Image processing and interactive selection with Java based on genetic algorithms

Knowledge acquisition systems for image enhancement procedures have been de veloped using Java. Based on genetic algorithms (GAs), the systems can opti mize procedures for enhancing target components in the digital images of pl ants in fields. Using rough objective images given by users as a standard i mage for evaluating fitness, it can provide appropriate filtering operation s and their parameters. To improve convergence, interactive selection, whic h selects a promising individual by human intention instead of the fitness function, has been introduced. Consequently, the combination of the fitness function and interactive selection has contributed to rapid convergence of the processing. Copyright (C) 1998 IFAC.