# US 2019/0244334 A1 · Face image processing system, face image processing method, and face image processing program

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

- Number: US 2019/0244334 A1
- Document ID: US20190244334A1
- Status: Published application
- Kind: A1
- Application number: 16/314,210
- Filed: 2017-06-23
- Published: 2019-08-08
- Earliest claimed: 2016-06-30
- Assignees: Meiji University; Kose Corporation
- Applicants: Meiji University; Kose Corporation
- Inventors: Kaoru ARAKAWA; Fumihiko TSUKIYAMA
- Web page: https://patentgrep.com/patent/US20190244334A1

## CPC

- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 1/00: General purpose image data processing
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/00: Image analysis
- G06T 7/50: Depth or shape recovery
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 7/90: Determination of colour characteristics
- G06T 11/10: Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77)
- G06T 11/60: Creating or editing images; Combining images with text
- G06V 40/16: Human faces, e.g. facial parts, sketches or expressions
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/20024: Filtering details
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30088: Skin; Dermal
- G06T 2207/30201: Face
- G06V 40/178: {estimating age from face image; using age information for improving recognition}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A face image processing system includes: a component extracting means which receives an input of face image information indicating a face image, and extracts a wrinkle component, a fleck component and a pore component of the face image from the face image information; a removal rate adjusting means which adjusts a removal rate of each of the wrinkle component, the fleck component and the pore component extracted by the component extracting means; a storage means which stores the removal rate; a synthesizing means which synthesizes the wrinkle component, the fleck component and the pore component which are amplified or attenuated at the removal rate adjusted by the removal rate adjusting means, and generates a face image; and an output means which outputs the face image information synthesized by the synthesizing means.

## Claims

### Claim at position 1

1-10. (canceled)

### Claim 11

A face image processing system comprising:
a component extracting means which receives an input of face image information indicating a face image, and extracts a wrinkle component, a fleck component and a pore component of the face image from the face image information;
a removal rate adjusting means which adjusts a removal rate of each of the wrinkle component, the fleck component and the pore component extracted by the component extracting means;
a storage means which stores the removal rate;
a synthesizing means which synthesizes the wrinkle component, the fleck component and the pore component which are amplified or attenuated at the removal rate adjusted by the removal rate adjusting means, and generates a face image; and
an output means which outputs the face image information synthesized by the synthesizing means.

### Claim 12 (depends on 11)

The face image processing system according to claim 11, further comprising a face region extracting means which extracts the face image indicating a face region from which at least one of an eye region, a nose region and a mouth region of an input face image included in inputted image information has been removed.

### Claim 13 (depends on 11)

The face image processing system according to claim 11, wherein the component extracting means includes
a filter means which divides the face image information indicating the inputted face image into a first component, a second component, a third component, a fourth component and a fifth component in an amplitude-frequency space, and extracts the fourth component, and
a component recognizing means which recognizes the wrinkle component, the fleck component and the pore component in the face image based on the fourth component extracted by the filter means, and distinguishes an appearance position and a shape of each component in the face image.

### Claim 14 (depends on 12)

The face image processing system according to claim 12, wherein the component extracting means includes
a filter means which divides the face image information indicating the inputted face image into a first component, a second component, a third component, a fourth component and a fifth component in an amplitude-frequency space, and extracts the fourth component, and
a component recognizing means which recognizes the wrinkle component, the fleck component and the pore component in the face image based on the fourth component extracted by the filter means, and distinguishes an appearance position and a shape of each component in the face image.

### Claim 15 (depends on 13)

The face image processing system according to claim 13, wherein the removal rate adjusting means adjusts the removal rate of each of the components in the face image by weighting the wrinkle component, the fleck component and the pore component.

### Claim 16 (depends on 14)

The face image processing system according to claim 14, wherein the removal rate adjusting means adjusts the removal rate of each of the components in the face image by weighting the wrinkle component, the fleck component and the pore component.

### Claim 17 (depends on 13)

The face image processing system according to claim 13, wherein the synthesizing means synthesizes the fourth component corresponding to the wrinkle component, the fleck component and the pore component based on the removal rate stored in the storage means, and the first component, the second component, the third component and the fifth component divided by the filter means or the inputted face image information.

### Claim 18 (depends on 14)

The face image processing system according to claim 14, wherein the synthesizing means synthesizes the fourth component corresponding to the wrinkle component, the fleck component and the pore component based on the removal rate stored in the storage means, and the first component, the second component, the third component and the fifth component divided by the filter means or the inputted face image information.

### Claim 19 (depends on 11)

The face image processing system according to claim 11, further comprising:
a face color processing means at a subsequent stage of the synthesizing means, the face color processing means including
a skin color extracting means which extracts a skin color region of which at least one of a luminance and color information of the face image information is in a predetermined range, and
a shade adjusting means which changes a shade of a skin color in the skin color region extracted by the skin color extracting means.

### Claim 20 (depends on 12)

The face image processing system according to claim 12, further comprising:
a face color processing means at a subsequent stage of the synthesizing means, the face color processing means including
a skin color extracting means which extracts a skin color region of which at least one of a luminance and color information of the face image information is in a predetermined range, and
a shade adjusting means which changes a shade of a skin color in the skin color region extracted by the skin color extracting means.

### Claim 21 (depends on 13)

The face image processing system according to claim 13, further comprising:
a face color processing means at a subsequent stage of the synthesizing means, the face color processing means including
a skin color extracting means which extracts a skin color region of which at least one of a luminance and color information of the face image information is in a predetermined range, and
a shade adjusting means which changes a shade of a skin color in the skin color region extracted by the skin color extracting means.

### Claim 22 (depends on 14)

The face image processing system according to claim 14, further comprising:
a face color processing means at a subsequent stage of the synthesizing means, the face color processing means including
a skin color extracting means which extracts a skin color region of which at least one of a luminance and color information of the face image information is in a predetermined range, and
a shade adjusting means which changes a shade of a skin color in the skin color region extracted by the skin color extracting means.

### Claim 23 (depends on 19)

The face image processing system according to claim 19, wherein
a plurality of the face image information outputted from the output means is generated,
the output means displays a plurality of candidate face images based on the plurality of generated face image information, on a display screen of a display means,
the face image processing system further comprises
an input means which accepts one of a selection instruction of a desired candidate face image designated by a user and a determination instruction of a final candidate face image from the plurality of displayed candidate face images, and
a computing means which, when the input means accepts the selection instruction of the candidate face image, sets a parameter of each processing of the component extracting means, the removal rate adjusting means and the face color processing means based on the face image information indicating the selected candidate face image by interactive evolutionary computation by performing crossover processing and mutation processing based on a genetic algorithm, and
the component extracting means, the removal rate adjusting means and the face color processing means repeatedly generate the face image information based on the parameter set by the computing means until the input means accepts the determination instruction of the candidate face image.

### Claim 24 (depends on 20)

The face image processing system according to claim 20, wherein
a plurality of the face image information outputted from the output means is generated,
the output means displays a plurality of candidate face images based on the plurality of generated face image information, on a display screen of a display means,
the face image processing system further comprises
an input means which accepts one of a selection instruction of a desired candidate face image designated by a user and a determination instruction of a final candidate face image from the plurality of displayed candidate face images, and
a computing means which, when the input means accepts the selection instruction of the candidate face image, sets a parameter of each processing of the component extracting means, the removal rate adjusting means and the face color processing means based on the face image information indicating the selected candidate face image by interactive evolutionary computation by performing crossover processing and mutation processing based on a genetic algorithm, and
the component extracting means, the removal rate adjusting means and the face color processing means repeatedly generate the face image information based on the parameter set by the computing means until the input means accepts the determination instruction of the candidate face image.

### Claim 25 (depends on 21)

The face image processing system according to claim 21, wherein
a plurality of the face image information outputted from the output means is generated,
the output means displays a plurality of candidate face images based on the plurality of generated face image information, on a display screen of a display means,
the face image processing system further comprises
an input means which accepts one of a selection instruction of a desired candidate face image designated by a user and a determination instruction of a final candidate face image from the plurality of displayed candidate face images, and
a computing means which, when the input means accepts the selection instruction of the candidate face image, sets a parameter of each processing of the component extracting means, the removal rate adjusting means and the face color processing means based on the face image information indicating the selected candidate face image by interactive evolutionary computation by performing crossover processing and mutation processing based on a genetic algorithm, and
the component extracting means, the removal rate adjusting means and the face color processing means repeatedly generate the face image information based on the parameter set by the computing means until the input means accepts the determination instruction of the candidate face image.

### Claim 26 (depends on 22)

The face image processing system according to claim 22, wherein
a plurality of the face image information outputted from the output means is generated,
the output means displays a plurality of candidate face images based on the plurality of generated face image information, on a display screen of a display means,
the face image processing system further comprises
an input means which accepts one of a selection instruction of a desired candidate face image designated by a user and a determination instruction of a final candidate face image from the plurality of displayed candidate face images, and
a computing means which, when the input means accepts the selection instruction of the candidate face image, sets a parameter of each processing of the component extracting means, the removal rate adjusting means and the face color processing means based on the face image information indicating the selected candidate face image by interactive evolutionary computation by performing crossover processing and mutation processing based on a genetic algorithm, and
the component extracting means, the removal rate adjusting means and the face color processing means repeatedly generate the face image information based on the parameter set by the computing means until the input means accepts the determination instruction of the candidate face image.

### Claim 27 (depends on 23)

The face image processing system according to claim 23, wherein, when the input means accepts the determination instruction of the candidate face image, the storage means stores as a reference parameter the parameter for generating the face image information indicating a determined candidate face image.

### Claim 28 (depends on 24)

The face image processing system according to claim 24, wherein, when the input means accepts the determination instruction of the candidate face image, the storage means stores as a reference parameter the parameter for generating the face image information indicating a determined candidate face image.

### Claim 29 (depends on 25)

The face image processing system according to claim 25, wherein, when the input means accepts the determination instruction of the candidate face image, the storage means stores as a reference parameter the parameter for generating the face image information indicating a determined candidate face image.

### Claim 30

A face image processing method of a face image processing system comprising: a component extracting means; a removal rate adjusting means; a storage means; a synthesizing means; and an output means, the face image processing method comprising:
extracting a wrinkle component, a fleck component and a pore component of a face image from face image information indicating an inputted face image by the component extracting means;
adjusting a removal rate of each of the extracted wrinkle component, fleck component and pore component by the removal rate adjusting means;
storing the removal rate by the storage means;
synthesizing the wrinkle component, the fleck component and the pore component which are amplified or attenuated at the removal rate adjusted in the step of adjusting the removal rate, and generating the face image by the synthesizing means; and
outputting the synthesized face image information by the output means.
