# US 2021/0342390 A1 · Image search system, image search method, and program

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

- Number: US 2021/0342390 A1
- Document ID: US20210342390A1
- Status: Published application
- Kind: A1
- Application number: 17/273,068
- Filed: 2019-09-05
- Published: 2021-11-04
- Earliest claimed: 2018-09-05
- Assignees: NEC Corporation
- Applicants: NEC Corporation
- Inventors: Shoji NISHIMURA; Tingting DONG
- Web page: https://patentgrep.com/patent/US20210342390A1

## CPC

- G06F 16/583: using metadata automatically derived from the content
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 16/532: Query formulation, e.g. graphical querying
- G06F 16/538: Presentation of query results
- G06F 16/5838: {using colour}
- G06T 1/00: General purpose image data processing
- G06T 7/90: Determination of colour characteristics
- G06V 10/56: relating to colour
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An image search system (1) is provided with: a search key information acquisition unit (110) that acquires color specifying information indicating a plurality of colors and reference information indicating a reference of proportions of the plurality of colors being occupied in an image area; a specified color proportion information acquisition unit (120) that acquires specified color proportion information indicating proportions of the plurality of colors associated with the color specifying information, being occupied in an image to be processed; and an image search unit (130) that identifies whether the image to be processed is a search target image, based on the specified color proportion information and the reference information.

## Claims

### Claim 1

An image search system, comprising:
a search key information acquisition unit that acquires color specifying information indicating a plurality of colors and reference information indicating a reference of proportions of the plurality of colors being occupied in an image area;
a specified color proportion information acquisition unit that acquires specified color proportion information indicating proportions of the plurality of colors associated with the color specifying information, being occupied in an image to be processed; and
an image search unit that identifies whether the image to be processed is a search target image, based on the specified color proportion information and the reference information.

### Claim 2 (depends on 1)

The image search system according to claim 1, further comprising
a storage unit that stores color histogram information indicating a frequency distribution of a color included in the image to be processed, wherein
the specified color proportion information acquisition unit acquires the specified color proportion information by using the color specifying information and the color histogram information.

### Claim 3 (depends on 1)

The image search system according to claim 1, wherein
the image to be processed is a partial image acquired by cutting an area of a search target object within an original image into a predetermined shape.

### Claim 4 (depends on 1)

The image search system according to claim 1, further comprising
a color correction unit that corrects the plurality of colors associated with the color specifying information by using preset information.

### Claim 5 (depends on 4)

The image search system according to claim 4, wherein
the color correction unit changes the preset information according to a generation condition of the image to be processed.

### Claim 6 (depends on 1)

The image search system according to claim 1, wherein
the search key information acquisition unit acquires a plurality of sets of the color specifying information and the reference information,
the specified color proportion information acquisition unit acquires the specified color proportion information for each of the plurality of sets by using the color specifying information of the each set, and
the image search unit identifies the search target image by using the specified color proportion information for the each set and the reference information for the each set.

### Claim 7 (depends on 1)

The image search system according to claim 1, wherein
the search key information acquisition unit acquires the color specifying information and the reference information for each predefined partial area of an image,
the specified color proportion information acquisition unit acquires the specified color proportion information for the each partial area by using the color specifying information for the each partial area, and
the image search unit identifies the search target image by using the specified color proportion information for the each partial area and the reference information for the each partial area.

### Claim 8 (depends on 1)

The image search system according to claim 1, wherein
the search key information acquisition unit acquires the color specifying information, based on selection input on a color pallet or a color plane being displayed as a user interface.

### Claim 9

An image search method executed by a computer, the method comprising:
acquiring color specifying information indicating a plurality of colors and reference information indicating a reference of proportions of the plurality of colors being occupied in an image area;
acquiring specified color proportion information indicating proportions of the plurality of colors associated with the color specifying information, being occupied in an image to be processed; and
identifying whether the image to be processed is a search target image, based on the specified color proportion information and the reference information.

### Claim 10 (depends on 9)

The image search method executed by the computer according to claim 9, the method further comprising:
storing color histogram information indicating a frequency distribution of a color included in the image to be processed; and
acquiring the specified color proportion information by using the color specifying information and the color histogram information.

### Claim 11 (depends on 9)

The image search method according to claim 9, the method further comprising
the image to be processed being a partial image acquired by cutting an area of a search target object within an original image into a predetermined shape.

### Claim 12 (depends on 9)

The image search method executed by the computer according to claim 9, the method further comprising,
correcting the plurality of colors associated with the color specifying information by using preset information.

### Claim 13 (depends on 12)

The image search method executed by the computer according to claim 12, the method further comprising,
changing the preset information according to a generation condition of the image to be processed.

### Claim 14 (depends on 9)

The image search method executed by the computer according to claim 9, the method further comprising:
acquiring a plurality of sets of the color specifying information and the reference information;
acquiring the specified color proportion information for each of the plurality of sets by using the color specifying information of the each set; and
identifying the search target image by using the specified color proportion information for the each set and the reference information for the each set.

### Claim 15 (depends on 9)

The image search method executed by the computer according to claim 9, the method further comprising:
acquiring the color specifying information and the reference information for each predefined partial area of an image;
acquiring the specified color proportion information for the each partial area by using the color specifying information for the each partial area; and
identifying the search target image by using the specified color proportion information for the each partial area and the reference information for the each partial area.

### Claim 16 (depends on 9)

The image search method executed by the computer according to claim 9, the method further comprising,
acquiring the color specifying information, based on selection input on a color pallet or a color plane being displayed as a user interface.

### Claim 17

A non-transitory computer readable medium storing a program causing a computer to execute an image search method, the method comprising:
acquiring color specifying information indicating a plurality of colors and reference information indicating a reference of proportions of the plurality of colors being occupied in an image area;
acquiring specified color proportion information indicating proportions of the plurality of colors associated with the color specifying information, being occupied in an image to be processed; and
identifying whether the image to be processed is a search target image, based on the specified color proportion information and the reference information.
