Classification of Satellite Imagery for Identifying Land-Cover Objects using ECW Compression Images: The Case of Makassar City Area

This paper presents a case study on the effect of lossy compression using Enhanced Compressed Wavelet (ECW) format remote sensing image classification. ECW was chosen because it is widely used as standard for storing aerial and satellite imagery. The conducted high-resolution multispectral Pleiades taken from an area in Makassar, Indonesia. Image classification performed geographic object-based analysis method, where simple linear iterative clustering (SLIC) algorithm implemented segmentation before Six land cover categories were selected to validate results: water bodies, trees, rice fields, shrubs, urban areas. accuracy studied by varying ratio. Then results are compared with original image. Experimental prove that does not have much accuracy. Even Random Forest Gradient Boosting Machine provide higher compressed In addition, can be concluded best classifier highest