Character recognition apparatus, character recognition method, and character recognition program

Abstract

To provide a capital letter recognizing device, a capital letter recognizing method and a capital letter recognizing program for generating an electronic document where types and handwritten characters coexist. The image of an original where types and handwritten characters coexist is generated by an image inputting part 11, and the image is divided into a type section constituted of the types and a handwritten section constituted of the handwritten characters by a type section / handwritten section separation processing part 12. Those sections are OCR-processed by a type section OCR processing part 13 and a handwritten section OCR processing part 18, and the result of the type OCR is registered in a registration dictionary 17. When there are a plurality of the recognition candidates of the handwritten section by the handwritten section OCR processing part 18, and any type is matched with the type OCR result in the neighborhood, the OCR processing of the handwritten section is carried out by using the type, and the result is composed with the type OCR by the OCR result composition processing part 21.

Description

technical field [0001] The present invention relates to a character recognition device, a character recognition method and a character recognition program for manuscripts, in particular to a character recognition device, a character recognition method and a character recognition program capable of digitizing documents mixed with printed and handwritten characters. Background technique [0002] In recent years, the circulation of electronic documents such as e-mails has been increasing, but on the other hand, there are also a large number of documents output in the form of paper. One of the reasons is that it is easy to realize supplementary writing using handwriting on paper. [0003] For printed characters that output electronic information such as text symbols on paper, digitalized electronic information can be returned with a high probability by using Optical Character Reader (OCR: Optical Character Reader) software. However, in the prior art, if the text information des...

AI Technical Summary

Problems solved by technology

[0009] However, if a known character recognition device is used, in the case of Patent Document 1, typeface recognition and handwriting recognition are processed separately, and processing such as making the typeface data reflect the handwriting recognition process is not performed, so it is used for handwriting Recognition restrictions have increased, and handwriting input can only be used in specific cases such as mail, bills, and application forms.

[0010] Moreover, if patent document 2 is used, the mark on the sheet of paper and printed / handwritten characters are read, so that the applicable originals are limited, and handwriting recognition of general documents that do not contain marks cannot be performed.

Moreover, the load of registering and reading sheets is heavy, making flexible format changes difficult

In addition, due to strict conditions such as cell designation and only numbers, it is difficult to obtain a practical recognition rate for general files, and it is difficult to use for online / offline information conversion

Images