KR-102961253-B1 - Method for displaying result of document recognition and apparatus using the same

KR102961253B1KR 102961253 B1KR102961253 B1KR 102961253B1KR-102961253-B1

Abstract

The present invention relates to a method for displaying document recognition results and a document recognition device using the same. A method for displaying document recognition results according to one embodiment of the present invention may include: a step of extracting text from an input document image and generating key-value pairs by matching a plurality of key values and value values included in the text; a step of extracting key-value pairs corresponding to the output item from the document image based on a set output item; and a step of generating a first image by adding an emphasis object to an area corresponding to the extracted key-value pairs within the document image and displaying the first image.

Inventors

송효섭
조성호
권영준

Assignees

삼성에스디에스 주식회사

Dates

Publication Date: 20260508
Application Date: 20211029

Claims (13)

A method for displaying character recognition results performed by a computing device, A step of extracting text from an input document image and generating key-value pairs by matching multiple key values and value values included in the text; A step of extracting key-value pairs corresponding to the output items from the document image based on the set output items; and A method for displaying a document recognition result comprising the step of generating a first image by adding a highlight object to an area corresponding to the extracted key-value pair within the document image, and displaying the first image.
In paragraph 1, the displaying step A method for displaying document recognition results characterized by generating a table representing key values and value values included in key-value pairs corresponding to the above output items, and further including and displaying the table.
In paragraph 2, the displaying step A method for displaying document recognition results, characterized by accumulating key values and value values corresponding to key-value pairs extracted from each document image in the table when the above-mentioned input document image is added.
In claim 1, the step of extracting the key-value pair is A method for displaying a document recognition result characterized by searching for a key-value pair having a key value corresponding to the output item among the key-value pairs above, and extracting the key-value pair.
In paragraph 4, the step of extracting the key-value pairs is A method for displaying document recognition results characterized by searching for a key value corresponding to the output item using a pre-configured similar mapping DB, and extracting a key-value pair corresponding to the output item using the searched key value.
In paragraph 1, A method for displaying a document recognition result, characterized by further including the step of receiving input from a user to add or delete the output item and setting the output item.
In paragraph 6, the step of setting the above output item A method for displaying document recognition results, characterized by further including an item display area comprising a list of the above-mentioned output items and a selection object that adds or deletes output items within the list according to user input.
In paragraph 2, A method for displaying document recognition results, characterized by further including the step of generating and providing the above table in at least one file format among JSON, XML, Excel, and PDF.
In paragraph 1, A step of displaying a thumbnail display area that displays thumbnail images of each input document image; and A method for displaying a document recognition result, characterized by including the step of displaying a document image corresponding to the selected thumbnail image within the selected image area when any one thumbnail image within the thumbnail display area is selected.
A computer program stored on a medium to perform a method of displaying a document recognition result of any one of claims 1 to 9 in combination with hardware.
processor; and It includes memory coupled to the above processor, The above memory includes one or more modules configured to be executed by the processor, and The above one or more modules are, Text is extracted from an input document image, and multiple key values and value values included in the text are matched to generate key-value pairs, Based on the set output items, key-value pairs corresponding to the output items are extracted from the document image, and A first image is generated by adding a highlight object to an area corresponding to the extracted key-value pair within the document image, and the first image is displayed. A document recognition device including commands.
In claim 11, in extracting the above key-value pairs A document recognition device characterized by searching for a key-value pair having a key value corresponding to the output item among the key-value pairs above, and extracting the key-value pair.
In Clause 12, in extracting the above key-value pairs, A document recognition device characterized by searching for a key value corresponding to the output item using a pre-configured similar mapping DB, and extracting a key-value pair corresponding to the output item using the searched key value.

Description

Method for displaying result of document recognition and apparatus using the same The present invention relates to a method for displaying a document recognition result capable of efficiently providing text extracted from a document image to a user, and a document recognition device utilizing the same. Optical Character Recognition (OCR) technology is designed to recognize characters present in input documents and derive digitized results. Once character recognition is performed on a document image, it is possible to search for specific keywords contained within the image, thereby enabling the easy extraction of necessary information from image-based documents. However, a problem existed in the past where the technology merely provided a function to find specific keywords within the document image, and specific UI elements for utilizing the recognized document images were not implemented. FIG. 1 is a block diagram showing a document recognition device according to one embodiment of the present invention. FIG. 2 is an exemplary diagram showing a document image according to one embodiment of the present invention. FIGS. 3 to 7 are exemplary diagrams illustrating a method of providing a basic provided item of a document recognition device as an output item according to an embodiment of the present invention. FIGS. 8 and 9 are exemplary diagrams illustrating a method for providing additional output items in addition to the basic items provided by a document recognition device according to an embodiment of the present invention. FIG. 10 is an exemplary diagram showing the initial page of a document recognition device according to one embodiment of the present invention. FIG. 11 is a flowchart illustrating a method for displaying document recognition results according to an embodiment of the present invention. FIG. 12 is a diagram showing an exemplary hardware configuration of a computing device in which methods according to various embodiments of the present invention can be implemented. Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings. The objects, specific advantages, and novel features of the present invention will become more apparent from the following detailed description and preferred embodiments in conjunction with the accompanying drawings. Prior to this, the terms and words used in this specification and claims are appropriately defined by the inventor to best describe his invention and should be interpreted in a meaning and concept consistent with the technical spirit of the invention; they are intended merely to describe embodiments and should not be interpreted as limiting the invention. In assigning reference numerals to components, identical or similar components are assigned the same reference numeral regardless of the reference numeral, and redundant descriptions thereof are omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably for the sake of ease of drafting the specification; they do not inherently possess distinct meanings or roles and may refer to software or hardware components. In describing the components of the present invention, when a component is expressed in a singular form, it should be understood that the component also includes a plural form unless specifically stated otherwise. Furthermore, terms such as "first," "second," etc., are used to distinguish one component from another, and the components are not limited by said terms. Additionally, if one component is connected to another component, it implies that yet another component may be connected between the components. In addition, when describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art may obscure the essence of the embodiments disclosed in this specification, such detailed description is omitted. Furthermore, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that the drawings include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the invention. FIG. 1 is a block diagram showing a document recognition device according to one embodiment of the present invention. Referring to FIG. 1, a document recognition device (100) according to one embodiment of the present invention may include a text extraction unit (110), a key-value pair generation unit (120), an operation unit (130), and a display unit (140). A document recognition device according to an embodiment of the present invention will be described below with reference to FIG. 1. The text extraction unit (110) can extract text by performing character recognition on the received document image (I). That is,