Translation of japanese printed documents into english language with touching character problems

摘要

The project deals with the character segmentation method for Japanese printed documents. Since character segmentation is a kind of a search problem, avoiding “combinatorial explosion” is essential in realizing practical systems. Segmentation is very complicated especially when characters touch each other. This method gives a multi-stage algorithm, where earlier stages treat more reliable segmentation than later stages and later stages utilize information obtained from the results of earlier stages. Segmentation hypotheses are generated in each stage on the basis of the results of earlier stages, and they are verified by character recognition results. Following invention is described in detail with the help of figure 1 of sheet 1 showsSeparable and Compound Japanese Charactersand figure 2 of sheet 1 shows Flowchart.