An Efficient Spectral Spatial Classification for Hyper Spectral Images

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    An expanded random walker comprises of two primary advances ghostly spatial order strategy for hyper Ghastly pictures. To begin with go to pixel astute order by utilizing bolster vector machine (SVM) which is arrangement likelihood maps for a hyper unearthly picture. Probabilities of hyper phantom Pixel have a place with various classes. The second approach is getting pixel shrewd likelihood maps are upgraded broadened arbitrary walker calculation. Pixel astute measurements data by SVM classifier, spatial relationship between neighboring pixels displayed through weight of diagram edges preparation and test tests demonstrated irregular walkers. These 3 components utilizing for the class of validating pixel are resolved. So, these three elements considered in ERW. The proposed technique demonstrates great order performs for three generally utilized genuine hyper otherworldly informational collections even the quantity of preparing tests is moderately little.

     

     


  • Keywords


    Extended random walkers; hyper spectral images; optimization; spectral-spatial classification; k-means.

  • References


      [1] A.Vlla,J, A.Benediktsson, J.Chanussot, and C.JUTTEN, Hyper spectral image classification with independent component discriminative analysis.IEEE Trans.Geosci.Remote sens, vol .49.no. 12 ,pp 4865-4876 dec.2011.

      [2] B.Demir and S. erturk Empiricial mode decomposition of hyper spectral images for support vector machine.IEEE trans geosci remote sens vol 48 no.11 pp4071-4084,nov 2010

      [3] SK Hasane Ahammad and Rajesh Image Processing Based Segmentation Techniques For Spinal Cord In MRI, Indian Journal Of Public Health Research & Development, June 2018, Vol. 9, No. 6

      [4] M.Pedergnana p.Marpu. m.mura J.A Benediktsson and L.BRUZZONE Anovel tech. for optimal fearure selection in attribute profile based on genetic algorithms IEEEtrans Geosci remote sens vol.51.no 6 pp 3514-3528 jun 2013.


 

View

Download

Article ID: 17630
 
DOI: 10.14419/ijet.v7i3.12.17630




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.