Feature Extraction Techniques in Remote Sensing Images: A survey on Algorithms, Parameterization and Performance
Edmore Chikohora1, Obeten O. Ekabua2
1Edmore Chikohora, Department of Computer Science North-West University, Mafikeng Campus Private Bag X2046, Mmabatho, South Africa.
2Obeten O. Ekabua, Department of Computer Science North-West University, Mafikeng Campus Private Bag X2046, Mmabatho, South Africa.
Manuscript received on March 03, 2014. | Revised Manuscript received on March 05, 2014. | Manuscript published on March 05, 2014. | PP: 140-144 | Volume-4 Issue-1, March 2014. | Retrieval Number: A2118034114/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Remote Sensing Images (RSI) employs various Feature Extraction Techniques (FET) that implement different algorithms to extract features from a query image. In this paper, we provide a critical and comprehensive survey on algorithms implemented by different FET, their parameter selection strategies and performance. The survey is divided into three parts where initially three FET are selected and the algorithms they implement are analysed. Secondly, their parameter selection strategies are surveyed and finally a critical analysis on performance based on literature results obtained is provided with some concluding remarks.
Keywords: Remote Sensing, Feature Extraction, Convolution Mask, Mahalanobis Distance, Gaussian Envelope, Frequency Harmonic.