# US 2018/0025214 A1 · Face recognition method

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

- Number: US 2018/0025214 A1
- Document ID: US20180025214A1
- Status: Published application
- Kind: A1
- Application number: 15/469,671
- Filed: 2017-03-27
- Published: 2018-01-25
- Earliest claimed: 2016-07-25
- Assignees: Hon Hai Precision Industry Co., Ltd.
- Applicants: Hon Hai Precision Industry Co., Ltd.
- Inventors: TIEN-PING LIU; I-HAO CHUNG; KUEI-KANG WU; HORNG-JUING LEE
- Web page: https://patentgrep.com/patent/US20180025214A1

## CPC

- G06F 16/5854: {using shape and object relationship}
- G06F 16/51: Indexing; Data structures therefor; Storage structures
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching}
- G06V 40/165: {using facial parts and geometric relationships}
- G06V 40/172: {Classification, e.g. identification}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The disclosure relates to a face recognition method. The face recognition method includes: providing a face recognition system, the face recognition system includes a database module, a camera module, and a feature point compare module, wherein the database module stores a plurality of data-photos of a plurality of users; turning on the face recognition system to a searching motion, and searching person faces by the camera module to get a target person face of a target person; and, turning on the face recognition system to a recognition motion to judge whether the target person is one user.

## Claims

### Claim 1

A face recognition method comprising:
S1: providing a face recognition system, the face recognition system includes a database module, a camera module, and a feature point compare module, wherein the database module stores a plurality of data-photos of a plurality of users;
S2: turning on the face recognition system to a searching motion, and searching person faces by the camera module to get a target person face of a target person;
S3: turning on the face recognition system to a recognition motion to judge whether the target person is one user, which comprises steps of:
S31: judging a location of the target face, if the location of the target face complies with a standard of the camera module, taking a scene-photo of the target person by the camera module;
S32: comparing the scene-photo with the plurality of data-photos of the plurality of users stored in the database module; and
S33: evaluating the scene-photo to judge whether the scene-photo is the same as one data-photo of the plurality of users, if the scene-photo is the same as one data-photo of the plurality of users, the target person is one user; if the scene-photo is not the same as one data-photo of the plurality of users, reminding the target person to change location and taking second scene-photo of the target person, and comparing the second scene-photo with data of users stored in the database module;
S34: considering the target person is one user if the second scene-photo is the same as one data-photo of the plurality of users, and storing the second scene-photo in the camera module; considering the target person is a stranger if the second scene-photo is not the same as one data-photo of the plurality of users.

### Claim 2 (depends on 1)

The method of claim 1, wherein in step S1, each of the plurality of user has at least one data-photo, each of the plurality of data-photos has a group of data-camera parameters and a group of data-feather parameters.

### Claim 3 (depends on 2)

The method of claim 2, wherein the group of data-camera parameters comprises white balance, ISO, diaphragm, shutter, color temperature, pixel, brightness, contrast ratio, time and light.

### Claim 4 (depends on 2)

The method of claim 2, wherein the group of data-feather parameters comprises area of person face, distance between eyes, size of eye, distance between eye and mouth.

### Claim 5 (depends on 1)

The method of claim 1, wherein the scene-photo comprises a group of scene-camera parameters and a group of scene-feather parameters, the group of scene-camera parameters comprises parameters of the camera module taking a scene-photo, the group of scene-feather parameters is feather sizes of the scene-photos.

### Claim 6 (depends on 5)

The method of claim 5, wherein the group of scene-feather parameters comprises white balance, ISO, diaphragm, shutter, color temperature, pixel, brightness, contrast ratio, time and light.

### Claim 7 (depends on 5)

The method of claim 5, wherein the group of scene-feather parameters comprises an area of person face, a distance between eyes, a size of eye, a distance between eye, mouth, and a size of mouth.

### Claim 8 (depends on 1)

The method of claim 1, wherein the feature point compare module is configured to compare the scene-photo of the target person with the plurality of data-photos of the plurality of users to judge whether the target person is one user.

### Claim 9 (depends on 1)

The method of claim 1, wherein in step S32, each of the plurality of data-photos has a group of data-camera parameters and a group of data-feather parameters, the scene-photo comprises a group of scene-camera parameters and a group of scene-feather parameters, the step of comparing the scene-photo with the plurality of data-photos of the plurality of users stored in the database module comprises:
Sa: comparing the group of scene-camera parameters of the scene-photo with the group of data-camera parameters of each data-photos to calculate x groups of data-camera parameters of x data-photos that are most similar to the group of data-camera parameters, wherein x is the quantity of groups of data-camera parameters and the quantity of data-photos, x≧1; and
Sb: comparing the x groups of data-feather parameters of the x data-photos with the group of scene-feather parameters of the scene-photo to evaluate the scene-photo.

### Claim 10 (depends on 9)

The method of claim 9, wherein in the step Sa, the group scene-camera parameters and the data-camera parameters have L same values and K similar values, the K similar values are K values different from each other, and the differences is less than 5%.

### Claim 11 (depends on 9)

The method of claim 9, wherein in the step Sa, the calculate step comprises: calculate L, the greater the L, the more similar the group scene-camera parameters and the data-camera parameters.

### Claim 12 (depends on 9)

The method of claim 9, wherein in the step Sa, the calculate step comprises: calculate K, the greater the K, the more similar the group scene-camera parameters and the data-camera parameters.

### Claim 13 (depends on 9)

The method of claim 9, wherein in the step Sa, the calculate step comprises: comparing L and K, if L is greater than K, the greater the L, the more similar the group scene-camera parameters and the data-camera parameters; if K is greater than L, the greater the K, the more similar the group scene-camera parameters and the data-camera parameters.

### Claim 14 (depends on 9)

The method of claim 9, wherein in the step Sa, the calculate step comprises: calculating a sum of K and L, the greater the sum of K and L, the more similar the group scene-camera parameters and the data-camera parameters.

### Claim 15 (depends on 9)

The method of claim 9, wherein the step of evaluating the scene-photo is operated by scoring the scene-photo, if a difference of the scene-feather parameter and the data-feather parameter is less than 1% or 2%, the scene-feather parameter and the data-feather parameter is regarded as the same with each other.

### Claim 16 (depends on 15)

The method of claim 15, wherein the scene-photo has y scene-feather parameters the same as data-feather parameters of one data-photo, the greater of y, the higher score the scene-photo has.