Computer Science ›› 2014, Vol. 41 ›› Issue (12): 275-279.doi: 10.11896/j.issn.1002-137X.2014.12.059

Previous Articles     Next Articles

Band Grouping Based Hyperspectral Image Classification Using Mathematical Morphology and Support Vector Machines

ZHANG Fan,DU Bo,ZHANG Liang-pei and ZHANG Le-fei   

  • Online:2018-11-14 Published:2018-11-14

Abstract: How to analysis and recognize image accurately is an important issue in computer vision and pattern recognition fields.Remote sensing image,especially hyperspectral images combine spatial and spectral information in one data cube.In this paper,we proposed a band grouping feature selection method,then extracted morphology features.A feature selection algorithm called recursive feature elimination was applied to decrease the dimensionality of the input morphology features data.A support vector machine was used for the final classification.Experiments performed on real hyperspectral images,confirm that it is efficient using band grouping and mathematical morphology.

Key words: Classification,Hyperspectral image,Features selection,Morphology,Support vector machines

[1] 钟燕飞,张良培,李平湘.基于多值免疫网络的多光谱遥感影像分类[J].计算机学报,2007,30(12):2181-2188
[2] 王兆虎,刘芳,焦李成.一种基于视觉特性的遥感图像分割[J].计算机学报,2005,8(10):1686-1691
[3] Goetz A F H,Vane G,Solomon J E,et al.Imaging spectrometry for earth remote sensing[J].Science,1985(228):1147-1153
[4] Hsu Pai-hui.Feature extraction for hyperspectralimage[C]∥Proceeding of the 20th Asian Conference Remote Sensing.1999:408-410
[5] Yang Zhu-sheng,Guo Lei,Luo Xin.Research on segmentedPCA based on band selection algorithm of hyperspectral image[J].Engineering of Surveying and Mapping,2006,5:15-18
[6] Chavez P S,Berlin G L,Sowers L B.Statistical method for selecting Landsat MSS Ratios[J].Journal of Applied Photogramme-tric Engineering,1982,1:23-30
[7] Samiappan S,Prasad S,Bruce L M.Non-Uniform random feature selection and kernel density scoring with svmbased ensemble classification for hyperspectralimage analysis[J].IEEE Journal of PP Selected Topics in Applied Earth Observations and Remote Sensing,2013(99):1-9
[8] Prasad S,Bruce M.Decision fusion with confidence-based-weight assignment for hyperspectral target recognition[J].IEEE Transactions Geoscience and Remote Sensing,2008,6:1448-1456
[9] Soille P,Pesaresi M.Advances in mathematical morphology applied to geoscience and remote sensing[J].IEEE Transactions Geoscience and Remote Sensing,2002,0(9):2042-2055
[10] Haralick R M,Shanmugam K,Dinstein I.Textural featuresforimage classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,SMC-3(6):610-621
[11] Fauvel M,Tarabalka Y,Benediktsson J A,et al.Advances inSpectral-Spatial classification of hyperspectral Images[J].Proceedings of the IEEE PP,2012(99):1-24
[12] Kruizinga P,Petkov N,Grigorescu S E.Comparison of tex-turefeatures based on Gabor filters[C]∥Proc.Int.Conf.Image Anal.Process..1999:142-147
[13] Clausi D A,Deng H.Design-based texture feature fusionusingGabor filters and co-occurrence probabilities[J].IEEE Transactions Image Processing,2005,4(7):925-936
[14] Pesaresi M J,Benediktsson A.A new approach for the morphological segmentation of high-resolution satellite images[J].IEEE Transactions Geoscience and Remote Sensing,2001,39(2):309-320
[15] Fauvel M,Benediktsson J A,Chanussot J,et al.Spectral andspatial classification of hyperspectraldata using svms and morphological profiles[J].IEEE Transactions Geoscience and Remote Sensing,2008,46(11):3804-3814
[16] Hughes G.On the mean accuracy of statistical pattern recogni-zers[J].IEEE Transactions on Information Theory,1968,14(1):55-63
[17] Tuia D,Pacifici F,Kanevski M,et al.Classification of very high spatial resolution imagery using mathematical morphology and support vector machines[J].Geoscience and remote sensing,IEEE Transactions,2009,47(11):3866-3879
[18] Burges C J C.A tutorial on support vector machines for patternrecognition[J].Data Mining and Knowledge Discovery, 1998,2:212-167
[19] Chang C C,Lin C J.LIBSVM:A library for support vector machines.http://www.csie.ntu.edu.tw/~cjlin/libsvm

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!