Title :
Noise Removal from Land Cover Maps by Post Processing of Classification Reslts
Author :
Hosseini, M. ; Saradjian, M.R. ; Javahery, A. ; Nadi, S.
Author_Institution :
Univ. of Tehran, Tehran
Abstract :
Classification of satellite images with the intend of land cover mapping is the main concern in this study. Many algorithms are available for classification of satellite images, Minimum distance classification method is a simple and quick method that does not include covariance information. Maximum likelihood classification method is widely used in many remote sensing applications and can be regard as one of the most reliable techniques. Neural network classification is based on training during a training phase, and the proper classification. In this paper we studying the usefulness of these methods for the purpose of land cover mapping and we use a post classification method has been used to detect the pixels that are wrongly classified and reappointed to correct class. The experimental results show that the proposed approach can produce a more accurate classification results.
Keywords :
geophysical signal processing; image classification; image denoising; maximum likelihood estimation; neural nets; terrain mapping; classification results processing; covariance information; land cover maps; maximum likelihood classification; minimum distance classification; neural network classification; noise removal; remote sensing application; satellite images classification; Data mining; Filters; Image analysis; Image classification; Image sensors; Maximum likelihood detection; Neural networks; Pixel; Remote monitoring; Satellites; Confusion matrix; Image classification; Maximum likelihood; Neural network;
Conference_Titel :
Recent Advances in Space Technologies, 2007. RAST '07. 3rd International Conference on
Conference_Location :
Istanbul
Print_ISBN :
1-4244-1057-6
Electronic_ISBN :
1-4244-1057-6
DOI :
10.1109/RAST.2007.4284002