Currently, image Segmentation is one of the important tasks in the scope of image processing. It has essential applications in a number of fields such as medical applications, satellite images and others. Satellite image segmentation is considered as a significant step in the process of detection of geometrical forms belonging to various land covers which has been used in many applications. In this work, three techniques have been used successively to detect the interesting regions in Landsat 7 imagery. First, the histogram is used to detect the range of each peak in input images, then this range is used as the threshold to generate the mask in an active contour algorithm. Finally, edge detectors are implemented to create the final template belong to each detected region. The results are compared with traditional edge detection methods which present the effective of the proposed approach.
Volume 11 | 02-Special Issue
Pages: 494-505