In the first step of the object based image analysis strategy, a multi-resolution segmentation technique is applied on the image content in order to segment it into regions (see Section 4). The multi-resolution segmentation procedure starts with single image objects of one pixel and repeatedly merges a pair of image objects into larger ones. The merging decision is based on the local homogeneity criterion, describing the similarity between adjacent image objects. This homogeneity criterion is defined as a combi- nation of spectral homogeneity and shape homogeneity which is modified by compactness and shape parameters. Moreover, a scale parameter is defined for modifying the size of segmented regions. The procedure stops when there are no more possible merges.