(a) uses digital data as inputs, and thus eliminates front-end manual digitization,(b) uses expert systems to extract features automatically from fused image and map data, and thus eliminates time-consuming and error prone manual object tracing, and(c) vectorizes the extracted objects and converts them into GlS layers automatically, and thus eliminates all the cumbersome intermediate, man-in-the-loop steps of GIS analyses employed by current systems.We achieve such data processing efficiency by first combining Image processing, Multi-sources analysis and GIS into one single system, and second by using pseudo English as a programming language to ignore incompatibility between vector and raster data Accordingly, each GIS processor is an English key word, and a set of key words becomes an expert system that controls the entire GIS processes We will demonstrate these claimed system capabilities and GIS benefits by using empirical test results derived from analyses of scanned topomaps and digital or orthophotoquads in a transportation planning scenarioAnticipated Results/Potential Commercial Applications of Results :We will prove(1) that using raster data as GIS inputs can save GIS project cost up to 50 percent,(2) automated object extraction, attribution and vectorization will enhance GIS use efficiency further Commercial applications are automated GIS layers generation from tax maps, digitized airphotos, digital topomaps and digital orthophotos