# US 2019/0057276 A1 · Image analysis apparatus, image analysis method, and non-transitory computer readable medium

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

- Number: US 2019/0057276 A1
- Document ID: US20190057276A1
- Status: Published application
- Kind: A1
- Application number: 15/912,926
- Filed: 2018-03-06
- Published: 2019-02-21
- Earliest claimed: 2017-08-16
- Assignees: Fuji Xerox Co., Ltd.
- Applicants: Fuji Xerox Co., Ltd.
- Inventors: Daisuke Tatsumi
- Web page: https://patentgrep.com/patent/US20190057276A1

## CPC

- G06V 30/1448: {based on markings or identifiers characterising the document or the area}
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- G06V 30/10: Character recognition
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An image analysis apparatus includes an extraction section, an acquisition section, an exclusion section, and a recognition section. The extraction section extracts, from a target image, a text area including a character. The acquisition section acquires a predetermined target-object condition. The predetermined target-object condition defines a target object. The exclusion section searches for the target object in the text area and excludes the target object from a target of character recognition. The text area is extracted by the extraction section. The target object satisfies the predetermined target-object condition. The recognition section performs character recognition on the text area. The text area is an area from which the target object is excluded.

## Claims

### Claim 1

An image analysis apparatus comprising:
an extraction section that extracts, from a target image, a text area including a character;
an acquisition section that acquires a predetermined target-object condition, the predetermined target-object condition defining a target object;
an exclusion section that searches for the target object in the text area and excludes the target object from a target of character recognition, the text area being extracted by the extraction section, the target object satisfying the predetermined target-object condition; and
a recognition section that performs character recognition on the text area, the text area being an area from which the target object is excluded.

### Claim 2 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the exclusion section deletes the searched target object from the text area; and
wherein the recognition section performs character recognition on the text area, the text area being an area from which the target object is deleted by the exclusion section.

### Claim 3 (depends on 2)

The image analysis apparatus according to claim 2,
wherein the acquisition section acquires an arrangement of lines constituting the target object, and
wherein the exclusion section searches for the target object on a basis of the arrangement of the lines constituting the target object, and deletes the lines constituting the searched target object.

### Claim 4 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the exclusion section includes a separation section that determines a target-object area to be a non-text area, and separates the non-text area from the text area, the target-object area corresponding to the target object in the text area, and
wherein the recognition section performs character recognition on the text area, the text area being an area from which the non-text area is separated.

### Claim 5 (depends on 4)

The image analysis apparatus according to claim 4,
wherein the acquisition section acquires an arrangement of lines constituting the target object, and
wherein the separation section searches for the target object by using the arrangement of the lines constituting the target object, determines the target-object area to be the non-text area, and separates the non-text area from the text area, the target-object area corresponding to the target object in the text area.

### Claim 6 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the acquisition section acquires a reference image indicating the target object, and
wherein the exclusion section searches for the target object by using the reference image, and excludes the target object from the target of character recognition.

### Claim 7 (depends on 2)

The image analysis apparatus according to claim 2,
wherein the acquisition section acquires a reference image indicating the target object, and
wherein the exclusion section searches for the target object by using the reference image, and excludes the target object from the target of character recognition.

### Claim 8 (depends on 3)

The image analysis apparatus according to claim 3,
wherein the acquisition section acquires a reference image indicating the target object, and
wherein the exclusion section searches for the target object by using the reference image, and excludes the target object from the target of character recognition.

### Claim 9 (depends on 4)

The image analysis apparatus according to claim 4,
wherein the acquisition section acquires a reference image indicating the target object, and
wherein the exclusion section searches for the target object by using the reference image, and excludes the target object from the target of character recognition.

### Claim 10 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the acquisition section acquires a condition about one of a height, a size, and a position of the target object, and
wherein the exclusion section excludes the target object from the target of character recognition, one of a height, a size, and a position of the target object satisfying the condition about one of the height, the size, and the position of the target object.

### Claim 11 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the acquisition section acquires a condition about one of a height, a size, and a position of the target object, and
wherein the exclusion section excludes the target object from the target of character recognition, the target object being obtained through the searching performed by the exclusion section, one of a height, a size, and a position of the target object satisfying the condition about one of the height, the size, and the position of the target object.

### Claim 12 (depends on 10)

The image analysis apparatus according to claim 10,
wherein the condition about one of the height, the size, and the position of the target object is one of first to third conditions, the first condition indicating that the height of the target object is larger than a height of a character that is the target of character recognition performed by the recognition section, the second condition indicating that the size of the target object is larger than a size of a character that is the target of character recognition performed by the recognition section, and the third condition indicating that a height-direction position of the target object is located between lines of a text in the text area.

### Claim 13 (depends on 11)

The image analysis apparatus according to claim 11,
wherein the condition about one of the height, the size, and the position of the target object is one of first to third conditions, the first condition indicating that the height of the target object is larger than a height of a character that is the target of character recognition performed by the recognition section, the second condition indicating that the size of the target object is larger than a size of a character that is the target of character recognition performed by the recognition section, and the third condition indicating that a height-direction position of the target object is located between lines of a text in the text area.

### Claim 14 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the acquisition section acquires a condition about an arrangement area, as the predetermined target-object condition, the arrangement area being an area in which the target object is arranged in the text area, and
wherein the exclusion section excludes the target object from the target of character recognition, the arrangement area of the target object in the text area satisfying the condition about the arrangement area of the target object in the text area.

### Claim 15 (depends on 1)

The image analysis apparatus according to claim 1,
wherein the acquisition section acquires a search area, the search area being a portion of the text area, and
wherein the exclusion section searches for the target object in the search area, and excludes the target object from the target of character recognition.

### Claim 16 (depends on 15)

The image analysis apparatus according to claim 15,
wherein an area in which the target object is included is a portion of the text area, the portion including an end of the text area.

### Claim 17 (depends on 1)

A non-transitory computer readable medium storing a program causing a computer to function as the sections of the image analysis apparatus according to claim 1.

### Claim 18

An image analysis apparatus comprising:
means for extracting, from a target image, a text area including a character;
means for acquiring a predetermined target-object condition, the predetermined target-object condition defining a target object;
means for searching for the target object in the extracted text area and excluding the target object from a target of character recognition, the target object satisfying the predetermined target-object condition; and
means for performing character recognition on the text area, the text area being an area from which the target object is excluded.
