An Efficient Spectral Spatial Classification for Hyper Spectral Images
DOI:
https://doi.org/10.14419/ijet.v7i3.12.17630Published:
2018-07-20Keywords:
Extended random walkers, hyper spectral images, optimization, spectral-spatial classification, k-means.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.
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.
How to Cite
License
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution Licensethat allows others to share the work with an acknowledgement of the work''s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal''s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Accepted 2018-08-16
Published 2018-07-20