Cross correlation based clustering for feature selection in hyperspectral imagery

Cukur, Huseyin; Binol, Hamidullah; Uslu, Faruk Sukru; Kalayci, Yusuf; Bal, Abdullah

doi:10.1109/eleco.2015.7394552

Cited by 3 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The measure criteria may vary in registration methods. In this scope, the most common measure criterias are defined as cross correlation [2], phase correlation, mutual information and sum of squared difference. The interpolation method used in the registration takes an important place, since it creates new pixels and these pixels change the amount of translation.…”

Section: Sub Pixel Registrationmentioning

confidence: 99%

“…In equation 4, the function is positive in the interval [0, 1] and negative in the interval [1,2] for a negative constant . With the negative constant , the function becomes a form of windowed sinc function that provides high frequency performance [7].…”

Section: Cubic Splinementioning

confidence: 99%

“…By choosing , the second derivatives of two cubic polynomials, (one is defined on the interval [0,1], and the second one is defined on the interval [1,2]) is equal to each other at point 1 [9].…”

Section: Cubic Splinementioning

confidence: 99%

See 2 more Smart Citations

Reconstruction of Super Resolution Images With Correlation Based Sub-Pixel Registration

2016

IJCCIE

View full text Add to dashboard Cite

The accuracy of super resolution application depends on the performance of registration, interpolation and restoration steps. In this stage, the rate of sub-pixel accuracy, which processed in registration step, holds an important place for providing the success of super resolution application. In this paper, correlation based subpixel registration methods are handled and how these methods influence over the accuracy of the super resolution application is explored. In this scope, registrations achieved by correlation measure criteria combined with Bilinear, New Edge Directed Interpolation (NEDI) and Cubic Spline methods one by one and these registration results are utilized in super resolution application. Experimental results show that, using correlation combined with Cubic Spline interpolation obtain higher performance than correlation combined with other interpolation methods in a super resolution application.

show abstract

Section: Sub Pixel Registrationmentioning

confidence: 99%

Section: Cubic Splinementioning

confidence: 99%

See 1 more Smart Citation

Reconstruction of Super Resolution Images With Correlation Based Sub-Pixel Registration

2016

IJCCIE

View full text Add to dashboard Cite

show abstract

“…High dimensional feature spaces typically contain feature redundancy (Cukur et al 2015;Tolosi & Lengauer 2011;Yu & Liu 2004). Although feature correlation and redundancy are related, they are not strictly the same thing (Brown et al 2012;Guyon & Elisseeff 2003).…”

Section: Introductionmentioning

confidence: 99%

“…The raw bands of multi-spectral imagery often have significant spectral overlap and consequently are correlated with one another. This spectral overlap will exacerbate the redundancy amongst features derived from these raw bands (Cukur et al 2015). Hyperspectral imagery is also wellknown for containing redundancy amongst the bands (Yuan, Zhu & Wang 2015).…”

Section: Introductionmentioning

confidence: 99%

Regional mapping of spekboom canopy cover using very high resolution aerial imagery

Harris

Vlok

Niekerk

2018

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

My sincere thanks to my supervisor, Adriaan van Niekerk, for his valuable technical input and guidance and for all the patient encouragement. Jan Vlok was instrumental in this research, and he is gratefully acknowledged for his vision, support and remarkable field expertise. Special thanks to Julie Verhulp, Raoul Duesimi and Aslam Parker of Chief Directorate: National Geospatial Information, for their generous provision of aerial imagery and related support. The Centre for Geographical Analysis, especially Garth Stephenson, Theo Pauw and Jascha Muller, graciously assisted with data, computing and software resources. Ilze Boonzaaier beautified some of the maps and Helene van Niekerk assisted with editing. Camera calibration software was kindly provided by Adrian Roos of Intergraph SA. Bernhard Jacobs of GeoSpace International assisted with valuable calibration discussions and data. Andrew Knipe, of the Gamtoos Irrigation Board, helped with funding administration. Finally, to Mireille van Reenen, for your moral support and great companythank you.

show abstract

Feature clustering and ranking for selecting stable features from high dimensional remotely sensed data

Harris

Niekerk

2018

International Journal of Remote Sensing

View full text Add to dashboard Cite

Cross correlation based clustering for feature selection in hyperspectral imagery

Cited by 3 publications

References 9 publications

Reconstruction of Super Resolution Images With Correlation Based Sub-Pixel Registration

Reconstruction of Super Resolution Images With Correlation Based Sub-Pixel Registration

Regional mapping of spekboom canopy cover using very high resolution aerial imagery

Feature clustering and ranking for selecting stable features from high dimensional remotely sensed data

Contact Info

Product

Resources

About