# US 2023/0274456 A1 · Apparatus, system, and control method for measuring led panel

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

- Number: US 2023/0274456 A1
- Document ID: US20230274456A1
- Status: Published application
- Kind: A1
- Application number: 18/143,389
- Filed: 2023-05-04
- Published: 2023-08-31
- Earliest claimed: 2020-11-06
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Kwangdon KIM; Seihan PARK; Jaehee KWAK; Chanyul KIM; Dubok PARK; Cheolseong PARK; Sangwook BAEK
- Web page: https://patentgrep.com/patent/US20230274456A1

## CPC

- G06T 7/60: Analysis of geometric attributes
- G09G 3/32: semiconductive, e.g. using light-emitting diodes [LED]
- G01J 1/42: using electric radiation detectors (optical or mechanical part G01J1/04; by comparison with a reference light or electric value G01J1/10)
- G01J 3/465: {taking into account the colour perception of the eye; using tristimulus detection}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06T 7/90: Determination of colour characteristics
- G01J 2001/4252: {for testing LED's}
- G06T 2207/10024: Color image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G09G 3/006: {Electronic inspection or testing of displays and display drivers, e.g. of LED or LCD displays (testing individual LED's G01R31/2635; testing lamps G01R31/44; testing of optical features of LCD displays G02F1/1309)}
- G09G 3/2003: {Display of colours (specific for liquid crystal displays G09G3/3607)}
- G09G 2320/0693: Calibration of display systems
- G09G 2340/06: Colour space transformation
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G09G: ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION (arrangements for transferring data between digital computers and displays G06F3/14; static indicating arrangements comprising an association of a number of separate sources or light control cells G09F9/00; static indicating arrangements comprising integral associations of a number of light sources H01J, H01K, H10H, H05B33/12; scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission, details thereof H04N1/00)
- G01J: MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY (light sources F21, H01J, H01K, H05B; investigating properties of materials by optical means G01N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed are an apparatus, a system, and a control method for measuring an LED panel. The method for measuring an LED panel comprises the steps of: capturing an image of an LED panel displayed in a preset color; classifying each pixel of the LED panel from the captured image of the LED panel into pixel regions having different sizes according to a predetermined threshold brightness value; obtaining a tristimulus value of each pixel by using the data of the classified pixel regions and a trained artificial intelligence model; and obtaining the luminance and chrominance of each pixel on the basis of the obtained tristimulus value.

## Claims

### Claim 1

A method for measuring an light-emitting diode (LED) panel, the method comprising:
capturing an image of the LED panel while the LED panel displays a preset color;
classifying, based on the captured image of the LED panel, each pixel of the LED panel into pixel regions comprising different sizes, wherein the size of each pixel region corresponds to a predetermined threshold brightness value;
obtaining a tristimulus value of each pixel of the LED panel based on the classified pixel regions and a trained artificial intelligence model; and
obtaining a luminance and a chromaticity of each pixel of the LED panel based on the obtained tristimulus value.

### Claim 2 (depends on 1)

The method of claim 1,
wherein a positive correlation exists between the sizes of the pixel regions and brightness values of the pixels included in the pixel regions.

### Claim 3 (depends on 1)

The method of claim 1,
wherein the trained artificial intelligence model is trained using input data for one pixel comprising data of a pixel region in a red (R) color of a preset size, data of a pixel region in a green (G) color of the preset size, and data of a pixel region in a blue (B) color of the preset size, and output data for the one pixel comprising two-dimensional (2D) data of a tristimulus value of the same size as the preset size.

### Claim 4 (depends on 3)

The method of claim 3,
wherein the output data is padded based on the tristimulus value.

### Claim 5 (depends on 1)

The method of claim 1,
wherein the obtaining the tristimulus value of each pixel further comprises:
inputting data of a pixel region in an R color, data of a pixel region in a G color, and data of a pixel region in a B color of each pixel of the LED panel into the trained artificial intelligence model, and obtaining two-dimensional (2D) data for a tristimulus value of each pixel of a size corresponding to a size of the pixel region of the R color, a size of the pixel region of the G color, and a size of the pixel region of the B color from the trained artificial intelligence model.

### Claim 6 (depends on 5)

The method for measuring an LED panel of claim 5,
wherein the obtaining the tristimulus value of each pixel further comprises:
obtaining a single value as the tristimulus value of each pixel comprising one of a maximum value, an average value, or a weighted average value of the 2D data for the tristimulus value of each pixel.

### Claim 7

An LED panel measuring apparatus comprising:
an input interface;
a display;
at least one memory storing a trained artificial intelligence model; and
at least one processor configured to:
control the input interface to receive an image of an LED panel displaying a preset color,
classify, based on the received image of the LED panel, each pixel of the LED panel into pixel regions comprising different, wherein the size of each pixel region corresponds to a predetermined threshold brightness value,
obtain a tristimulus value of each pixel of the LED panel based on the data of the classified pixel regions and the trained artificial intelligence model, and obtain a luminance and a chromaticity of each pixel of the LED panel based on the obtained tristimulus value, and
display the obtained luminance and the obtained chromaticity of each pixel on the display.

### Claim 8 (depends on 7)

The LED panel measuring apparatus of claim 7,
wherein a positive correlation exists between the sizes of the pixel regions and brightness values of the pixels included in the pixel regions.

### Claim 9 (depends on 7)

The LED panel measuring apparatus of claim 7,
wherein the trained artificial intelligence model is trained using data for one pixel comprising data of a pixel region in a red (R) color of a preset size, data of a pixel region in a green (G) color of the preset size, and data of a pixel region in a blue (B) color of the preset size for one pixel are set as input data, and output data for the one pixel comprising two-dimensional (2D) data of a tristimulus value of the same size as the preset size.

### Claim 10 (depends on 9)

The LED panel measuring apparatus of claim 9,
wherein the output data is padded based on the tristimulus value.

### Claim 11 (depends on 7)

The LED panel measuring apparatus of claim 7,
wherein the at least one processor is further configured to:
input data of a pixel region in an R color, data of a pixel region in a G color, and data of a pixel region in a B color of each pixel of the LED panel into the trained artificial intelligence model, and obtain two-dimensional (2D) data for a tristimulus value of each pixel of the LED panel of a size corresponding to a size of the pixel region of the R color, a size of the pixel region of the G color, and a size of the pixel region of the B color from the trained artificial intelligence model.

### Claim 12 (depends on 11)

The LED panel measuring apparatus of claim 11,
wherein the at least one processor is further configured to:
obtain a single value as the tristimulus value of each pixel of the LED panel comprising one of a maximum value, an average value, or a weighted average value of the 2D data for the tristimulus value of each pixel of the LED panel.

### Claim 13

An LED panel measuring system comprising:
a camera configured to capture an image of an LED panel while the LED panel displays a preset color; and
an LED panel measuring apparatus comprising: at least one memory storing at least one instruction; and at least one processor configured to execute the at least one instruction to:
receive input of the captured image of the LED panel,
classify, based on the captured image of the LED panel, each pixel of the LED panel into pixel regions having different sizes, wherein the size of each pixel region corresponds to a predetermined threshold brightness value,
obtain a tristimulus value of each pixel of the LED panel based on the data of the classified pixel regions and a trained artificial intelligence model,
obtain a luminance and a chromaticity of each pixel of the LED panel based on the obtained tristimulus value, and
display, on a display, the obtained luminance and the obtained chromaticity of each pixel.

### Claim 14 (depends on 13)

The LED panel measuring system of claim 13,
wherein a positive correlation exists between the sizes of the pixel regions and the brightness values of the pixels included in the pixel regions.

### Claim 15 (depends on 13)

The LED panel measuring system of claim 13,
wherein the trained artificial intelligence model is trained using input data for one pixel comprising data of a pixel region in a red (R) color of a preset size, data of a pixel region in a green (G) color of the preset size, and data of a pixel region in a blue (B) color of the preset size, and output date for the one pixel comprising two-dimensional (2D) data of a tristimulus value of the same size as the preset size.

### Claim 16 (depends on 15)

The LED panel measuring system of claim 15, wherein the output data is padded based on the tristimulus value.

### Claim 17 (depends on 13)

The LED panel measuring system of claim 13,
wherein the at least one processor is further configured to:
input data of a pixel region in an R color, data of a pixel region in a G color, and data of a pixel region in a B color of each pixel of the LED panel into the trained artificial intelligence model, and obtain two-dimensional (2D) data for a tristimulus value of each pixel of the LED panel of a size corresponding to a size of the pixel region of the R color, a size of the pixel region of the G color, and a size of the pixel region of the B color from the trained artificial intelligence model.

### Claim 18 (depends on 17)

The LED panel measuring system of claim 17,
wherein the at least one processor is further configured to:
obtain a single value as the tristimulus value of each pixel of the LED panel comprising one of a maximum value, an average value, or a weighted average value of the 2D data for the tristimulus value of each pixel of the LED panel.

### Claim 19

A non-transitory computer readable medium having instructions stored therein, which when executed by a processor cause the processor to execute a method of measuring an LED panel, the method comprising:
capturing an image of the LED panel while the LED panel displays a preset color;
classifying, based on the captured image of the LED panel, each pixel of the LED panel into pixel regions comprising different sizes, wherein the size of each pixel region corresponds to a predetermined threshold brightness value;
obtaining a tristimulus value of each pixel based on the classified pixel regions and a trained artificial intelligence model; and
obtaining a luminance and a chromaticity of each pixel of the LED panel based on the obtained tristimulus value.
