DEVELOPMENT OF AN EXPERT SYSTEM USING IMAGE DATABASE FOR DIAGNOSING PLANT PROTECTION

A diagnostic expert system shell based on production rules and frames with color image database was developed and applied to lawn diseases, pests and physiological disorders diagnosis as a case study. The expert system shell was made up a 32 bits multimedia desktop microcomputer. The knowledge base had 264 frames, 206 production rules and 926 synonym words as the result of interview and arrangement. It was desired that 78.8 % of total frames used the visual color image data to explain the meaning of observations and conclusions. Visual color image display with the phrases of questions and answers from the expert system helped the user to understand diagnosis turf diseases and pests. The expert system can be also applied to diagnosis of the other plant protection with changing the knowledge base easily.