Character identifying method, program and recording media

Abstract

The present invention provides a character recognition method and recording medium for recognizing characters entered in a document or the like including preprint information. An object of the invention is to recognize characters in contact with or superposed on the preprint information without using any knowledge of the preprint information or a difference in gray level. An image in an area where the characters to be recognized are present is divided into line segments individually, wherein the image is obtained by reading the preprint information and the entry characters. A recognition image is created by changing a combination of the plurality of line segments divided. A recognition result with the reliability is memorized by making the character recognition for the created recognition image. And the recognition result having a greatest reliability is output by executing the character recognition for all the combinations while changing the combination of line segments successively.

Description

technical field [0001] The present invention relates to a character recognition method, program and recording medium. [0002] In recent years, character recognition technology has been widely used to input characters written or printed on paper into computers. In order to indicate input positions of characters on paper such as documents, leading characters or ruler lines (hereinafter referred to as preprinted information) are printed on the front side of the paper, allowing characters to be input near the guide characters or rule lines in most cases. [0003] In such cases, due to the presence of preprinted information, it becomes difficult to correctly recognize the input characters. Hence the need for improvement. Background technique [0004] Fig. 28 shows an example of characters written on preprinted information. As shown in the figure, in this example, the preprints represent units of ten million, million, hundred thousand, ten thousand, thousand, hundred, ten, and...

AI Technical Summary

Problems solved by technology

[0006] With the conventional methods described above, the method of deleting preprinted information has the problem that character recognition cannot be performed correctly without knowledge about the preprinted information

Meanwhile, even if preprinted information can be extracted using another method, extraction errors may occur in some cases, or, when a ruler line or preprinted information remains in recognized characters, the character recognition result may be wrong

[0007] In addition, when the document cannot be obtained as a grayscale image due to system limitations, or there is little difference in grayscale between the preprinted information and the recognized characters, there is a problem that the recognized characters cannot be extracted based on the grayscale information

Images