Skip to Main Content
A complete document analysis system involves multiple techniques and indifferent processing steps. Even a character recognition or word recognition module (subsystem) needs techniques combining a few algorithms. To exemplify how the techniques are practically used and how they are performing, some concrete examples of using multiple techniques to build practical recognition systems are presented, and experimental results on real image data are showed. In the paper, evolutionary generation of pattern recognizers will be discussed and a co evolution algorithm in the image recognition system will be researched. This result shows that competitive co evolution and camouflage are expected to aid in the problem of over fitting and reliability without expert tuning, and also in the generation of a larger and more diverse data set.