoscience and Remote Sensing53(7) (2015), 3694–3706.
20.
M.X.Xu, F.Xu and C.R.Huang, Image restoration using majorization-minimizaiton algorithm based on generalized total variation, Journal of Image and Graphics6(7) (2011), 1317–1325.
21.
A.Shi, D.Q.Huynh, F.C.Huang, S.H.Shen, W.P.Lu and Z.L.Ma, Unsupervised change detection based on robust chi-squared transform for bitemporal remotely sensed images, International Journal of Remote Sensing35(21) (2014), 7555–7566.
22.
A.Shi, L.Xu, F.Xu and C.Huang, Multispectral and panchromatic image fusion based on improved bilateral filter, Journal of Applied Remote Sensing5(1) (2011), 053542–053542.
23.
L.Z.Xu, M.Li, A.Y.Shi, M.Tang and F.C.Huang, Feature detector model for multi-spectral remote sensing image inspired by insect visual system, Dianzi Xuebao(Acta Electronica Sinica)39(11) (2011), 2497–2501.
24.
C.M.Li, L.Q.Zhu and Q.Wang, High-resolution remote multi-spectral sensing images based on texture features, Applied Mechanics and Materials687 (2014), 3596–3599.
25.
N.Li and H.Huo, A novel texture-preceded segmentation algorithm for high-resolution imagery, IEEE Transactions on Geoscience and Remote Sensing48(7) (2010), 2818–2828.
26.
S.Chen and D.Q.Zhang, Robust image segmentation using FCM with spatial constraints based on new kernel induced distance measure, IEEE Transactions on System Man and Cybernetics-Part B34(4) (2004), 1907–1916.
27.
C.Wang, M.X.Xu, X.Wang, S.N.Zheng and Z.L.Ma, Object-oriented change detection approach for high-resolution remote sensing images based on multiscale fusion, Journal of Applied Remote Sensing7(1) (2013), 073696–073699.
28.
L.N.Yi and G.F.Zhang, A scale-synthesis method for high spatial resolution remote sensing image segmentation, IEEE Transactions on Geoscience and Remote Sensing50(10) (2012), 4062–4070.
29.
R.M.Haralick, K.Shanmugam and I.Dinstein, Texture features for image classification, IEEE Trans on Systems, Man and Cybernetics3(6) (1973), 610–621.
30.
C.Wang and L.Z.Xu, A Multi-scale Segmentation method of oil spills in SAR images based on JSEG and spectral clustering, International Journal of Signal Processing, Image Processing and Pattern Recognition7(1) (2014), 425–432.
31.
C.Wang, A.Y.Shi, X.Wang, F.M.Wu, F.C.Huang and L.Z.Xu, A Novel Multi-scale segmentation algorithm for high resolution remote sensing images based on wavelet transform and improved JSEG algorithm, International Journal for Light and Electron Optics (2014).
32.
J.Liu, J.Zhang and F.Xu, Adaptive Algorithm for automated polygonal approximation of high spatial resolution remote sensing imagery segmentation contours, IEEE Transactions on Geoscience and Remote Sensing52(2) (2014), 1099–1106.
