# US 2017/0286753 A1 · Method for identifying age based on facial feature

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

- Number: US 2017/0286753 A1
- Document ID: US20170286753A1
- Status: Published application
- Kind: A1
- Application number: 15/149,172
- Filed: 2016-05-08
- Published: 2017-10-05
- Earliest claimed: 2016-04-01
- Assignees: Hon Hai Precision Industry Co., Ltd.
- Applicants: Hon Hai Precision Industry Co., Ltd.
- Inventors: LING-CHIEH TAI
- Web page: https://patentgrep.com/patent/US20170286753A1

## CPC

- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/165: {using facial parts and geometric relationships}
- G06V 40/172: {Classification, e.g. identification}
- G06V 40/178: {estimating age from face image; using age information for improving recognition}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for identify age based on facial features, includes: getting a face image and capturing a face area from the face image; setting a plurality of facial feature points on the face area; defining a plurality of age feature areas on the face area based on coordinates of the plurality of feature points; acquiring age feature from the plurality of age feature area to get an age value; and comparing the age value with at least one threshold value.

## Claims

### Claim 1

A method for identify age based on facial features, comprising:
getting a face image and capturing a face area from the face image;
setting a plurality of facial feature points on the face area;
defining a plurality of age feature areas on the face area based on coordinates of the plurality of feature points;
acquiring age feature from the plurality of age feature area to get an age value; and
comparing the age value with at least one threshold value.

### Claim 2 (depends on 1)

The method of claim 1, wherein the plurality of facial feature points mark eyebrow, eye, nose, and mouth of the face image.

### Claim 3 (depends on 2)

The method of claim 2, wherein there are seventeen feature points to mark a left eyebrow tail, a left eyebrow head, a right eyebrow head, a right eyebrow tail, an outer canthus of a left eye, a middle portion of the left eye, an inner canthrus of the left eye, an inner canthrus of a right eye, a middle portion of the right eye, an outer canthurs of the right eye, a left nosewing, a tip of the nose, a right nosewing, a left corner of the mouth, a middle portion of a upper lip of the mouth, a right corner of the mouth, and a middle portion of a lower lip of the mouth.

### Claim 4 (depends on 3)

The method of claim 3, wherein before defining the plurality of age feature areas on the face area based on coordinates of the plurality of feature points, a distance between the left eye and the right eye and a distance between the tip of the nose and a middle portion of the two eyes are calculated.

### Claim 5 (depends on 4)

The method of claim 4, wherein the plurality of age feature areas includes a left eye tail area, a right eye tail area, a left eye nether area, a right eye nether area, a left smile folds area and a right smile fold area.

### Claim 6 (depends on 5)

The method of claim 5, wherein before acquiring age feature from the plurality of age feature area, same type age feature areas are adjusted into a same size.

### Claim 7 (depends on 6)

The method of claim 6, wherein the left and right eye tail areas are same type age feature areas, the left and right eye nether areas are same type age feature areas, and the left and right smile folds areas are same type age feature areas.

### Claim 8 (depends on 6)

The method of claim 6, wherein the face area is processed into a processed image by Modified Census Transform method before acquiring age feature from the plurality of age feature area.

### Claim 9 (depends on 1)

The method of claim 1, wherein the at least one threshold value comprises a first threshold value and a second threshold value, and the age value is compared to the second threshold value when the age value is not smaller than the first threshold value.

### Claim 10

A method for identify age based on facial features, comprising:
getting a face image and capturing a face area from the face image;
setting a plurality of facial feature points on the face area;
defining a plurality of age feature areas on the face area based on coordinates of the plurality of feature points;
acquiring age feature from the plurality of age feature area to get an age value;
comparing the age value with a first threshold value and a second threshold value, and defining belong to youth when the age value is smaller than the first threshold value, defining belong to middle age when the age value is not smaller than the first threshold value and smaller than the second threshold value, defining belong to the old when the age value is not smaller than the second threshold value.

### Claim 11 (depends on 10)

The method of claim 10, wherein the plurality of facial feature points mark eyebrow, eye, nose, and mouth of the face image.

### Claim 12 (depends on 11)

The method of claim 11, wherein there are seventeen feature points to mark a left eyebrow tail, a left eyebrow head, a right eyebrow head, a right eyebrow tail, an outer canthus of a left eye, a middle portion of the left eye, an inner canthrus of the left eye, an inner canthrus of a right eye, a middle portion of the right eye, an outer canthurs of the right eye, a left nosewing, a tip of the nose, a right nosewing, a left corner of the mouth, a middle portion of a upper lip of the mouth, a right corner of the mouth, and a middle portion of a lower lip of the mouth.

### Claim 13 (depends on 12)

The method of claim 12, wherein before defining the plurality of age feature areas on the face area based on coordinates of the plurality of feature points, a distance between the left eye and the right eye and a distance between the tip of the nose and a middle portion of the two eyes are calculated.

### Claim 14 (depends on 13)

The method of claim 13, wherein the plurality of age feature areas includes a left eye tail area, a right eye tail area, a left eye nether area, a right eye nether area, a left smile folds area and a right smile fold area.

### Claim 15 (depends on 14)

The method of claim 14, wherein before acquiring age feature from the plurality of age feature area, same type age feature areas are adjusted into a same size.

### Claim 16 (depends on 15)

The method of claim 15, wherein the left and right eye tail areas are same type age feature areas, the left and right eye nether areas are same type age feature areas, and the left and right smile folds areas are same type age feature areas.

### Claim 17 (depends on 15)

The method of claim 15, wherein the face area is processed into a processed image by Modified Census Transform method before acquiring age feature from the plurality of age feature area.
