# US 2020/0356769 A1 · Image processing apparatus, image processing method, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0356769 A1
- Document ID: US20200356769A1
- Status: Published application
- Kind: A1
- Application number: 16/864,421
- Filed: 2020-05-01
- Published: 2020-11-12
- Earliest claimed: 2019-05-09
- Assignees: Canon Kabushiki Kaisha
- Applicants: Canon Kabushiki Kaisha
- Inventors: Natsuki Kato
- Web page: https://patentgrep.com/patent/US20200356769A1

## CPC

- G06V 30/413: Classification of content, e.g. text, photographs or tables
- H04N 1/00127: {Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture}
- G06F 3/1256: {User feedback, e.g. print preview, test print, proofing, pre-flight checks}
- G06V 30/416: Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
- H04N 1/00204: {with a digital computer or a digital computer system, e.g. an internet server (programmed control between transmitter and receiver or between image input and image output device H04N1/32561)}
- H04N 1/0035: {User-machine interface; Control console (input or output arrangements for computers G06F3/00)}
- H04N 1/00355: {Mark-sheet input (sensing record carriers G06K7/00; character recognition G06V30/10; document-oriented image-based pattern recognition G06V30/40)}
- H04N 1/00366: {Marks in boxes or the like, e.g. crosses or blacking out (H04N1/0036 takes precedence)}
- H04N 1/00374: {on the same page as at least a part of the image}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A technique in the present disclosure makes it possible to accurately obtain a value selected by a user with respect to a selection-type item for which a legend is prepared in a situation where a value entered in a document is extracted from a scanned image of the document. An item name is extracted from a document image, input information input by a user is extracted from the document image, and a legend is extracted from the document image. Additionally, in a case where the input information is unsuitable as a value corresponding to the item name, the value corresponding to the item name is obtained based on the legend and the input information.

## Claims

### Claim 1

An image processing apparatus comprising:
at least one memory that stores a program; and
at least one processor that executes the program to perform:
extracting an item name from a document image;
extracting input information input by a user from the document image;
extracting a legend from the document image; and
obtaining, in a case where the input information is unsuitable as a value corresponding to the item name, the value corresponding to the item name based on the legend and the input information.

### Claim 2 (depends on 1)

The image processing apparatus according to claim 1, wherein
the legend is extracted in a case where the input information is unsuitable as the value corresponding to the item name.

### Claim 3 (depends on 1)

The image processing apparatus according to claim 1, wherein
the legend is information in which selection candidates of the value corresponding to the item name and identifiers allocated to the respective selection candidates are listed alongside, and
in the selection candidates of the value corresponding to the item name, a selection candidate corresponding to an identifier that matches the input information is obtained as the value corresponding to the item name.

### Claim 4 (depends on 3)

The image processing apparatus according to claim 3, wherein
in a case where the selection candidate corresponding to the identifier that matches the input information is unsuitable as the value corresponding to the item name, the input information is employed as the value corresponding to the item name without any change.

### Claim 5 (depends on 1)

The image processing apparatus according to claim 1, wherein
the legend is extracted by searching at least any of an area including the item name, an area including the input information, and surrounding areas around the area including the input information.

### Claim 6 (depends on 5)

The image processing apparatus according to claim 5, wherein
the surrounding areas around the area including the input information are areas next to the area including the input information in a horizontal direction or a vertical direction.

### Claim 7 (depends on 5)

The image processing apparatus according to claim 5, wherein
the legend is extracted by making sequential searches in accordance with priority preset for each of the area including the item name, the area including the input information, and the surrounding areas.

### Claim 8 (depends on 5)

The image processing apparatus according to claim 5, wherein
in a case where the legend cannot be extracted, the input information is obtained as the value corresponding to the item name without any change.

### Claim 9 (depends on 1)

The image processing apparatus according to claim 1, wherein
in a case where the input information corresponds to the item name, the input information is obtained as the value corresponding to the item name without any change.

### Claim 10 (depends on 1)

The image processing apparatus according to claim 1, wherein
the document image is a scanned image obtained by scanning a business form.

### Claim 11

An image processing method performed by an image processing apparatus, the method comprising:
extracting an item name from a document image;
extracting input information input by a user from the document image;
extracting a legend from the document image; and
obtaining, in a case where the input information is unsuitable as a value corresponding to the item name, the value corresponding to the item name based on the legend and the input information.

### Claim 12

A non-transitory computer readable storage medium storing a program for causing a processor to perform:
extracting an item name from a document image;
extracting input information input by a user from the document image;
extracting a legend from the document image; and
obtaining, in a case where the input information is unsuitable as a value corresponding to the item name, the value corresponding to the item name based on the legend and the input information.
