Volume 3, Issue 1, May 2013, Pages 112–115
E. Menaka1, S. Suresh Kumar2, and M. Bharathi3
1 Department of Information Technology, Vivekanandha College of Engineering for Women, Namakkal, TamilNadu, India
2 Vivekanandha College of Technology for Women, Namakkal, TamilNadu, India
3 Department of Information Technology, Vivekanandha College of Engineering for Women, Namakkal, TamilNadu, India
Original language: English
Copyright © 2013 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Cloud is the major obstacle to analyze data in the satellite images. The various approaches are used to remove the cloud from the satellite image for further processing. The approaches are in-painting and multi-temporal. But, the algorithm working for these approaches cannot produce the accurate results. So, that the accuracy assessment helps to motivate the increased accuracy result. The main aim of this paper is to analyze the accuracy of in-paint and multi-temporal approach and produce the pros and cons of those approaches. Accuracy assessment helps to obtain degree of truthfulness of the results. There are 'n' numbers of metrics are available to find the accuracy of the result such as analyzing variance, spatial error, probabilistic error etc. In this paper, two approaches are implemented and the results are applied to the segmentation algorithm. Then, the segmentation results are analyzed by using the error matrix. The error matrix have constructed based on the difference between the clusters of the image result. For segmentation the K-Means algorithm is used and for simplicity only two clusters are segmented. Segmentation result will clearly show that the accuracy of the in-paint and multi-temporal approaches. From the result it is evident that the multi-temporal approach produces a better result when compared to the in-painting. Especially, in that multi-temporal the Averaging method produces better accuracy result.
Author Keywords: Cloud Detection, Cloud Reconstruction, Segmentation, K-Means, Accuracy Assessment.
E. Menaka1, S. Suresh Kumar2, and M. Bharathi3
1 Department of Information Technology, Vivekanandha College of Engineering for Women, Namakkal, TamilNadu, India
2 Vivekanandha College of Technology for Women, Namakkal, TamilNadu, India
3 Department of Information Technology, Vivekanandha College of Engineering for Women, Namakkal, TamilNadu, India
Original language: English
Copyright © 2013 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Cloud is the major obstacle to analyze data in the satellite images. The various approaches are used to remove the cloud from the satellite image for further processing. The approaches are in-painting and multi-temporal. But, the algorithm working for these approaches cannot produce the accurate results. So, that the accuracy assessment helps to motivate the increased accuracy result. The main aim of this paper is to analyze the accuracy of in-paint and multi-temporal approach and produce the pros and cons of those approaches. Accuracy assessment helps to obtain degree of truthfulness of the results. There are 'n' numbers of metrics are available to find the accuracy of the result such as analyzing variance, spatial error, probabilistic error etc. In this paper, two approaches are implemented and the results are applied to the segmentation algorithm. Then, the segmentation results are analyzed by using the error matrix. The error matrix have constructed based on the difference between the clusters of the image result. For segmentation the K-Means algorithm is used and for simplicity only two clusters are segmented. Segmentation result will clearly show that the accuracy of the in-paint and multi-temporal approaches. From the result it is evident that the multi-temporal approach produces a better result when compared to the in-painting. Especially, in that multi-temporal the Averaging method produces better accuracy result.
Author Keywords: Cloud Detection, Cloud Reconstruction, Segmentation, K-Means, Accuracy Assessment.
How to Cite this Article
E. Menaka, S. Suresh Kumar, and M. Bharathi, “Accuracy Assessment of Cloud Reconstruction Approaches Using Segmentation,” International Journal of Innovation and Applied Studies, vol. 3, no. 1, pp. 112–115, May 2013.
