A SELF-TUNING VISION SYSTEM FOR MONITORING BIOTECHNOLOGICAL PROCESSES.1. APPLICATION TO PRODUCTION OF PULLULAN BY AUREOBASIDIUM-PULLULANS

A prototype of a self-tuning vision system (STVS) has been developed t o monitor cell population in fermentations. The STVS combines classica l image processing techniques, neural networks and fuzzy logic technol ogies By combining these technologies the STVS is able to analyze samp led images of the culture. The proposed system can be ''tailored'' wit h minimum effort by an expert who can ''teach'' the system to recogniz e cells by showing examples of different morphologies. After adaptatio n, the STVS is able to capture images, isolate the different cells, cl assify them according to the expert's criteria, and provide the profil e of the cell's population. The system was applied to the classificati on and analysis of Aureobasidium pullulans. The importance of understa nding the changes of population distribution during the fermentation a nd its effect in the production of pullulan are emphasized. The STVS c an be used for monitoring and control of the cell population in small research fermentors or in large-scale production. (C) 1996 John Wiley & Sons, Inc.