System for capturing and using expert's knowledge for image processing

摘要: The present invention relates to an apparatus and a method for object detection in image. this includes preprocessor, detector, segmentor, classifier, classifier systems integrator, system output post processor. allows the user identify by using three approaches: (1) segmentation (2) pixel-based (3) grid-cell mesotexture based detector. All of aforementioned approaches use pseudo-English programming language processing detection. This expert's knowledge convert it content retrieval algorithms. can preserve segmented scenes original data perform raster-to-vector conversion which preserves size shape objects. Further, image be converted into geographic information (GIS) layers analyzed standard GIS software such as ARC/Info or ARC/View.