# US 10,872,229 B2 · Image processing device, image processing method, and recording medium

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

- Number: US 10,872,229 B2
- Document ID: US10872229B2
- Status: Granted
- Kind: B2
- Application number: 16/159,292
- Filed: 2018-10-12
- Published: 2019-04-18
- Granted: 2020-12-22
- Earliest claimed: 2017-10-12
- Assignees: Casio Computer Co., Ltd.
- Applicants: Casio Computer Co., Ltd.
- Inventors: Kyosuke Sasaki; Takao Nakai; Daiki Yamazaki; Takeharu Takeuchi
- Web page: https://patentgrep.com/patent/US10872229B2

## CPC

- G06V 40/162: {using pixel segmentation or colour matching}
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 7/11: Region-based segmentation
- G06V 40/169: {Holistic features and representations, i.e. based on the facial image taken as a whole}
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06T 2207/10024: Color image
- G06T 2207/30201: Face
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An image processing device includes an acquirer which acquires a face image and a controller. The controller generates an image depicted by at least one of multiple kinds of parameter making up a color space on a basis of the face image acquired by the acquirer, detects a particular image region in the generated image by setting multiple sizes, and sets the detected image region as a region on which a designated processing is to be performed.

## Claims

### Claim 1

An image processing device comprising:
an acquirer which acquires a face image; and
a controller, wherein the controller:
generates an image depicted by at least one of multiple kinds of parameter making up a color space based on the face image acquired by the acquirer,
detects a particular image region in relation to surrounding pixels in the face image by setting multiple sizes of the particular image region each of which is smaller than a size of the face image based on the generated image, and
sets the detected particular image region as a region on which a designated processing is to be performed.

### Claim 2 (depends on 1)

The image processing device according to claim 1, wherein:
the multiple kinds of parameter define a specific direction of a color difference component, and
the controller sets the detected particular image region as the region on which the designated processing is to be performed based on a size of the particular image region and an edge detection result of the image of a particular direction of the color difference component.

### Claim 3 (depends on 1)

The image processing device according to claim 1, wherein the particular image region is a local region of melasma in the face image.

### Claim 4 (depends on 1)

The image processing device according to claim 1, wherein:
the multiple kinds of parameter are a luminance component, and
the controller sets the particular image region as the region on which the designated processing is to be performed based on a size of the detected particular image region and an edge detection result of the luminance component.

### Claim 5 (depends on 1)

The image processing device according to claim 1, wherein the particular image region is a region in which a mole exists in the face image.

### Claim 6 (depends on 1)

The image processing device according to claim 1, wherein the controller sets multiple kinds of size of the particular image region to be detected using ring filters in multiple sizes provided in advance, to detect the particular image region in relation to the surrounding pixels in the face image.

### Claim 7

An image processing device comprising:
an acquirer which acquires a face image; and
a controller, wherein the controller:
generates an image depicted by at least one of multiple kinds of parameter making up a color space based on the face image acquired by the acquirer,
detects a particular image region in relation to surrounding pixels in the face image based on the generated image,
determines a size of the detected particular image region, and
sets the detected image region as a region on which a designated processing is to be performed based on the determined size of the detected particular image region.

### Claim 8

An image processing method comprising:
acquiring a face image;
generating an image depicted by at least one of multiple kinds of parameter making up a color space based on the acquired face image;
detecting a particular image region in relation to surrounding pixels in the face image by setting multiple sizes of the particular image region each of which is smaller than a size of the face image based on the generated image; and
setting the particular image region detected in the detecting as a region on which a designated processing is to be performed.

### Claim 9

An image processing method comprising:
acquiring a face image;
generating an image depicted by at least one of multiple kinds of parameter making up a color space based on the acquired face image;
detecting a particular image region in relation to surrounding pixels in the face image based on the generated image;
determining a size of the detected particular image region; and
setting the particular image region detected in the detecting as a region on which a designated processing is to be performed based on the determined size of the particular image region.

### Claim 10

A non-transitory computer readable recording medium storing a program which causes a computer to:
acquire a face image;
generate an image depicted by at least one of multiple kinds of parameter making up a color space based on the acquired face image;
detect a particular image region in relation to surrounding pixels in the face image by setting multiple sizes of the particular image region each of which is smaller than a size of the face image based on the generated image; and
set the particular image region detected in the detecting as a region on which a designated processing is to be performed.

### Claim 11

A non-transitory computer readable recording medium storing a program which causes a computer to:
acquire a face image;
generate an image depicted by at least one of multiple kinds of parameter making up a color space based on the acquired face image;
detect a particular image region in relation to surrounding pixels in the face image based on the generated image;
determine a size of the detected particular image region; and
set the particular image region detected in the detecting as a region on which a designated processing is to be performed based on the determined size of the particular image region.