Noise Removal from Land Cover Maps by Post Processing of Classification Reslts

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.