JP2018085093A5

JP2018085093A5 -

Info

Publication number: JP2018085093A5
Application number: JP2017147464A
Authority: JP
Filing date: 2017-07-31
Publication date: 2020-08-20
Anticipated expiration: 2037-07-31

Description

そこで、本発明の目的は、文書の中で文字列が認識された複数の領域の妥当性を確認することができる仕組みを提供することを目的とする。
Therefore, an object of the present invention is to provide a mechanism capable of confirming the validity of a plurality of areas in which a character string is recognized in a document .

本発明は、文書の中の文字列を取得する情報処理装置であって、文書の中の複数の領域から文字列が認識された認識結果を取得する取得手段と、前記認識結果を取得した複数の領域の関連性と、前記取得した認識結果とにより、前記文字列が認識された複数の領域の妥当性を決定する決定手段とを備えることを特徴とする。
The present invention is an information processing apparatus for acquiring a character string in a document, comprising: an acquisition unit for acquiring a recognition result in which the character string is recognized from a plurality of areas in the document; And a determination unit that determines the validity of the plurality of regions in which the character string is recognized, based on the relationship between the regions and the acquired recognition result .

本発明によれば、文書の中で文字列が認識された複数の領域の妥当性を確認することができる。
According to the present invention, it is possible to confirm the validity of a plurality of areas in which a character string is recognized in a document .

Claims

An information processing device for acquiring a character string in a document,
An acquisition means for acquiring a recognition result in which a character string is recognized from a plurality of areas in a document,
Information processing , comprising: a determining unit that determines the validity of the plurality of regions in which the character string is recognized, based on the relationship between the plurality of regions that have acquired the recognition result and the obtained recognition result. apparatus.

The information processing apparatus according to claim 1, further comprising a display control unit that distinguishably displays an area in which a character string in the document is recognized based on the determined validity .

The information processing apparatus according to claim 1 or 2, wherein the determining unit determines, in a plurality of related areas that have acquired the recognition result, whether the plurality of areas are valid according to the acquired recognition result. ..

A storage means for storing the format of a character string recognized from each of the plurality of areas;
The information processing apparatus according to claim 1, wherein the acquisition unit acquires a recognition result of whether or not a character string according to the format is recognized.

The information processing apparatus according to any one of claims 1 to 4, further comprising: a receiving unit that receives a designation of a region where a character string is recognized from a region in the document .

The information processing apparatus according to any one of claims 1 to 5 , wherein the plurality of areas are areas of columns or rows of a table.

7. The information processing apparatus according to claim 1 , wherein the plurality of areas are areas within a certain range of vertical arrangement or horizontal arrangement.

A method of controlling an information processing device for acquiring a character string in a document, comprising:
An acquisition step in which the acquisition means acquires a recognition result in which a character string is recognized from a plurality of areas in a document;
The determining means includes a determining step of determining the validity of the plurality of regions in which the character string is recognized, based on the relevance of the plurality of regions in which the recognition result is acquired and the acquired recognition result. And a method for controlling the information processing apparatus.

A program for causing an information processing device to function as the unit according to claim 1.