Sharpening post-processing method, device and equipment for art illustration and medium

Abstract

The invention provides a sharpening post-processing method and device for art illustration, equipment and a medium, and the method comprises the steps: obtaining an illustration, carrying out the DCT transformation, converting from a spatial domain to a frequency domain, and obtaining a high-frequency component and a low-frequency component; filtering the low-frequency component through a Gaussian filter to obtain a low-frequency filtering component, combining the low-frequency filtering component with the high-frequency component, and then carrying out inverse DCT (Discrete Cosine Transform) to obtain an interpolation transformation graph; performing Gamma brightness correction on the illustration transformation graph to obtain an illustration correction graph; soft light superposition processing is carried out on the illustration correction image and the illustration image to obtain a needed illustration processing image, natural fusion of the processed image and the original image is achieved, and therefore the overall quality of commercial illustration is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a clear post-processing method, device and equipment for art illustration and a medium. BACKGROUND

[0002] In the application scenario of commercial illustration, the original illustration image often has problems of low resolution, blurred details and insufficient texture, which affects its display effect and commercial value in the fields of advertising, product packaging and digital media. At the same time, after processing, the image is prone to unreasonable light and shade distribution, dark areas that are too dark to lose details, and bright areas that are too bright to produce a glaring effect.

[0003] In addition, the image directly processed has certain problems in fusion with the original image, and cannot naturally show the effect of clear processing, which is difficult to meet the strict requirements of the commercial field for high-quality illustration images. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a clear post-processing method, device and equipment for art illustration, which realizes the natural fusion of the processed image and the original image, thereby improving the overall quality of commercial illustration.

[0005] In a first aspect, the present application provides a clear post-processing method for art illustration, comprising the following steps:

[0006] Step 1: Obtain an illustration image, perform DCT transformation to convert from spatial domain to frequency domain, and obtain high-frequency components and low-frequency components;

[0007] Step 2: Filter the low-frequency components through a Gaussian filter to obtain low-frequency filtered components, combine the low-frequency filtered components with the high-frequency components, and then perform inverse DCT transformation to obtain an illustration transformed image;

[0008] Step 3: Perform Gamma brightness correction on the illustration transformed image to obtain an illustration corrected image;

[0009] Step 4: Perform soft light superposition processing on the illustration corrected image and the illustration image to obtain a desired illustration processed image.

[0010] In a second aspect, the present application provides a clear post-processing device for art illustration, comprising:

[0011] A conversion module obtains an illustration image, performs DCT transformation to convert from spatial domain to frequency domain, and obtains high-frequency components and low-frequency components;

[0012] The inverse conversion module filters the low-frequency component through a Gaussian filter to obtain a low-frequency filtered component, merges the low-frequency filtered component with the high-frequency component, and then performs an inverse DCT transformation to obtain an illustration transformation graph;

[0013] The correction module performs Gamma brightness correction on the illustration transformation graph to obtain an illustration correction graph;

[0014] The soft light processing module performs soft light superposition processing on the illustration correction graph and the illustration graph to obtain the required illustration processing graph.

[0015] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the method of the first aspect.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method of the first aspect.

[0017] The one or more technical solutions provided by the present application have at least the following technical effects or advantages:

[0018] Significant improvement in resolution and texture: through the Swin-IR super-resolution algorithm, the resolution of the commercial illustration is effectively expanded, and the details and texture of the image are significantly enhanced, which can clearly display the lines, color transitions and textures in the illustration, providing higher quality image materials for commercial applications.

[0019] Optimization of image details and structure: using DCT transformation and Gaussian filtering to process the high-frequency and low-frequency parts of the image, effectively retaining the detail information of the image while smoothing the low-frequency area, making the structure of the image more reasonable, and the overall visual effect more clear and natural, avoiding image distortion caused by excessive processing.

[0020] Reasonable improvement in brightness distribution: Gamma brightness correction technology can accurately adjust the brightness of the image, effectively solving the problem of dark light in the image and high light, making the brightness distribution of the image more consistent with the visual habits of the human eye, improving the overall visual comfort and aesthetic of the image, and better meeting the needs of commercial display.

[0021] Natural fusion effect is prominent: by superimposing the processed image with the original image, the natural fusion of the processed image with the original image is realized, which fully displays the effect of the clear processing, and also retains the style and characteristics of the original image, so that the final output commercial illustration improves the quality while maintaining the original artistic characteristics, and is suitable for various commercial scene applications.

[0022] Processing efficiency and good compatibility: The present application has high processing efficiency while realizing high-quality sharpening processing, can quickly process a large number of commercial illustration images, and meets the demand of the commercial field for image rapid processing. In addition, the present application can be seamlessly integrated into existing image editing software and commercial illustration production processes, and has good compatibility with other image processing technologies and tools, which facilitates users to use in the original workflow, reduces the threshold and cost of technology application.

[0023] The above description is only a summary of the technical solutions of the present application, in order to more clearly understand the technical means of the present application, and to be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0024] The present application will be further described below with reference to the accompanying drawings combined with embodiments.

[0025] Figure 1 The flowchart in the method of the first embodiment of the present application;

[0026] Figure 2 The structure diagram of the device in the second embodiment of the present application. DETAILED DESCRIPTION

[0027] The embodiments of the present application provide a kind of for fine art illustration sharpening post-processing method, device, equipment and medium, by combining Swin-IR super-resolution algorithm, DCT transform, Gaussian filter, Gamma brightness correction and image fusion etc., improve the resolution and texture of commercial illustration, optimize the light and shade distribution of image, reasonably process the high frequency and low frequency information of image, and realize the natural fusion of processed image and original image, to improve the overall quality of commercial illustration, meet the diversified demand of high-quality illustration image in commercial field.

[0028] The technical solutions in the embodiments of the present application are as follows:

[0029] Swin-IR super-resolution algorithm: an image super-resolution algorithm based on Transformer architecture, which can convert low-resolution images into high-resolution images by learning the characteristics and rules of a large number of image data, and effectively improve the details and texture of images. In this algorithm, it is used for resolution improvement and texture optimization of commercial illustration.

[0030] DCT transform (Discrete Cosine Transform): a mathematical transform method that converts images from spatial domain to frequency domain, which can decompose image signals into high-frequency and low-frequency components. The high-frequency part mainly contains the details, edges and textures of the image, and the low-frequency part mainly reflects the overall outline and slowly changing background information of the image.

[0031] Gaussian filter: A linear smoothing filter that can effectively suppress noise and smooth images by performing a weighted average operation on the image. In this algorithm, a 3*3 Gaussian filter is used to process the low-frequency part of the image to reduce noise and blur in the low-frequency region while preserving the main structural information of the image.

[0032] Gamma brightness correction: An image brightness adjustment technique based on power function transformation, which changes the overall brightness distribution of the image by adjusting the Gamma value. The principle is to perform bilinear interpolation on the pixel values of the image to adjust the brightness of the high-light and dark-light regions of the image, making the brightness of the image more consistent with the visual perception of the human eye.

[0033] Soft light superposition: An image fusion method that takes a weighted average of the pixel values of two images to fuse the processed image with the original image, making the processed image more natural and preserving some features of the original image.

[0034] Image resolution enhancement and texture optimization: The Swin-IR super-resolution algorithm is used to process the original commercial illustration image, expanding the image resolution by a predetermined multiple while optimizing the details and texture of the image, making the image clearer and more delicate, and enriching the texture and color performance of the image.

[0035] Image frequency domain decomposition: The image processed by the Swin-IR super-resolution algorithm is subjected to DCT transformation, converting the image from spatial domain to frequency domain, and decomposing the image signal into high-frequency and low-frequency components, thereby distinguishing the image into high-frequency parts containing details, edges and texture information, and low-frequency parts reflecting overall contour and background information.

[0036] High and low frequency processing and merging: The high-frequency part of the image is preserved to ensure that the details and texture of the image are not lost; for the low-frequency part of the image, a 3*3 Gaussian filter is used for filtering processing to smooth the low-frequency region, reduce noise and blur, and preserve the main structural information of the image. After filtering, the processed high-frequency and low-frequency parts are merged and subjected to DCT inverse transformation to convert the image from frequency domain back to spatial domain.

[0037] Gamma brightness correction: Since the image after DCT transformation is prone to dark-light overdarkening and high-light over-brightening, the image output in step three needs to be subjected to Gamma brightness correction. By adjusting the Gamma value, bilinear interpolation is performed on the pixel values of the image based on power function transformation to change the overall brightness distribution of the image, achieve darkening of the high-light and brightening of the dark-light, and make the brightness of the image more consistent with the visual perception of the human eye, improving the visual effect of the image.

[0038] Image fusion: the image after Gamma brightness correction is scaled to the resolution of the original image, and then is soft light superimposed with the original image. The specific method is to take a weighted average of the pixel values of the two images, so that the processed image is naturally fused with the original image, while retaining the clear effect of the processed image, maintaining part of the features and style of the original image, making the final output image more natural and beautiful, and meeting the application requirements of commercial illustrations.

[0039] Embodiment one

[0040] As Figure 1 shown, the embodiment provides a clear post-processing method for art illustrations, including the following steps:

[0041] Step 1, obtaining an illustration, performing DCT transformation to convert from spatial domain to frequency domain, obtaining high frequency component and low frequency component;

[0042] Step 2, filtering the low frequency component through a Gaussian filter to obtain a low frequency filtered component, merging the low frequency filtered component with the high frequency component, and then performing inverse DCT transformation to obtain an illustration transformed image;

[0043] Step 3, performing Gamma brightness correction on the illustration transformed image to obtain an illustration corrected image;

[0044] Step 4, performing soft light superimposition processing on the illustration corrected image and the illustration to obtain the required illustration processed image.

[0045] In this embodiment, preferably, step 1 specifically: obtaining an illustration, processing the illustration image using Swin-IR super-resolution algorithm, expanding the resolution of the illustration by a preset multiple to obtain an enlarged illustration; performing DCT transformation on the enlarged illustration to convert from spatial domain to frequency domain, obtaining high frequency component and low frequency component.

[0046] In this embodiment, preferably, step 4 specifically: scaling the illustration corrected image to an illustration Figure 1 scaled image of the resolution of the illustration, and then performing soft light superimposition processing with the illustration, i.e. taking a weighted average of the pixel values of the illustration scaled image and the illustration to obtain the required illustration processed image.

[0047] In this embodiment, preferably, step 3 specifically: first performing bilinear interpolation on the pixel values of the illustration transformed image based on power function transformation, and then adjusting the Gamma coefficient value for brightness correction to obtain the illustration corrected image;

[0048] The adjustment Gamma coefficient value is: first, the brightness histogram of the image is counted, the number of pixels of each brightness value is counted, the average brightness value of the image is calculated, if the average brightness value is greater than 200, the Gamma coefficient value is set to 0.85; if the average brightness value is greater than or equal to 130 and less than or equal to 200, the Gamma coefficient value is set to 1; if the average brightness value is less than 130, the Gamma coefficient value is set to 1.25.

[0049] Based on the same inventive concept, the application also provides a device corresponding to the method in embodiment one, which is described in detail in embodiment two.

[0050] Embodiment two

[0051] As Figure 2 shown, in the embodiment, a clear post-processing device for art illustration is provided, which comprises:

[0052] A conversion module acquires an illustration image, performs DCT transformation to convert from spatial domain to frequency domain, and obtains high-frequency components and low-frequency components;

[0053] An inverse conversion module filters the low-frequency components through a Gaussian filter to obtain low-frequency filtered components, merges the low-frequency filtered components with the high-frequency components, and then performs inverse DCT transformation to obtain an illustration transformed image;

[0054] A correction module performs Gamma brightness correction on the illustration transformed image to obtain an illustration corrected image;

[0055] A soft light processing module performs soft light superposition processing on the illustration corrected image and the illustration image to obtain a required illustration processed image.

[0056] In the embodiment, preferably, the conversion module specifically: acquires an illustration image, processes the illustration image using a Swin-IR super-resolution algorithm, expands the resolution of the illustration image by a preset multiple to obtain an illustration enlarged image, and performs DCT transformation on the illustration enlarged image to convert from spatial domain to frequency domain, thereby obtaining high-frequency components and low-frequency components.

[0057] In the embodiment, preferably, the soft light processing module specifically: scales the illustration corrected image to an illustration scaled image with a resolution of the illustration, and then performs soft light superposition processing on the illustration scaled image and the illustration image, that is, performs weighted average on the pixel values of the illustration scaled image and the pixel values of the illustration image, thereby obtaining a required illustration processed image. Figure 1

[0058] In the embodiment, preferably, the correction module specifically: first performs bilinear interpolation on the pixel values of the illustration transformed image based on power function transformation, and then adjusts the Gamma coefficient value to perform brightness correction, thereby obtaining an illustration corrected image. ​

[0059] The adjustment of the Gamma coefficient value is as follows: first, statistics are collected on the brightness histogram of the image, the number of pixels at each brightness value is counted, and the average brightness value of the image is calculated. If the average brightness value is greater than 200, the Gamma coefficient value is set to 0.85; if the average brightness value is greater than or equal to 130 and less than or equal to 200, the Gamma coefficient value is set to 1; if the average brightness value is less than 130, the Gamma coefficient value is set to 1.25.

[0060] Since the device described in the second embodiment of the present invention is used to implement the method of the first embodiment of the present invention, those skilled in the art will be able to understand the specific structure and variations of the device based on the method described in the first embodiment of the present invention, and therefore will not be described in detail here. All devices used in the method of the first embodiment of the present invention fall within the scope of protection of the present invention.

[0061] Based on the same inventive concept, this application provides an electronic device embodiment corresponding to the first embodiment, see the third embodiment for details.

[0062] Example 3

[0063] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any implementation method in the first embodiment can be implemented.

[0064] Since the electronic device described in this embodiment is the device used to implement the method in Example 1 of this application, based on the method described in Example 1 of this application, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of this application will not be described in detail here. As long as the device used by those skilled in the art to implement the method in the embodiment of this application falls within the scope of protection to be provided by this application.

[0065] Based on the same inventive concept, this application provides a storage medium corresponding to Example 1, see Example 4 for details.

[0066] Example 4

[0067] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any implementation method in the first embodiment can be implemented.

[0068] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In a software embodiment, the methods can be tangibly embodied in a machine-readable storage medium having stored thereon instructions that can be used to program a computer to perform any of the methods. The software implementation can be initialized by loading and executing a set of instructions arranged to perform one of the methods into the computer's memory. Alternatively, hard-wired circuitry can be used in place of, or in combination with, software instructions. Thus, the

[0069] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in one or more of the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in one or more of the flowchart illustrations and / or block diagrams.

[0070] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in one or more of the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in one or more of the flowchart illustrations and / or block diagrams.

[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in one or more of the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in one or more of the flowchart illustrations and / or block diagrams.

[0072] While the present application has been described with reference to specific implementations thereof, it should be understood by those skilled in the art that a variety of equivalents for the specific embodiments could be made and that such equivalents are within the scope of the present application, which is not to be limited to the specific embodiments described and which extends to wherever the specific techniques described can be employed.

Claims

1. A post-processing method for clarifying art illustrations, characterized by: The steps include: Step 1: Get an illustration image, perform DCT transformation, convert it from the spatial domain to the frequency domain, and obtain high-frequency components and low-frequency components; Step 2: Filter the low-frequency component through a Gaussian filter to obtain a low-frequency filtered component, merge the low-frequency filtered component with the high-frequency component, and then perform an inverse DCT transform to obtain an illustration transformation image; Step 3: Perform gamma brightness correction on the illustration transformation image to obtain an illustration correction image; Step 4: Perform soft light overlay processing on the illustration correction image and the illustration image to obtain the required illustration processing image.

2. The post-processing method for clarifying an art illustration according to claim 1, characterized in that: The step 1 specifically comprises the following steps: obtaining an illustration image, processing the illustration image using the Swin-IR super-resolution algorithm, enlarging the resolution of the illustration image by a preset multiple, and obtaining an enlarged illustration image; performing a DCT transform on the enlarged illustration image, converting it from the spatial domain to the frequency domain, and obtaining high-frequency components and low-frequency components.

3. The post-processing method for clarifying an art illustration according to claim 2, characterized in that: The step 4 is specifically as follows: scaling the illustration correction image to a scaled illustration image with the same resolution as the illustration image, and then performing soft light overlay processing with the illustration image, that is, performing weighted averaging on the pixel values ​​of the scaled illustration image and the pixel values ​​of the illustration image to obtain the required illustration processing image.

4. The post-processing method for art illustration clarity according to claim 1, characterized in that: The step 3 specifically comprises: performing bilinear interpolation on the pixel values ​​of the image by power function transformation on the illustration transformation image, and then adjusting the gamma coefficient value to perform brightness correction to obtain the illustration correction image; The Gamma coefficient value is adjusted as follows: first, the brightness histogram of the image is counted, the number of pixels of each brightness value is counted, and the average brightness value of the image is calculated. If the average brightness value is greater than 200, the Gamma coefficient value is set to 0.85; If the average brightness value is greater than or equal to 130 and less than or equal to 200, the Gamma coefficient value is set to 1; If the average brightness value is less than 130, the gamma coefficient value is set to 1.

25.

5. A post-processing device for sharpening art illustrations, characterized by: include: The conversion module obtains an illustration image, performs DCT transformation, converts it from the spatial domain to the frequency domain, and obtains high-frequency components and low-frequency components; The inverse transformation module filters the low-frequency component through a Gaussian filter to obtain a low-frequency filtered component, merges the low-frequency filtered component with the high-frequency component, and then performs an inverse DCT transform to obtain an illustration transformation image; The correction module performs gamma brightness correction on the illustration transformation image to obtain an illustration correction image; The soft light processing module performs soft light superposition processing on the illustration correction image and the illustration image to obtain the required illustration processing image.

6. The device for post-processing art illustrations according to claim 5, characterized in that: The conversion module specifically obtains an illustration image, processes the illustration image using the Swin-IR super-resolution algorithm, and enlarges the resolution of the illustration image according to a preset multiple to obtain an enlarged illustration image; performs a DCT transform on the enlarged illustration image, converting it from the spatial domain to the frequency domain to obtain high-frequency components and low-frequency components.

7. The apparatus for post-processing art illustrations according to claim 6, characterized in that: The soft light processing module specifically scales the illustration correction image to a scaled illustration image with the same resolution as the illustration image, and then performs soft light overlay processing with the illustration image, that is, weighted averaging the pixel values ​​of the scaled illustration image and the pixel values ​​of the illustration image to obtain the required illustration processing image.

8. The apparatus for post-processing art illustrations according to claim 5, characterized in that: The correction module specifically comprises: first performing bilinear interpolation on the pixel values ​​of the image based on the power function transformation on the illustration transformation map, and then adjusting the Gamma coefficient value to perform brightness correction to obtain the illustration correction map; The Gamma coefficient value is adjusted as follows: first, the brightness histogram of the image is counted, the number of pixels of each brightness value is counted, and the average brightness value of the image is calculated. If the average brightness value is greater than 200, the Gamma coefficient value is set to 0.85; If the average brightness value is greater than or equal to 130 and less than or equal to 200, the Gamma coefficient value is set to 1; If the average brightness value is less than 130, the gamma coefficient value is set to 1.

25.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images