# US 2021/0065339 A1 · Image processing apparatus, image processing method, and computer-readable recording medium

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

- Number: US 2021/0065339 A1
- Document ID: US20210065339A1
- Status: Published application
- Kind: A1
- Application number: 16/962,270
- Filed: 2019-01-24
- Published: 2021-03-04
- Earliest claimed: 2018-01-24
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Minsu CHEON; Yongsup PARK; Changhan KIM; Jaeyeon PARK; lljun AHN; Heeseok OH; Tammy LEE; Kiheum CHO
- Web page: https://patentgrep.com/patent/US20210065339A1

## CPC

- G06T 5/90: Dynamic range modification of images or parts thereof
- G06T 5/92: based on global image properties
- G09G 5/005: {Adapting incoming signals to the display format of the display terminal}
- G09G 5/10: Intensity circuits
- H04N 23/741: by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
- G06T 2207/10016: Video; Image sequence
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20208: High dynamic range [HDR] image processing
- 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)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

An image processing apparatus is disclosed. The present image processing apparatus comprises: a memory for storing a low dynamic range (LDR) image and a processor for adjusting the brightness of the LDR image by means of a pixel-specific brightness ratio identified using a first parameter, and acquiring a high dynamic range (HDR) image by adding or subtracting a pixel-specific correction value identified using a second parameter in the brightness-adjusted LDR image.

## Claims

### Claim 1

An image processing apparatus comprising:
a memory storing a low dynamic range (LDR) image; and
a processor configured to:
adjust the brightness of the LDR image by means of a pixel-specific brightness ratio identified by using a first parameter, and acquire a high dynamic range (HDR) image by adding or subtracting a pixel-specific correction value identified by using a second parameter to or from the pixel value of the brightness-adjusted LDR image.

### Claim 2 (depends on 1)

The image processing apparatus of claim 1,
wherein, in the memory, an original HDR image and an LDR image for learning corresponding to the original HDR image are stored, and
the first parameter has been learned such that the difference between the brightness of an HDR image generated by using the LDR image for learning and the brightness of the original HDR image becomes minimal.

### Claim 3 (depends on 2)

The image processing apparatus of claim 2,
wherein the second parameter has been learned such that the difference between the pixel value of an HDR image generated by using the LDR image for learning and the pixel value of the original HDR image becomes minimal.

### Claim 4 (depends on 2)

The image processing apparatus of claim 2,
wherein the processor is configured to:
learn the first parameter in consideration of normalization of the range of the brightness value of the LDR image for learning and the range of the brightness value of the original HDR image.

### Claim 5 (depends on 2)

The image processing apparatus of claim 2,
wherein the processor is configured to:
based on a control command for changing the network structure being input, learn the first parameter based on a pixel-specific brightness ratio identified by using at least one multiplication operation.

### Claim 6 (depends on 1)

The image processing apparatus of claim 1,
wherein the processor is configured to:
identify a pixel-specific correction value such that the difference of the brightness among the pixels within an area having brightness smaller than a predetermined value in the brightness-adjusted LDR image is big.

### Claim 7 (depends on 1)

The image processing apparatus of claim 1,
wherein the processor is configured to:
identify a pixel-specific correction value such that the difference of the brightness among the pixels within an area having brightness greater than or equal to a predetermined value in the brightness-adjusted LDR image is small.

### Claim 8 (depends on 1)

The image processing apparatus of claim 1,
wherein the processor is configured to:
perform an operation of identifying a pixel-specific brightness ratio by using the first parameter and an operation of identifying a pixel-specific correction value by using the second parameter in parallel.

### Claim 9 (depends on 1)

The image processing apparatus of claim 1,
wherein the processor is configured to:
identify the pixel-specific brightness ratio in further consideration of adjacent pixels for each pixel of the LDR image.

### Claim 10

An image processing method, the method comprising:
adjusting the brightness of the low dynamic range (LDR) image by means of a pixel-specific brightness ratio identified by using a first parameter; and
acquiring a high dynamic range (HDR) image by adding or subtracting a pixel-specific correction value identified by using a second parameter to or from the pixel value of the brightness-adjusted LDR image.

### Claim 11 (depends on 10)

The image processing method of claim 10,
wherein the first parameter has been learned such that the difference between the brightness of an HDR image generated by using an LDR image for learning corresponding to the original HDR image and the brightness of the original HDR image becomes minimal.

### Claim 12 (depends on 10)

The image processing method of claim 10,
wherein the pixel-specific correction value is identified such that the difference among the pixels within an area having brightness smaller than a predetermined value in the brightness-adjusted LDR image is big.

### Claim 13 (depends on 10)

The image processing method of claim 10,
wherein the pixel-specific correction value is identified such that the difference of the brightness among the pixels within an area having brightness greater than or equal to a predetermined value in the brightness-adjusted LDR image is small.

### Claim 14 (depends on 10)

The image processing method of claim 10,
wherein an operation of identifying a pixel-specific brightness ratio by using the first parameter and an operation of identifying a pixel-specific correction value by using the second parameter are performed in parallel.

### Claim 15 (depends on 10)

The image processing method of claim 10,
wherein the pixel-specific brightness ratio is identified in further consideration of adjacent pixels for each pixel of the LDR image.
