Fusion of Gabor filter and morphological operators for the detection of settlement zones in Google Earth satellite images

Research on the segmentation and detection of settlement zones in satellite images has attained immense attention in recent years. Design advancements in imaging sensor technology have made it possible to capture high resolution images of earth but unfortunately these very high quality images are very expensive, especially for researchers. For this reason, our research focus is on Google Earth images which are available free of cost for everyone. In this paper we present a novel approach of extracting settlement zones from Google Earth images of different resolutions. The method involves the use of Gabor filter for the extraction of high frequency orientation features followed by the application of different morphological operators and performing a heuristic based connected component analysis of the resulting images. The method has been tested on the images of different regions of Pakistan having a lot of variability in the looks of a settlement zone. The initial experimental results are promising.