Segmentation of Remote Sensing Images Using Fuzzy-K-Means Clustering

Ramudu Kama

ISBN 10: 6200007128 / ISBN 13: 9786200007124

Editore: LAP LAMBERT Academic Publishing Apr 2019, 2019

Riguardo questo articolo

Neuware -Due to the difficulties occurred in remote sensing image information, an analysis algorithms growth of a large scale image segmentation haven¿t kept a place with the requirement for the methods which to develop the final accuracy of object detection as well as the recognition. Traditional Level set segmentation methods which are Chan-Vese (CV), IVC 2010, ACM with SBGFRLS, Online Region Based ACM (ORACM) were suffered from more amount of time complexity, as well as low segmentation accuracy due to the large intensity homogeneities and the noise. The robust segmentation of remote sensing images is a tedious task because due to lack of spatial information and pixel intensities are non-homogenous. In this regard region based segmentation is impossible. So this is the reason we consider clustering algorithms in pre-processing to improve the cluster efficiency & overcome the obstacles present in traditional methods. In the proposed method we were having two stages, the first stage, in order to pre-process the image we were utilizing the fuzzy logic and k-means clustering known as Fuzzy-k-Means clustering. Here the clustered segmentation results suffering from boundaries and edge leak.Books on Demand GmbH, Überseering 33, 22297 Hamburg 56 pp. Englisch.

Codice articolo 9786200007124

Dati bibliografici

• Titolo: Segmentation of Remote Sensing Images Using Fuzzy-K-Means Clustering
• Editore: LAP LAMBERT Academic Publishing Apr 2019
• Data di pubblicazione: 2019
• Lingua: Inglese
• ISBN 10: 6200007128
• ISBN 13: 9786200007124
• Rilegatura: Taschenbuch
• Condizione: Neu

Descrizione articolo

Riassunto

Due to the difficulties occurred in remote sensing image information, an analysis algorithms growth of a large scale image segmentation haven’t kept a place with the requirement for the methods which to develop the final accuracy of object detection as well as the recognition. Traditional Level set segmentation methods which are Chan-Vese (CV), IVC 2010, ACM with SBGFRLS, Online Region Based ACM (ORACM) were suffered from more amount of time complexity, as well as low segmentation accuracy due to the large intensity homogeneities and the noise. The robust segmentation of remote sensing images is a tedious task because due to lack of spatial information and pixel intensities are non-homogenous. In this regard region based segmentation is impossible. So this is the reason we consider clustering algorithms in pre-processing to improve the cluster efficiency & overcome the obstacles present in traditional methods. In the proposed method we were having two stages, the first stage, in order to pre-process the image we were utilizing the fuzzy logic and k-means clustering known as Fuzzy-k-Means clustering. Here the clustered segmentation results suffering from boundaries and edge leak.