# US 2019/0244011 A1 · Low-Power Face Identification Method Capable of Controlling Power Adaptively

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

- Number: US 2019/0244011 A1
- Document ID: US20190244011A1
- Status: Published application
- Kind: A1
- Application number: 15/889,229
- Filed: 2018-02-06
- Published: 2019-08-08
- Earliest claimed: 2018-02-06
- Assignees: Kneron Inc.
- Applicants: Kneron Inc.
- Inventors: Chun-Chen Liu
- Web page: https://patentgrep.com/patent/US20190244011A1

## CPC

- G06V 20/64: Three-dimensional [3D] objects
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 10/145: Illumination specially adapted for pattern recognition, e.g. using gratings
- G06V 10/955: {using specific electronic processors}
- G06V 40/166: {using acquisition arrangements}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A low-power face identification method includes emitting at least one first light signal to an object, receiving at least one second light signal reflected by the object, decoding the at least one second light signal to generate a decoded light signal, extracting two-dimensional image information from the decoded light signal, performing a two-dimensional face detection function by an artificial intelligence chip according to the two-dimensional image information and two-dimensional face training data, inhibiting a two-dimensional face recognition function when a two-dimensional face is undetected, and disabling an image converter by the artificial intelligence chip in order to inhibit a three-dimensional face recognition function when the two-dimensional face recognition function is inhibited.

## Claims

### Claim 1

A low-power face identification system comprising:
a transceiver configured to emit at least one first light signal to an object and receive at least one second light signal reflected by the object;
an artificial intelligence chip coupled to the transceiver;
a decoder coupled to the transceiver and the artificial intelligence chip, and configured to receive the at least one second light signal, decode the at least one second light signal to generate a decoded light signal, and transmit a part of the decoded light signal to the artificial intelligence chip;
an image converter coupled to the decoder and the artificial intelligence chip, and configured to convert a two-dimensional image of the object to a three-dimensional image of the object according to the decoded light signal, and output a three-dimensional face image from the three-dimensional image of the object when a two-dimensional face image is successfully detected and recognized from the two-dimensional image of the object by the artificial intelligence chip;
an encoder coupled to the image converter and configured to encode data of the three-dimensional face image after the three-dimensional face image is generated;
wherein after the part of decoded light signal is received by the artificial intelligence chip, the artificial intelligence chip disables the image converter when the two-dimensional face image is undetected or unrecognized.

### Claim 2 (depends on 1)

The system of claim 1, wherein the two-dimensional face image is recognized as of a user identifier after the two-dimensional face image is detected from the two-dimensional image of the object.

### Claim 3 (depends on 1)

The system of claim 1, wherein the decoded light signal comprises two-dimensional image information and three-dimensional image information of the object, and the part of the decoded light signal comprises the two-dimensional image information of the object.

### Claim 4 (depends on 3)

The system of claim 3, wherein the three-dimensional image information of the object is a bitmap information matrix of the object.

### Claim 5 (depends on 1)

The system of claim 1, wherein the transceiver comprises:
a dual camera light emitting lens configured to emit two first light signals to the object with different angles of incidence; and
a receiver configured to receive two second light signals reflected by the object.

### Claim 6 (depends on 1)

The system of claim 1, wherein the transceiver comprises:
a three-dimensional structured light emitting device configured to emit at least one three-dimensional structured light signal to the object;
a two-dimensional light emitting device configured to emit a two-dimensional light signal to the object; and
a receiver configured to receive a plurality of second light signals reflected by the object.

### Claim 7 (depends on 1)

The system of claim 1, wherein the transceiver comprises a near infrared sensor (NIR sensor) configured to detect an optical signal outside a visible spectrum reflected by the object.

### Claim 8 (depends on 1)

The system of claim 1, further comprising:
a memory coupled to the artificial intelligence chip and configured to save two-dimensional face training data and three-dimensional face training data.

### Claim 9 (depends on 8)

The system of claim 8, wherein the artificial intelligence chip generates a recognition result of the two-dimensional face image by checking a likelihood of the two-dimensional face image detected from the two-dimensional image of the object and two-dimensional face training data stored in the memory.

### Claim 10 (depends on 9)

The system of claim 9, wherein the memory is an electrically-erasable programmable read-only memory (EEPROM).

### Claim 11 (depends on 1)

The system of claim 1, further comprising:
a processor coupled to the artificial intelligence chip and configured to assist the artificial intelligence chip in detecting the two-dimensional face image and recognizing the two-dimensional and three-dimensional face images; and
a buffer coupled to the processor and configured to provide a buffer space for image processing data.

### Claim 12 (depends on 11)

The system of claim 11, wherein the buffer is a flash memory.

### Claim 13 (depends on 1)

The system of claim 1, wherein the artificial intelligence chip uses a first driving power to perform a two-dimensional face detection function, the artificial intelligence chip uses a second driving power to perform a two-dimensional face image recognition function, the artificial intelligence chip uses a third driving power to perform a three-dimensional face image recognition function, the first driving power is smaller than the second driving power, and the second driving power is smaller than the third driving power.

### Claim 14 (depends on 13)

The system of claim 13, wherein the two-dimensional face detection function is a resident program, and the two-dimensional face recognition function and the three-dimensional face recognition function are non-resident programs.

### Claim 15

A low-power face identification method comprising:
emitting at least one first light signal to an object;
receiving at least one second light signal reflected by the object;
decoding the at least one second light signal to generate a decoded light signal;
extracting two-dimensional image information from the decoded light signal;
performing a two-dimensional face detection function by an artificial intelligence chip according to the two-dimensional image information;
inhibiting a two-dimensional face recognition function when a two-dimensional face is undetected; and
disabling an image converter by the artificial intelligence chip in order to inhibit a three-dimensional face recognition function when the two-dimensional face recognition function is inhibited.

### Claim 16 (depends on 15)

The method of claim 15, wherein the two-dimensional face detection function is a resident program, and the two-dimensional face recognition function and the three-dimensional face recognition function are non-resident programs.

### Claim 17 (depends on 15)

The method of claim 15, wherein the decoded light signal comprises the two-dimensional image information and the three-dimensional image information, and the artificial intelligence chip receives the two-dimensional image information extracted from the decoded light signal for performing the two-dimensional face detection function.
