In this study, we carried out land cover change detection using satellite remote sensing data. The data came from Landsat-5 TM satellite covering the area of Klang, located in Selangor, Malaysia. Initially, region of interests (ROI) were drawn on each of the land cover classes identified in order to extract the training sets. Landsat bands 1, 2, 3, 4, 5 and 7 were then used as the input for the Support Vector Machine classification. The accuracy of the classifications was then assessed by comparing the classifications with a reference data set using a confusion matrix. The classification results were used to identify the conversion of land cover from year 2000 to 2005, using statistical change detection techniques. The outcomes of change detection analysis are reported in terms of pixel counts, percentages and areas. © 2006-2016 Asian Research Publishing Network (ARPN). All rights reserved.