In this paper a new pattern or feature abstraction algorithm was developed simulating our human eyes scan on situation leapingly and focus its attention only to limited space, in order to make a physiognomic analysis of the remote sensing images of the earth's surface, in the end to acquire a description like that in where the foothill, the forest, the desert or the alluvial pie slice was, and so on. At first a size-changeable and edge-fuzzy window was designed to get many samples of the earth's surface through sliding around the image, all these samples served for the learning of a Support Vector Machine model, which was designed to make pattern's classifications. This process was repeated in different area, with different sampling size, to different pattern and lasting different times. Once some distinct local patterns were found and mastered, a self-organizing of comparability assembling will happen based on the similarity of some types of local patterns to form a holistic description or understanding of the remote sensing image. Our aim was to compartmentalize the image by physiognomic features. At the end of this paper the results of classification experiment and application of this method to some actual visible light images were presented. This method was suitable to extend to other pattern recognition problems with texture property.