Generating Expert Systems to Detect Specific Bacteria Types and Extract Handwriting from Banck Checks

Detecting specific types of bacteria in a microscopic Bacteria Colony Image (BCI) is a tedious and timeconsuming task. Based on the previous experience in the field of computerized signature and handwriting analysis, we generated two expert systems to detect specific types of bacteria in BCI and to extract handwriting from binary bank checks images using the same software platform developed for this purpose. Using the Domain Expert Guided Heuristic Search (DEGHS) and the platform, we generated an expert system that succeeded in cases where no algorithmic approach can be applied. We exploited the fact that the function of an expert system is determined mainly by its knowledge base to generate different expert systems by modifying the content of the knowledge base. The mechanism used expedite very much the development of the expert system to reach its best performance.