Abstract: An optical character recognition screen editing process is performed efficiently and only when necessary. The process is ordered so that editing is performed in increasing order of work intensity. That is, less "expensive" (i.e., less time consuming) correction methods are performed first, as a filter for more "expensive" correction methods. In the preferred embodiment, individual character are corrected first, information fields are corrected second, and entire forms are correction last. Preferably, the individual characters may be collected from a number of forms before being displayed for correction.

Abstract: A character recognition system includes a character input device, such as a stylus and tablet or optical scanner, for receiving inputted characters, and a processor. The processor determines which of a number of model characters best matches the inputted character. To that end, the processor compares each inputted character to each of a plurality of classes into which the model characters are organized. Specifically, the processor extracts a feature value vector from the inputted character, and compares it to the mean feature value vector of each class. The processor recognizes the inputted character as the model character corresponding to the mean feature value vector which is closest to the feature value vector of the inputted character. The processor also constructs the database from multiple specimens of each model character. The processor organizes the specimens of each model character into multiple classes. The processor then determines the mean feature value vector of each class.