Segmentation of satellite images using Self-Organizing Maps 249 x Segmentation of satellite images using Self-Organizing Maps Mohamad Awad National Council for Scientific Research-Center for Remote Sensing Lebanon 1. Introduction Remote sensing plays a key role in many domains devoted to observation of the Earth, such as land cover/use, agriculture monitoring, military battles, oceanography…etc. There are many types of acquisition systems which have different spatial, spectral, and temporal characteristics. Some of them are passive, such as Landsat, Spot, Ikonos, Quickbird, Orbview…etc. Others are active such as SAR (Space Airborne Radar). These systems have opened the field of applications since early 1970. Image segmentation is the process of image division into regions with similar attributes (Pratt, 1991). It is an important step in image analysis chain with applications to pattern recognition, object detection, etc. Until recently, most of the segmentation methods and approaches are supervised such as Maximum A Posteriori (MAP) (Lopes et al., 1990) or Maximum Likelihood (ML) (Benediktson et al., 1990) with an average efficiency rate of about 85% (Perkins et al., 2000), (Zhang et al., 2003). In the supervised methods a priori knowledge is needed to get a successful segmentation process and sometime the required information may not be available. In addition, there are unsupervised methods which require many parameters and they are sensitive to noise such as Iterative Self-Organizing Map Data (ISODATA) (Tou & Gonzalez, 1974), and SEM (Mason & Pieczynski, 1993). In order to overcome the deficiencies found in many previously listed methods, Kohonen’s Self-Organizing Maps (SOM) (Kohenen, 2001) is used to segment different satellites images. SOM is an unsupervised non-parametric Artificial Neural Network (ANN) method. The main characteristic of SOM is the ability to convert patterns of arbitrary dimensionality into the responses of two dimensional arrays of neurons. Another important characteristic of the SOM is that the feature map preserves neighborhood relations of the input pattern. Although the use of SOM in image segmentation is well reported in the literature, such as segmentation of printed fabric images (Xu & lin, 2002), or in sonar images (Yao et al.,2000), their application in satellite image segmentation is not widely known. One can cite the work of (Aria et al., 2004) which was used in the segmentation of Indian Remote Sensing “IRS” satellite image. The cooperative segmentation approach between K-means and SOM (Zhou et al., 2007) is a recent work where the role of K-means is to segment the image in the coarser scale, and then SOM will re-segment the image in the fine scale. In This method K- 15 www.intechopen.com