# US 12,223,757 B2 · Image processing method, device, electronic apparatus, and storage medium

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

- Number: US 12,223,757 B2
- Document ID: US12223757B2
- Status: Granted
- Kind: B2
- Application number: 17/846,364
- Filed: 2022-06-22
- Published: 2022-10-06
- Granted: 2025-02-11
- Earliest claimed: 2019-12-24
- Assignees: Zhuhai Pantum Electronics Co., Ltd.
- Applicants: Zhuhai Pantum Electronics Co., Ltd.
- Inventors: Jibing Peng; Yangxiao Ma
- Web page: https://patentgrep.com/patent/US12223757B2

## CPC

- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06V 10/82: using neural networks
- G06V 30/18: Extraction of features or characteristics of the image
- G06V 30/18105: {related to colour}
- H04N 1/448: {Rendering the image unintelligible, e.g. scrambling}
- H04N 1/60: Colour correction or control {(H04N1/54 takes precedence)}
- G06V 10/56: relating to colour
- G06V 30/153: {using recognition of characters or words}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

An image processing method, applied to an electronic apparatus, includes performing feature extraction processing on a source image to obtain a feature data set corresponding to a source file, determining an image processing parameter corresponding to the feature data set according to the feature data set, and processing the source image according to the image processing parameter.

## Claims

### Claim 1

An image processing method, applied to an electronic apparatus, comprising:
performing feature extraction processing on a source image to obtain a feature data set corresponding to a source file;
determining an image processing parameter corresponding to the feature data set according to the feature data set, including performing identification on the feature data set by using a trained neural network to obtain identification information and determining the image processing parameter corresponding to the identification information; and
processing the source image according to the image processing parameter,
wherein:
the feature data set includes tone information;
the identification information includes a CMYK tone adjustment value, and a tone curve adjustment value;
the image processing parameter includes a CMYK tone processing parameter, and a tone curve processing parameter;
performing identification on the feature data set by using the trained neural network to obtain the identification information includes:
identifying the tone information by using the trained neural network to obtain the CMYK tone adjustment value, and the tone curve adjustment value; and
determining the image processing parameter corresponding to the identification information includes:
retrieving the CMYK tone processing parameter corresponding to the CMYK tone adjustment value, and the tone curve processing parameter corresponding to the tone curve adjustment value.

### Claim 2 (depends on 1)

The method according to claim 1, wherein
the pre-trained neural network is configured to perform identification and calculation on the feature data set to output the identification information.

### Claim 3 (depends on 2)

The method according to claim 2, wherein:
the feature data set includes image element information and/or boundary contour information in first image data;
the identification information includes file type information;
performing the identification on the feature data set by using the trained neural network to obtain the identification information includes:
performing file type identification on the source file corresponding to the source image by using the trained neural network according to the image element information and/or the boundary contour information to obtain the file type information of the source file.

### Claim 4 (depends on 1)

The method according to claim 1, wherein performing the feature extraction processing on the source image further includes:
performing first image processing on the source image; and
processing the source image according to the image processing parameter, including performing second image processing on the source image after the first image processing according to the image processing parameter.

### Claim 5 (depends on 4)

The method according to claim 4, wherein:
the feature data set includes character information;
the character information includes at least one first character and position information of each first character;
the identification information includes sensitive character identification information;
the sensitive character identification information includes at least one sensitive character of the at least one first character and position information corresponding to each sensitive character;
the image processing parameter includes a sensitive character processing parameter;
performing the identification on the feature data set by using the trained neural network to obtain the identification information includes:
performing sensitive character identification on the at least one first character by using the trained neural network to obtain the at least one sensitive character and the position information corresponding to each sensitive character of the at least one first character;
determining the image processing parameter corresponding to the identification information includes:
generating the sensitive character processing parameter according to the at least one sensitive character of the at least one first character and the position information corresponding to each sensitive character; and
processing the source image according to the image processing parameter includes:
performing sensitive character removal processing on the source image after the first image processing according to the sensitive character processing parameter.

### Claim 6 (depends on 4)

The method according to claim 4, wherein:
the feature data set includes color gamut information;
the identification information includes a brightness adjustment value, and a color adjustment value;
the image processing parameter includes a brightness processing parameter, and a color processing parameter;
performing identification on the feature data set by using the trained neural network to obtain the identification information includes:
identifying the color gamut information by using the trained neural network to obtain the brightness adjustment value, and the color adjustment value;
determining the image processing parameter corresponding to the identification information includes:
retrieving the brightness processing parameter corresponding to the brightness adjustment value, and the color processing parameter corresponding to the color adjustment value from a database according to the brightness adjustment value, and the color adjustment value; and
processing the source image according to the image processing parameter includes:
according to the CMYK tone processing parameter, the tone curve processing parameter, the brightness processing parameter, and the color processing parameter, processing the source image after the first image processing.

### Claim 7

An electronic apparatus comprising:
a memory storing program instructions; and
a processor coupled with the memory and, when the program instructions being executed, configured to:
perform feature extraction processing on a source image to obtain a feature data set corresponding to a source file;
determine an image processing parameter corresponding to the feature data set according to the feature data set; and
process the source image according to the image processing parameter,
wherein,
the processor is further configured to:
perform identification on the feature data set by using a trained neural network to obtain identification information; and
determine the image processing parameter corresponding to the identification information according to the identification information;
the feature data set includes tone information;
the identification information includes a CMYK tone adjustment value, and a tone curve adjustment value;
the image processing parameter includes a CMYK tone processing parameter, and a tone curve processing parameter; and
the processor is further configured to:
identify the tone information by using the trained neural network to obtain the CMYK tone adjustment value, the tone curve adjustment value; and
retrieve the CMYK tone processing parameter corresponding to the CMYK tone adjustment value, the tone curve processing parameter corresponding to the tone curve adjustment value, from a database according to the CMYK tone adjustment value, the tone curve adjustment value.

### Claim 8 (depends on 7)

The electronic apparatus according to claim 7, wherein
the pre-trained neural network is configured to perform identification and calculation on the feature data set to output the identification information.

### Claim 9 (depends on 8)

The electronic apparatus according to claim 8, wherein:
the feature data set includes image element information and/or boundary contour information in first image data;
the identification information includes file type information;
the processor is further configured to:
perform file type identification on the source file corresponding to the source image by using the trained neural network according to the image element information and/or the boundary contour information to obtain the file type information of the source file.

### Claim 10 (depends on 7)

The electronic apparatus according to claim 7, wherein the processor is further configured to:
perform first image processing on the source image; and
process the source image according to the image processing parameter, including performing second image processing on the source image after the first image processing according to the image processing parameter.

### Claim 11 (depends on 10)

The electronic apparatus according to claim 10, wherein:
the feature data set includes character information;
the character information includes at least one first character and position information of each first character;
the identification information includes sensitive character identification information;
the sensitive character identification information includes at least one sensitive character of the at least one first character and position information corresponding to each sensitive character;
the image processing parameter includes a sensitive character processing parameter;
the processor is further configured to:
perform sensitive character identification on the at least one first character by using the trained neural network to obtain the at least one sensitive character and the position information corresponding to each sensitive character of the at least one first character;
generate the sensitive character processing parameter according to the at least one sensitive character of the at least one first character and the position information corresponding to each sensitive character; and
perform sensitive character removal processing on the source image after the first image processing according to the sensitive character processing parameter.

### Claim 12 (depends on 10)

The electronic apparatus according to claim 10, wherein:
the feature data set includes color gamut information;
the identification information includes a brightness adjustment value, and a color adjustment value;
the image processing parameter includes a brightness processing parameter, and a color processing parameter;
the processor is further configured to:
identify the color gamut information by using the trained neural network to obtain the brightness adjustment value, and the color adjustment value;
retrieve the brightness processing parameter corresponding to the brightness adjustment value, and the color processing parameter corresponding to the color adjustment value from a database according the brightness adjustment value, and the color adjustment value; and
according to the CMYK tone processing parameter, the tone curve processing parameter, the brightness processing parameter, and the color processing parameter, process the source image after the first image processing.

### Claim 13

A non-transitory computer-readable storage medium storing a program that, when executed by a processor, causes the processor to:
perform feature extraction processing on a source image to obtain a feature data set corresponding to a source file;
determine an image processing parameter corresponding to the feature data set according to the feature data set; and
process the source image according to the image processing parameter,
wherein,
the processor is further configured to:
perform identification on the feature data set by using a trained neural network to obtain identification information; and
determine the image processing parameter corresponding to the identification information according to the identification information;
the feature data set includes tone information;
the identification information includes a CMYK tone adjustment value, and a tone curve adjustment value;
the image processing parameter includes a CMYK tone processing parameter, and
a tone curve processing parameter; and
the processor is further configured to:
identify the tone information by using the trained neural network to obtain the CMYK tone adjustment value, the tone curve adjustment value; and
retrieve the CMYK tone processing parameter corresponding to the CMYK tone adjustment value, the tone curve processing parameter corresponding to the tone curve adjustment value, from a database according to the CMYK tone adjustment value, the tone curve adjustment value.

### Claim 14 (depends on 13)

The storage medium according to claim 13, wherein
the pre-trained neural network is configured to perform identification and calculation on the feature data set to output the identification information.

### Claim 15 (depends on 14)

The storage medium according to claim 14, wherein:
the feature data set includes image element information and/or boundary contour information in first image data;
the identification information includes file type information;
the processor is further configured to:
perform file type identification on the source file corresponding to the source image by using the trained neural network according to the image element information and/or the boundary contour information to obtain the file type information of the source file.

### Claim 16 (depends on 13)

The storage medium according to claim 13, wherein the processor is further configured to:
perform first image processing on the source image; and
process the source image according to the image processing parameter, including performing second image processing on the source image after the first image processing according to the image processing parameter.

### Claim 17 (depends on 16)

The storage medium according to claim 16, wherein:
the feature data set includes character information;
the character information includes at least one first character and position information of each first character;
the identification information includes sensitive character identification information;
the sensitive character identification information includes at least one sensitive character of the at least one first character and position information corresponding to each sensitive character;
the image processing parameter includes a sensitive character processing parameter;
the processor is further configured to:
perform sensitive character identification on the at least one first character by using the trained neural network to obtain the at least one sensitive character and the position information corresponding to each sensitive character of the at least one first character;
generate the sensitive character processing parameter according to the at least one sensitive character of the at least one first character and the position information corresponding to each sensitive character; and
perform sensitive character removal processing on the source image after the first image processing according to the sensitive character processing parameter.

### Claim 18 (depends on 16)

The storage medium according to claim 16, wherein:
the feature data set includes color gamut information;
the identification information includes a brightness adjustment value, and a color adjustment value;
the image processing parameter includes a brightness processing parameter, and a color processing parameter;
the processor is further configured to:
identify the color gamut information by using the trained neural network to obtain the brightness adjustment value, and the color adjustment value;
retrieve the brightness processing parameter corresponding to the brightness adjustment value, and the color processing parameter corresponding to the color adjustment value from a database according to the brightness adjustment value, and the color adjustment value; and
according to the CMYK tone processing parameter, the tone curve processing parameter, the brightness processing parameter, and the color processing parameter, process the source image after the first image processing.