Landscape should be analyzed in segments for understanding its texture, structure, function and changes. These segments are used to evaluate landscape structure and function analysis. In this context, the most important segments which form the landscape are the landscape patches. Analysis and understanding of the landscape structure and ecological progress needs the measurement of the landscape patches and evaluation .Therefore, the neighborhood ratio between the patches should be known. In this study, we propose an automated method, which is based on Python language, to compute this ratio with consideration of neighborhood degrees between the patches. The test site is Mugla-Koycegiz town from Turkey, where there is a huge amount population of Liquidambar orientalis trees, and the town is important for shoreline tourism. Urban area, water surface, agricultural areas, marsh, and forest classes are defined. Sentinel 2A multispectral satellite image is used and Random Forest classification method is applied. The derived patches are produced from the classification, and then converted to the vector form. Each vector boundaries were converted to the point features with 10 m intervals. The ratio of number of points which is neighbor to the specific class to the all points along the boundary is computed automatically with developed script. Three different patches are analyzed, and the results are reported.