Visual imaging optimization method and system for digital oil painting

Abstract

The invention relates to the technical field of imaging optimization, in particular to a visual imaging optimization method and system for a digital oil painting. The method comprises the following steps: acquiring an initial oil painting shooting image set; performing digital image conversion on the initial oil painting shooting image set to generate a standard digital oil painting image; performing multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain digital oil painting multi-dimensional spatial feature data; performing image pyramid layer construction on the standard digital oil painting image by using the digital oil painting multi-dimensional spatial feature data to generate a multi-scale pyramid image; performing region fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; and performing oil painting spatial domain optimization on the standard digital oil painting image through the detail enhanced texture layer to generate a digital spatial domain optimized image. According to the method, the authenticity and flexibility of visual imaging of the digital oil painting are improved through multi-scale detail enhancement, environment illumination perception and high-resolution display optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of imaging optimization, and in particular to a visual imaging optimization method and system for digital oil paintings. Background Art

[0002] Initially, digital image processing technology was applied to the enhancement of two-dimensional images, such as color correction and resolution improvement, to help artworks present higher quality visual effects on the screen. However, the unique texture of oil paintings does not rely solely on color, but more on the texture and three-dimensional sense of the oil paint layer. With the development of 3D printing technology, three-dimensional modeling technology in computer graphics has gradually been applied to the three-dimensional reconstruction of images, allowing traditional flat images to be converted into three-dimensional forms with physical textures. After entering the 21st century, digital oil painting imaging methods have been continuously optimized, and by combining 3D printing and material science, the limitations of traditional oil painting displays have been broken. High-resolution digital oil painting images are converted into three-dimensional models and printed through sophisticated 3D printing technology to simulate the layering and brushstroke details of oil paintings. At this time, the reconstruction of texture is not only limited to the surface, but also involves the selection and processing of materials, such as the use of high-resolution resin materials to finely print each layer of oil paint texture, thereby achieving the oil painting texture of the paper box appearance. However, traditional digital oil painting processing methods usually ignore the impact of ambient lighting on the oil painting effect, resulting in the generated images may lose artistic effect in different display environments. At the same time, the spatial domain optimization of the image is often ignored in the oil painting generation process, resulting in the generated digital oil paintings lacking layering in depth and detail expression, which leads to low authenticity and flexibility of the visual imaging of digital oil paintings. Summary of the invention

[0003] Based on this, it is necessary to provide a visual imaging optimization method and system for digital oil painting to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for optimizing visual imaging of digital oil painting is provided, the method comprising the following steps: Step S1: obtaining an initial oil painting image set; performing digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; performing multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; Step S2: constructing an image pyramid layer for the standard digital oil painting image using the multi-dimensional spatial feature data of the digital oil painting to generate a multi-scale pyramid image; performing regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; optimizing the standard digital oil painting image in the oil painting space domain through the detail enhanced texture layer to generate a digital space domain optimized image; Step S3: collecting ambient light perception data of the digital space domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; performing interactive environmental perception enhancement of the digital space domain optimized image through the ambient light intensity data of the digital oil painting to generate a dynamic adjustment image of the digital oil painting; Step S4: storing the digital oil painting dynamically adjusted image, thereby generating a digital oil painting stored image; performing transmission resolution detection on the digital oil painting stored image, generating digital oil painting transmission resolution data; performing image display resolution constant on the digital oil painting stored image through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; Step S5: Use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining a digital oil painting 3D printed image to perform a paper box manufacturing process operation.

[0005] The present invention obtains the initial oil painting image and performs digital image conversion to ensure that the digitized oil painting image maintains artistic quality and visual authenticity, and extracts multidimensional spatial feature data at the same time, which helps to provide accurate spatial feature information for subsequent image optimization, laying the foundation for digital oil painting processing. By constructing an image pyramid using multidimensional spatial feature data, image processing can be performed from different scales, effectively improving the detail performance of the image. The generation of regional fuzzy separation and detail enhancement texture layers makes the texture and layering of the oil painting richer, and spatial domain optimization enhances the visual depth and realism of the oil painting, avoiding the common problems of flat surface and insufficient details of traditional digital oil paintings. Through the collection of ambient light perception data and the calculation of light intensity, the image can adapt to different ambient light conditions in real time. By dynamically adjusting the digital oil painting image, the color and light and shadow effects of the picture can be maintained under different viewing environments, thereby enhancing the interactivity and environmental adaptability of the image, and avoiding the distortion of the image effect under different display devices or lighting conditions. By detecting the image resolution and processing the constant display resolution, it is ensured that the image will not lose details during storage and transmission, so that it can be displayed with high resolution, clear and detailed effects on different devices, avoiding the problem of blur and distortion of traditional images at low resolution, improving the visual presentation effect of digital oil paintings, and adapting to a wider range of application scenarios. Therefore, the present invention improves the authenticity and flexibility of the visual imaging of digital oil paintings through multi-scale detail enhancement, ambient light perception and high-resolution display optimization.

[0006] Preferably, step S1 comprises the following steps: Step S11: using a camera to obtain an initial oil painting image set; Step S12: performing image cropping on the initial oil painting captured image set to generate an initial captured cropped image set; performing image filtering on the initial captured cropped image set to generate an initial captured filtered image set; Step S13: performing image color balancing on the initial shot filter image set to generate an initial shot balanced image set; performing image contrast adjustment on the initial shot balanced image set to generate a standard oil painting shot image set; Step S14: performing digital image conversion on the standard oil painting image set to generate a standard digital oil painting image; performing multi-dimensional space feature extraction on the standard digital oil painting image to obtain digital oil painting multi-dimensional space feature data.

[0007] The present invention uses a camera to collect the initial image, provides raw data for subsequent image processing, and ensures the authenticity and integrity of the image. Image cropping can remove irrelevant areas, focus on the main part, and improve image quality; image filtering removes noise, improves the clarity and quality of the image, and provides cleaner data for subsequent processing. Image color balance corrects the color deviation caused by lighting or camera equipment to ensure color authenticity; contrast adjustment enhances the visual effect of the image, makes the details of the oil painting more prominent, and improves the visual perception of the image. Through digital image conversion, the oil painting image is converted into a digital format, which is convenient for subsequent computer processing and analysis; multi-dimensional spatial feature extraction reveals the spatial structure and complex details in the image, which is helpful for further image analysis, feature matching and digital oil painting creation. This process provides a complete processing framework for the digitization and optimization of oil painting images. Through cropping, filtering, color balance and contrast adjustment, the quality and accuracy of the image are ensured. Through digital image conversion and multi-dimensional spatial feature extraction, not only the artistic characteristics of the oil painting are retained, but also the foundation for further image processing and analysis is laid.

[0008] Preferably, converting the standard oil painting image into a digital image comprises: Perform multi-perspective image screening on the standard oil painting image set to obtain multi-perspective oil painting images; perform perspective image fusion on the multi-perspective oil painting images to generate full-perspective oil painting images; perform oil painting texture analysis on the full-perspective oil painting fusion images to generate oil painting texture data; The full-view oil painting image is converted into Lab color space through oil painting texture data to generate a digital oil painting color reconstructed image; oil painting brush strokes are simulated on the digital oil painting color reconstructed image to generate digital oil painting brush stroke simulation data; image details of the digital oil painting color reconstructed image are enhanced based on the digital oil painting brush stroke simulation data to generate a standard digital oil painting image.

[0009] The present invention can capture different angles and levels of oil paintings through the screening of multi-view images, and provide rich visual information for subsequent image fusion and analysis, so as to avoid image distortion or detail loss caused by a single view, and improve the comprehensiveness and accuracy of the final digital effect. View image fusion synthesizes images from different viewpoints into a full-view image, avoiding the breakage or inconsistency between the viewpoints. This step enables the digitized oil painting image to more completely present the details and texture of the oil painting, and improves the coherence and realism of the visual performance. The oil painting texture analysis provides key feature data for subsequent digital reconstruction by extracting the surface texture, brushstroke effect and texture of the oil painting. This step retains the artistic characteristics of the oil painting and lays the foundation for the artistic reconstruction of the digital image. Lab color space conversion can more accurately restore the color details in the oil painting, especially in the fidelity of the human eye's perception of color. The Lab space provides a wider range of color representation. This process helps to restore the color depth and layering of the oil painting during digital image reconstruction, making the image more vivid and natural. Oil painting brushstroke simulation can reproduce the direction, thickness and strength of the brushstrokes in oil painting art creation, so that the digital image presents the unique artistic expression effect of oil painting. By simulating the creation process of oil painting, digital images can be made not only accurate in color, but also closer to the texture of real oil paintings in structure and expression. Image detail enhancement can not only enhance the clarity of the image, but also improve the texture and layering of the oil painting. By applying brushstroke simulation data, the details and artistic effects of the image are enhanced, making the final standard digital oil painting image present a richer and more refined visual effect.

[0010] Preferably, step S2 comprises the following steps: Step S21: Decomposing the standard digital oil painting image using the digital oil painting multi-dimensional spatial feature data to generate oil painting scale decomposition data; constructing an image pyramid layer according to the oil painting scale decomposition data to generate a multi-scale pyramid image; Step S22: performing image hierarchical division on the multi-scale pyramid image to generate oil painting hierarchical division data; performing brightness enhancement on the multi-scale pyramid image based on the oil painting hierarchical division data to generate a digital oil painting brightness enhanced image; Step S23: performing local detail region recognition on the digital oil painting brightness enhanced image to obtain local detail region data of the digital oil painting; performing regional fuzzy separation on the digital oil painting brightness enhanced image using the local detail region data of the digital oil painting to generate a detail enhanced texture layer; Step S24: optimizing the standard digital oil painting image in the oil painting space domain through a detail enhancement texture layer to generate a digital space domain optimized image.

[0011] The present invention can help extract different scales and hierarchical information of the image through scale decomposition, and maintain the diversity and details of the image. By constructing an image pyramid, multi-scale image processing can be achieved, thereby improving the detail performance of the digital oil painting image at different levels, avoiding excessive or insufficient detail processing, and ensuring the fineness of the image. Image hierarchical division helps to manage the image in a refined manner, making the processing of each level more targeted. Brightness enhancement improves the visual performance of the image by targetedly adjusting the brightness of different levels, making the light and dark levels of the oil painting image more distinct, enhancing the visual impact and sense of hierarchy, and making the image more vivid and expressive. Local detail area recognition helps to accurately locate the key detail areas in the image and ensure that the details are optimized. Regional fuzzy separation can process different areas in the image, highlight important details, and blur unimportant areas at the same time, avoid visual clutter, and enhance the overall harmonious beauty of the image. The generated detail enhancement texture layer further enhances the artistic sense and expressiveness of the detail area. Oil painting spatial domain optimization further optimizes the spatial structure of the image through the application of detail enhancement texture layers, making the image more coordinated and balanced in space. This step can improve the overall effect of the oil painting image, refine the details of the image, enhance the artistic expression and visual impact, and make the final digital oil painting image more delicate, realistic and artistic.

[0012] Preferably, constructing an image pyramid layer according to the oil painting scale decomposition data includes: Gaussian filtering is performed on the multi-dimensional spatial feature data of the digital oil painting according to the oil painting scale decomposition data to generate oil painting spatial level filtering data; the resolution of the oil painting spatial level filtering data is recursively reduced to generate oil painting spatial resolution recursive levels; the oil painting spatial resolution recursive levels are output at the image level to generate an oil painting fuzzy pyramid image; The oil painting fuzzy pyramid image is subjected to Laplace scale reduction to generate oil painting scale detail data; the oil painting fuzzy pyramid image is subjected to image reconstruction according to the oil painting scale detail data to generate an oil painting detail pyramid image; wherein the formula of Laplace scale reduction is as follows:

[0013] In the formula, Represented as a painting detail pyramid image, Expressed as Layer length is Width Oil painting of blurred pyramid image, Represented as oil painting level, Expressed as Layer length is Width Oil painting of blurred pyramid image, It is indicated as upsampling; The oil painting fuzzy pyramid image and the oil painting detail pyramid image are fused to generate a multi-scale pyramid image.

[0014] The present invention helps to smooth the image through Gaussian filtering, reduce noise and reduce the high-frequency information of the image, retain the basic structure and general features of the image, which provides a clean and smooth foundation for subsequent scale decomposition and pyramid level construction, avoiding the influence of unnecessary noise on details and textures. Recursive resolution reduction can gradually reduce the detail information of the image, thereby generating pyramid images of multiple levels. By recursively reducing the resolution, each level of the image can represent a different scale, so that the digital oil painting presents different levels of expressiveness at different scales, providing a basis for subsequent image reconstruction and detail enhancement. The image level output integrates the images of each layer after recursive resolution reduction into a pyramid image, so that the image maintains a smooth transition between different levels. The fuzzy pyramid image provides a fuzzy image foundation of different scales for subsequent detail extraction and reconstruction, ensuring the consistency and transition of the expression of details at each level. Laplace Pyramid is to extract the details of each layer of image by subtracting the upsampled version of the upper layer image from the current layer image. This process can finely capture the local details of the image (such as brushstrokes, textures, etc.), thereby retaining the artistic expression and fine texture of the oil painting. The generated oil painting scale detail data is very important because it reveals the detailed expression of the oil painting at different scales and provides important information for subsequent reconstruction and fusion. By reconstructing the fuzzy pyramid image using the oil painting scale detail data, the details of each level can be restored, thereby refining the expressiveness of the image. The generation of the detail pyramid image further enhances the texture and brushstroke effect of the oil painting, ensuring that the image has artistic expression depth and delicacy at all levels. Image fusion combines the fuzzy pyramid image and the detail pyramid image, combining the advantages of both: the fuzzy pyramid provides basic structural information at different scales, and the detail pyramid strengthens the presentation of local details. Through this fusion, the final multi-scale pyramid image can present rich details and textures at different levels, while maintaining the integrity and layering of the image, laying the foundation for subsequent image enhancement and optimization.

[0015] Preferably, step S23 includes the following steps: Step S231: Calculate the pixel brightness change rate of the digital oil painting brightness enhanced image to obtain pixel brightness change rate data; perform adjacent pixel brightness difference analysis on the pixel brightness change rate data to generate adjacent pixel brightness difference data; perform oil painting edge area analysis on the digital oil painting brightness enhanced image according to the adjacent pixel brightness difference data to generate oil painting edge area data and oil painting core area data; Step S232: performing region marking on the edge region data and the core region data of the oil painting to generate the edge region marking data and the core region marking data of the oil painting; performing local detail region recognition on the core region marking data of the oil painting to obtain the local detail region data of the digital oil painting; performing edge region chromaticity analysis on the local detail region data of the digital oil painting to generate edge region chromaticity data; Step S233: performing regional texture sharpening on the edge region chromaticity data to generate edge region texture sharpening data; performing detail texture enhancement on the digital oil painting brightness enhanced image using the edge region texture sharpening data to generate oil painting core region texture enhancement data; Step S234: regional texture smoothing is performed on the oil painting edge area marking data to generate oil painting edge area texture blur data; regional layer fusion is performed on the digital oil painting brightness enhanced image through the oil painting core area texture enhancement data and the oil painting edge area texture blur data to generate a detail enhancement texture layer.

[0016] The present invention can effectively identify the edge part and core area in the image by analyzing the pixel brightness change rate and the brightness difference of adjacent pixels. The edge area usually contains the outline and important structural information of the image, while the core area contains more details and textures. This step provides an accurate basis for subsequent regional marking, detail enhancement and regional fusion, and helps to carry out targeted detail processing in different areas, thereby improving the layering of the image. The purpose of regional marking is to clearly distinguish the edge area and the core area of ​​the image, and further improve the accuracy of image processing. Local detail area recognition helps to extract key details (such as brushstrokes, color changes, etc.) in oil paintings, while chromaticity analysis further studies the color characteristics of the edge area so as to optimize the edge area in subsequent processing. This step provides a detailed foundation for detail enhancement, chromaticity adjustment and texture processing. By performing regional texture sharpening on the chromaticity data of the edge area, the detail performance of the edge part of the image can be enhanced, making the image clearer and more powerful, highlighting the layering and three-dimensional sense of the oil painting, and this sharpening process can highlight the details of the edge, making the important elements in the image more vivid, and enhancing the visual impact. At the same time, through detail texture enhancement, the details of the core area of ​​the oil painting can be optimized, making the colors and textures in the image more delicate and rich, and improving the overall artistic expression. Texture smoothing in the edge area can avoid the visual discomfort caused by over-sharpening, making the edge processing more natural, and avoiding hard edges or incoherent visual effects. By fusing the smoothed texture blur data with the detail enhancement data in the core area, a smooth transition between image areas can be achieved, avoiding image incoordination caused by excessive local prominence. The final generated detail enhancement texture layer makes the detail processing of the entire image more balanced and natural, enhancing the artistic sense and realism of the oil painting.

[0017] Preferably, step S3 comprises the following steps: Step S31: collecting ambient light perception data of the digital spatial domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; Step S32: performing a digital oil painting color depth analysis on the digital space domain optimized image to generate digital oil painting color depth data; performing a chromaticity variation range analysis on the digital space domain optimized image according to the digital oil painting color depth data to generate digital oil painting chromaticity variation range data; Step S33: performing oil painting chromaticity gradient adjustment on the digital oil painting chromaticity change data according to the digital oil painting ambient light intensity data, thereby generating an ambient brightness color gradient adjustment strategy; Step S34: using the environment brightness and color gradient adjustment strategy to perform dynamic interactive environment perception enhancement on the digital space domain optimized image to generate a digital oil painting dynamically adjusted image.

[0018] The present invention can accurately evaluate the performance of the image under different ambient lighting conditions through the collection of ambient lighting perception data and the calculation of light intensity, which enables subsequent image adjustments to be optimized according to the actual lighting conditions. Ensure that digital oil paintings show real light and shadow effects under various lighting environments, thereby enhancing the spatial sense and three-dimensional sense of the image. Color depth analysis helps to evaluate the color expression and depth of the image, ensuring that the image can accurately reflect the layering and color richness of the oil painting. Chromaticity variation range analysis further refines color control, making the color changes in the image more natural and expressive, which provides a basis for image detail enhancement and color adjustment, ensuring that the image presents delicate color transitions and rich visual effects. Ambient brightness and chromaticity gradient adjustment can make the color transition of the oil painting image smoother and more natural according to different lighting conditions and color depth data. This adjustment strategy can effectively control the changes in light and shade and color in the image, ensuring that the color of the image will not have unnatural mutations due to changes in lighting. The beneficial effect of this step is to enhance the visual consistency and artistic expression of the image in different environments. Through dynamic interactive environmental perception enhancement, digital oil painting images can respond to lighting changes and color adjustments in real time, making the images more vivid and realistic. This not only improves the artistic expression of the images, but also makes the images more interactive and adaptable, especially in different display environments and lighting conditions, the performance is more flexible and natural.

[0019] Preferably, step S33 includes the following steps: Step S331: performing intensity change time series analysis on the digital oil painting ambient light intensity data to generate light intensity time series change time series data; performing change trend analysis on the light intensity time series change time series data to generate light intensity time series change trend data; Step S332: using the light intensity time series change trend data to divide the digital oil painting ambient light intensity data into light source modes, generating a natural light source mode and an artificial light source mode; performing three primary color gradient adjustment on the digital oil painting chromaticity change data according to the natural light source mode, thereby generating natural light source brightness color gradient adjustment data; Step S333: performing light source hue analysis on the digital oil painting chromaticity change data through an artificial light source mode to generate artificial light source hue analysis data, wherein the artificial light source hue analysis data includes warm-tone light source data and cold-tone light source data; performing red-yellow color component adjustment on the digital oil painting chromaticity change data through the warm-tone light source data to generate artificial light source warm-tone adjustment data; Step S334: adjusting the blue-purple color component of the digital oil painting chromaticity change data through the cold-tone light source data to generate artificial light source cold-tone adjustment data; integrating the artificial light source cold-tone adjustment data and the artificial light source warm-tone adjustment data to generate artificial light source brightness color gradient adjustment data; integrating the natural light source brightness color gradient adjustment data and the artificial light source brightness color gradient adjustment data to generate an environment brightness color gradient adjustment strategy.

[0020] The present invention can capture the temporal changes of light intensity in the image through the time series analysis of intensity changes, which is very important for simulating the changes of natural light sources and artificial light sources. By analyzing the time series trend of light intensity, the change pattern of image illumination under different time points and conditions can be accurately evaluated, providing an important basis for subsequent illumination adjustment and color correction, which helps the image to better adapt to dynamic illumination changes and enhance its expressiveness under different illumination environments. The division of light source modes enables digital oil painting images to be accurately adjusted according to different illumination sources (natural light sources and artificial light sources). The chromaticity gradient adjustment of the three primary colors under the natural light source mode helps to enhance the natural sense and illumination effect of the image, making the oil painting more vivid and realistic in the simulated sunlight or daylight environment. By reasonably adjusting the chromaticity gradient, the brightness and color of the image can transition more naturally, enhancing the spatial sense and texture of the oil painting. Artificial light source hue analysis enables digital oil painting images to adapt to various artificial light source conditions (such as lighting, night lighting, etc.). By adjusting warm tones (such as yellow light) and cold tones (such as white light or blue light), the real effects under different artificial light sources can be simulated. The red-yellow adjustment of warm-toned light sources helps to enhance the warmth and emotional expression of oil painting images, especially when a warm and peaceful atmosphere needs to be presented. The blue-purple adjustment of cool-toned light sources can effectively simulate the cold light effect at night or in a dark environment, which is particularly useful for presenting cold, silent or mysterious scenes. By integrating the adjustment data of warm and cool tones, a more delicate and comprehensive color correction can be provided for the image, making the image color transition under different artificial light conditions more natural and coordinated. By integrating the adjustment strategies of natural and artificial light sources, the final generated environmental brightness color gradient adjustment strategy can adapt to a variety of different lighting environments at the same time. Whether it is the oil painting performance under natural daylight or the effect under indoor artificial light sources, the best color and brightness adjustment can be achieved through this comprehensive strategy. This strategy ensures that the artistic effect of digital oil painting images under different lighting conditions is more consistent, realistic and expressive.

[0021] Preferably, step S4 comprises the following steps: Step S41: performing image rendering on the digital oil painting dynamically adjusted image to generate a digital oil painting rendered image; Step S42: uploading the digital oil painting rendering image to the cloud platform for image storage, thereby generating a digital oil painting storage image; performing transmission resolution detection on the digital oil painting storage image to generate digital oil painting transmission resolution data; Step S43: the image display resolution of the digital oil painting storage image is constant through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image.

[0022] The present invention uses image rendering as a key step in digital oil painting creation. Through rendering processing, digital oil painting images can better present details, textures and color levels. This process ensures that the image can reproduce the texture, lighting and color changes of oil paintings through computer graphics technology, thereby enhancing the visual effect and artistic expression of the image. The rendered image can provide a high-quality foundation for subsequent storage, transmission and display. The rendered digital oil painting image is uploaded to the cloud platform for storage, which is convenient for remote access, sharing and long-term preservation of the image. The storage of the cloud platform not only ensures the security of image data, but also supports large-scale data management and access. Through transmission resolution detection, the transmission quality of the image can be evaluated to ensure that the image during the transmission process will not affect the display effect due to insufficient resolution, which is crucial for the remote display and sharing of high-quality oil painting images. The processing of constant image display resolution ensures that the image can be displayed at high resolution under different devices or different network conditions, avoiding image blur or loss of details caused by insufficient resolution or transmission loss. Through this processing, digital oil painting images can achieve the best display effect on high-definition display screens, projectors or other devices, providing a clearer and more delicate visual experience, which helps to protect the artistic value of the oil painting and ensures that the audience can appreciate every fine stroke and every detail when watching.

[0023] In this specification, a visual imaging optimization system for digital oil painting is provided, which is used to execute the visual imaging optimization method for digital oil painting. The visual imaging optimization system for digital oil painting includes: The spatial feature extraction module is used to obtain an initial oil painting image set; perform digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; perform multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; The spatial domain optimization module is used to construct an image pyramid layer for a standard digital oil painting image using multi-dimensional spatial feature data of a digital oil painting to generate a multi-scale pyramid image; perform regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; perform oil painting spatial domain optimization on the standard digital oil painting image through the detail enhanced texture layer to generate a digital spatial domain optimized image; The environment perception enhancement module is used to collect environment light perception data of the digital space domain optimized image to obtain environment light perception data of the digital oil painting; calculate the environment light intensity of the digital oil painting environment light perception data to generate the digital oil painting environment light intensity data; perform interactive environment perception enhancement of the digital space domain optimized image through the digital oil painting environment light intensity data to generate a digital oil painting dynamically adjusted image; The image storage module is used to store the digital oil painting dynamically adjusted image, thereby generating a digital oil painting storage image; perform transmission resolution detection on the digital oil painting storage image, and generate digital oil painting transmission resolution data; perform image display resolution constant on the digital oil painting storage image through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; The 3D printing module is used to use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining the digital oil painting 3D printing image to perform the paper box manufacturing process operation.

[0024] The beneficial effect of the present invention is that through multi-dimensional spatial feature extraction and image pyramid layer construction, the details of the oil painting image are richer, and the artistic level and texture details of the oil painting can be better expressed. By enhancing the texture layer and optimizing the spatial domain, the oil painting image can be clearer and more vivid while retaining the artistic sense, presenting a more layered effect. By collecting ambient light perception data and calculating the light intensity, the image can be dynamically adjusted according to the actual environmental changes, the naturalness and interactivity of the image are improved, and the viewing experience of the audience under different lighting conditions is more realistic. During the transmission and display process, the high resolution and constant display effect of the image are maintained to avoid the image quality degradation caused by the resolution change. Through the transmission resolution detection and display resolution constant technology, the clarity and detail restoration of the digital oil painting are guaranteed, and the visual effect of the image is improved, especially the performance on large-screen display and high-definition display. This process enables the oil painting image to be personalized and dynamically adjusted on different display platforms (such as display, projector, etc.). According to the ambient light and device characteristics, the brightness, contrast, etc. of the image are automatically optimized to provide a better viewing experience. By using the image storage and transmission resolution detection technology, it is ensured that the digital oil painting image will not lose quality when transmitted under different network conditions, while reducing the storage space occupied and improving the efficiency of data processing. Therefore, the present invention improves the authenticity and flexibility of the visual imaging of digital oil paintings through multi-scale detail enhancement, ambient light perception and high-resolution display optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of the steps of a method for optimizing visual imaging of digital oil paintings; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0029] To achieve this, please refer to Figures 1 to 3 , a visual imaging optimization method for digital oil painting, the method comprising the following steps: Step S1: obtaining an initial oil painting image set; performing digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; performing multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; Step S2: constructing an image pyramid layer for the standard digital oil painting image using the multi-dimensional spatial feature data of the digital oil painting to generate a multi-scale pyramid image; performing regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; optimizing the standard digital oil painting image in the oil painting space domain through the detail enhanced texture layer to generate a digital space domain optimized image; Step S3: collecting ambient light perception data of the digital space domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; performing interactive environmental perception enhancement of the digital space domain optimized image through the ambient light intensity data of the digital oil painting to generate a dynamic adjustment image of the digital oil painting; Step S4: storing the digital oil painting dynamically adjusted image, thereby generating a digital oil painting stored image; performing transmission resolution detection on the digital oil painting stored image, generating digital oil painting transmission resolution data; performing image display resolution constant on the digital oil painting stored image through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; Step S5: Use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining a digital oil painting 3D printed image to perform a paper box manufacturing process operation.

[0030] The present invention obtains the initial oil painting image and performs digital image conversion to ensure that the digitized oil painting image maintains artistic quality and visual authenticity, and extracts multidimensional spatial feature data at the same time, which helps to provide accurate spatial feature information for subsequent image optimization, laying the foundation for digital oil painting processing. By constructing an image pyramid using multidimensional spatial feature data, image processing can be performed from different scales, effectively improving the detail performance of the image. The generation of regional fuzzy separation and detail enhancement texture layers makes the texture and layering of the oil painting richer, and spatial domain optimization enhances the visual depth and realism of the oil painting, avoiding the common problems of flat surface and insufficient details of traditional digital oil paintings. Through the collection of ambient light perception data and the calculation of light intensity, the image can adapt to different ambient light conditions in real time. By dynamically adjusting the digital oil painting image, the color and light and shadow effects of the picture can be maintained under different viewing environments, thereby enhancing the interactivity and environmental adaptability of the image, and avoiding the distortion of the image effect under different display devices or lighting conditions. By detecting the image resolution and processing the constant display resolution, it is ensured that the image will not lose details during storage and transmission, so that it can be displayed with high resolution, clear and detailed effects on different devices, avoiding the problem of blur and distortion of traditional images at low resolution, improving the visual presentation effect of digital oil paintings, and adapting to a wider range of application scenarios. Therefore, the present invention improves the authenticity and flexibility of the visual imaging of digital oil paintings through multi-scale detail enhancement, ambient light perception and high-resolution display optimization.

[0031] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a visual imaging optimization method for digital oil painting of the present invention. In this example, the visual imaging optimization method for digital oil painting includes the following steps: Step S1: obtaining an initial oil painting image set; performing digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; performing multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; In an embodiment of the present invention, the oil painting is photographed by using a high-resolution digital camera or a professional digital scanner. During the acquisition process, the lighting should be ensured to be uniform to avoid shadows affecting the shooting quality. The same oil painting is photographed at multiple angles and multiple lighting environments to facilitate multi-angle reconstruction of the image in the later stage. Special software or equipment is used to evaluate the image quality to ensure that the resolution and detail clarity of the image meet the requirements. The collected oil painting images are standardized, including removing noise, adjusting brightness and contrast, and automatically cutting out the oil painting part. If a scanner is used, the focus and resolution are automatically adjusted during the scanning process to ensure the clarity and true restoration of the image. The image obtained by shooting or scanning is converted from the original format (such as JPEG, TIFF, etc.) to a standard digital format, such as PNG or high-quality TIFF format, to retain the details of the image. Use an image processing algorithm to remove noise from the original image and perform image sharpening to ensure that the details are more prominent. Convert the RGB color space to a color space more suitable for oil painting (such as Lab color space or HSV color space) to more accurately enhance and adjust the color. Through the color enhancement algorithm, the color layering of the oil painting is enhanced, so that the image shows the heavy feeling and artistic style of the oil painting. Use the image style conversion algorithm (such as image style transfer in deep learning) to process the digital image into an image with the style of oil painting, simulating the unique brush traces and texture effects of oil painting. This step can apply a specific convolutional neural network (CNN) model to learn the texture features of oil painting and perform style transfer. Use computer vision methods such as SIFT (scale-invariant feature transform) or SURF (speeded up robust features) to detect key points of the image and extract spatial feature points in the image. Perform local area analysis on the oil painting image to extract the spatial morphological features of the image, such as edges, curves, textures, etc. Extract the multi-dimensional spatial features of the image such as color, texture, shape, etc., establish feature vectors, and form the multi-dimensional spatial feature data of the digital oil painting. Dimensionality reduction techniques such as principal component analysis (PCA) can be used to compress the multi-dimensional feature data to a lower dimension for subsequent analysis and processing. Different feature extraction methods need to be designed for different painting styles or different shooting angles to adapt to the feature diversity of different types of oil paintings. Use deep learning techniques such as convolutional neural networks (CNN) to automatically extract higher-level abstract features from digital oil painting images, such as brush strokes, smear thickness, light reflection, etc. By training the neural network model, it can automatically learn spatial features with artistic characteristics from a large number of oil painting images.

[0032] Step S2: constructing an image pyramid layer for the standard digital oil painting image using the multi-dimensional spatial feature data of the digital oil painting to generate a multi-scale pyramid image; performing regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; optimizing the standard digital oil painting image in the oil painting space domain through the detail enhanced texture layer to generate a digital space domain optimized image; In the embodiment of the present invention, by using standard digital oil painting images as input, these images should be high-quality oil painting images processed by convolutional neural network (CNN). The image is usually a high-resolution image, such as 256x256 or 512x512. The construction of the Gaussian pyramid is to obtain images of different scales by gradually performing Gaussian blurring and downsampling on the image. The image resolution of each layer will decrease, containing less and less details. Starting from the original image, the image is smoothed using a Gaussian filter, and the next layer of image is generated by downsampling (for example, the size of the image is reduced to half of the original size each time). Usually 3-5 layers of pyramids are generated. The Laplacian pyramid extracts the details of the image by calculating the difference between two adjacent layers of the Gaussian pyramid images, and can highlight the edges and detail information of the image. For each layer of the pyramid, it is subtracted from the upsampling result of the next layer to obtain the Laplacian detail image of the layer. The images of each layer of the Gaussian pyramid and the Laplacian pyramid are combined to obtain image representations of different scales, which are used for subsequent blur processing and detail enhancement. The image can be divided into regions by the spatial feature data of the image (such as color, texture, shape, etc.). Different regions can be segmented based on the color distribution, texture features, or depth information of the image. After region separation, the background region is Gaussian blurred to make it smooth, while the detail-related regions in the image are retained for high precision. Different degrees of blur are applied to each region of the image, usually with a stronger blur on the background region and a lighter blur on the foreground or detail region. Different regions can be identified by edge detection. Using methods such as Gaussian blur and bilateral filtering, the background region in the image is gradually blurred while the details remain sharp. The detail layer of the Laplacian pyramid is used to enhance the details after the region blur separation. The detail layer and the blurred image can be fused by weighted superposition. Emphasize the texture features of the detail area, such as brush strokes, smear thickness, light reflection, etc. The detail enhancement texture layer is fused with the original image to enhance the texture of the oil painting through the effect of detail enhancement. This operation is based on the results of the image pyramid and the region blur separation, and weighted fusion of different scales and details is performed. For the local details of the oil painting, the weighted average method is applied to fuse the detail layer to ensure that a high resolution is retained in the detail area while avoiding over-enhancement. By adjusting the detail enhancement texture layer, the spatial distribution in the image is optimized, especially the details of lighting and texture. This can be achieved through local contrast enhancement, local sharpening and other methods. The illumination distribution in the spatial domain is optimized using methods such as histogram equalization, making the light and dark contrast in the oil painting image more natural and delicate. The optimized image is combined with the original image, and the weighted overlay or adaptive fusion method is used to generate the final digital spatial domain optimized image, which enhances the spatial effect, texture and layering of the oil painting.

[0033] Step S3: collecting ambient light perception data of the digital space domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; performing interactive environmental perception enhancement of the digital space domain optimized image through the ambient light intensity data of the digital oil painting to generate a dynamic adjustment image of the digital oil painting; In an embodiment of the present invention, a physical model based on illumination is constructed by utilizing the brightness information and spatial features of an image. Common models include the Phong model, the Blinn-Phong model, or the Cook-Torrance model, which simulate the influence of illumination by using information such as material reflection, light source direction, and surface normal. The surface normal (obtained by previous image processing or depth information) and the light source direction are used to calculate the local illumination on the surface. The brightness value of each pixel is extracted from the digital oil painting optimized image, and the ambient illumination perception data can be collected by combining the direction information of the light source (assuming it is known or obtained through image analysis). The ambient illumination contribution of each pixel in the image is calculated, and information such as illumination intensity, direction, and illumination distribution is recorded. The ambient light intensity is calculated by a formula, for example, using an ambient light intensity model, which includes factors such as background illumination intensity, light source directionality, and object surface reflectivity. By combining the standardized image brightness value and the known ambient illumination information, the ambient light intensity of each pixel can be calculated. The image can be weighted averaged to summarize the local illumination information into a global ambient light intensity data representing the illumination effect of the entire oil painting. Using the calculated ambient light intensity data, the brightness and contrast of the image can be adjusted according to the actual lighting environment. By enhancing the highlight area or adjusting the shadow area, the lighting of the oil painting image can be richer and the layers can be more distinct. Use technologies such as gamma correction or local contrast enhancement (such as CLAHE) to dynamically adjust the lighting effect of the image to make it more consistent with the ambient light intensity. Apply an enhancement algorithm based on ambient light intensity to local areas of the image (such as highlight areas and shadow areas). According to the calculation results of the ambient light intensity, adjust the brightness, color saturation or contrast of these areas to make the overall image more artistic. Allow users to adjust the ambient light intensity through interactive methods (such as through the UI interface or real-time calculation) to achieve real-time changes in the image lighting effect. For example, the effect of different light source angles or intensities on oil paintings can be simulated to generate different oil painting lighting effects. In practical applications, this interactivity can be combined with virtual reality (VR) or augmented reality (AR) to achieve dynamic adjustment. Ultimately, through lighting perception enhancement, local adjustment and interactive optimization of the image, the generated digital oil painting image will show an effect that is more in line with actual lighting conditions, enhancing its artistry and sense of space.

[0034] Step S4: storing the digital oil painting dynamically adjusted image, thereby generating a digital oil painting stored image; performing transmission resolution detection on the digital oil painting stored image, generating digital oil painting transmission resolution data; performing image display resolution constant on the digital oil painting stored image through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; In an embodiment of the present invention, a suitable image storage format is selected to ensure the quality of the stored image. For example, a lossless compression format (such as TIFF, PNG) can be used to store digital oil painting images to ensure that the original image quality is preserved. If lossy compression is required (for example, in network transmission), the JPEG format can be selected, but the compression ratio should be reasonably set to avoid loss of image quality. The dynamically adjusted image is saved as a digital oil painting storage image. It can be selected to store multiple resolution image versions so that it can be adjusted according to transmission and display requirements. By detecting the resolution of the image, the width and height of the image are obtained. The image resolution can be determined by using the metadata of the image or directly reading the image size information. For different transmission requirements, different resolution ranges can be preset for adaptive transmission. For example, a lower resolution image can be transmitted under low bandwidth conditions, while a high resolution image can be transmitted under high bandwidth. The image resolution is calculated, and the digital oil painting transmission resolution data is generated according to the set rules. The data may include information such as image width, image height, compression rate, and bandwidth required for transmission. The resolution of the image can be dynamically adjusted according to the requirements of the transmission bandwidth or the display device. At this time, the image quality and transmission speed are balanced by changing the image resolution. The resolution of the user device or display device needs to be detected to determine the optimal resolution for displaying images on the device. The device resolution can be obtained through the system API (such as GetDeviceCaps in Windows or display settings in Linux). Adjust the resolution of the image according to the resolution of the display device. On a display device with a lower resolution, adjust the image to the optimal display resolution through image interpolation technology (such as bilinear interpolation, cubic interpolation, etc.) to ensure that the display effect is not distorted. Ensure that the image has a constant high-resolution performance when displayed through image interpolation or lossless compression technology. Even on a low-resolution display device, a high-quality display effect can be generated through an interpolation algorithm. Use detail enhancement technology (for example, through local contrast enhancement or sharpening algorithms) during display to further optimize the visual effect of the image, especially when displayed on a low-resolution device. Through the above steps, the final image will be displayed at a constant high resolution on the display device, and the image quality can be maintained or optimized under different transmission bandwidth or storage limitations.

[0035] Step S5: Use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining a digital oil painting 3D printed image to perform a paper box manufacturing process operation.

[0036] In an embodiment of the present invention, a high-resolution image is obtained from a digital oil painting file (e.g., in TIFF, PNG, or JPEG format). The image should include rich details and be able to fully display the brushstrokes, color transitions, and layering of the oil painting. A computer vision algorithm is used to analyze the high-resolution digital oil painting image to extract information such as color and texture. A three-dimensional height map (usually using the grayscale value of the image as the height) is generated through deep learning or image processing technology to convert the plane image into a three-dimensional model that can be used for 3D printing. Using 3D modeling software (such as Blender, ZBrush, etc.) or a dedicated image-to-3D conversion tool, each element in the image (such as color, texture) is mapped to a three-dimensional space to create a three-dimensional effect model of the oil painting. According to the printing requirements, a suitable printing material, such as resin, plastic, or metal, is selected to retain details and provide the required firmness during the printing process. For the layering of the oil painting, it is necessary to select a high-resolution material (such as a photosensitive resin) that can be finely printed for 3D printing. According to the specifications of the 3D printer, prepare the printer and perform necessary calibration to ensure printing accuracy and quality. The generated three-dimensional model is printed out using a 3D printer (such as FDM, SLA or SLS technology). A multi-level printing strategy can be adopted to print out different details of the oil painting layer by layer to simulate the texture and layering of the oil painting. Each layer of printing may correspond to a certain detailed area of ​​the oil painting. Make sure to control the resolution and layer thickness of the printing during the printing process to achieve rich details and clear layers. After printing, post-processing is required, such as removing support structures, sanding, coloring, coating, etc., to further optimize the printing effect and make it closer to the visual effect of the original oil painting. The oil effect of the oil painting can be imitated by adding a coating or using paint to color the model. Different paints and gloss coatings can be used, and even simulated oil painting brushstrokes can be used to ensure that the three-dimensional imaging is consistent with the original oil painting in color, texture and gloss. The resulting digital oil painting 3D printed imaging will be directly integrated into the manufacturing process of the carton as a design element of the carton. It can be used as a surface decoration or applied to the carton structure design through more complex modeling to give the carton a unique artistic appearance.

[0037] Preferably, step S1 comprises the following steps: Step S11: using a camera to obtain an initial oil painting image set; Step S12: performing image cropping on the initial oil painting captured image set to generate an initial captured cropped image set; performing image filtering on the initial captured cropped image set to generate an initial captured filtered image set; Step S13: performing image color balancing on the initial shot filter image set to generate an initial shot balanced image set; performing image contrast adjustment on the initial shot balanced image set to generate a standard oil painting shot image set; Step S14: performing digital image conversion on the standard oil painting image set to generate a standard digital oil painting image; performing multi-dimensional space feature extraction on the standard digital oil painting image to obtain digital oil painting multi-dimensional space feature data.

[0038] In the embodiment of the present invention, a high-resolution digital SLR camera or professional oil painting shooting equipment is selected to ensure that the image details and color reproduction are high. The oil painting is photographed under good natural light or artificial lighting conditions to avoid shadows and overexposure to ensure the clarity of the image and the accuracy of the color. The ISO, aperture and shutter speed of the camera are adjusted to obtain a clear image and proper exposure to ensure that the captured image meets the post-processing requirements. According to the required image part, the central area or specific detail area of ​​the oil painting is selected for cropping to remove unnecessary background. Image editing software (such as Adobe Photoshop) or an automated image processing algorithm is used for cropping to ensure that the selected area size is consistent. Algorithms such as Gaussian filtering and mean filtering are used to remove noise in the image to ensure image clarity. According to the style of the oil painting, an appropriate filter can be selected to enhance the texture and details of the oil painting. According to the actual tone of the oil painting, the color temperature of the image is adjusted so that the color of the image is consistent with the tone of the actual oil painting. Use the automatic color balance tool or manually adjust the RGB channels to ensure the true restoration of the image color. Adjust the brightness and contrast through the image processing software to make the details in the image more prominent, which is in line with the expressiveness of the oil painting. Use the Levels or Curves adjustment tools to make the highlights and shadows of the image distinct and enhance the visual effect. Convert the standard oil painting image set into a format suitable for digital processing, such as JPEG, TIFF or RAW format, to ensure high-quality image storage. Convert the image from the RGB color space to CMYK or other color models (if necessary) for higher-quality digital processing. Use wavelet transform, Gabor filtering and other methods to extract the texture features of the oil painting and capture its brushstrokes, smears and other details. Use image segmentation, edge detection and other techniques to extract the spatial layout, shape and structural features in the image, such as the outline of the object, spatial hierarchy, etc. The overall characteristics of the digital oil painting are obtained by calculating the statistical features of the image, such as the mean, standard deviation, skewness, etc.

[0039] Preferably, converting the standard oil painting image into a digital image comprises: Perform multi-perspective image screening on the standard oil painting image set to obtain multi-perspective oil painting images; perform perspective image fusion on the multi-perspective oil painting images to generate full-perspective oil painting images; perform oil painting texture analysis on the full-perspective oil painting fusion images to generate oil painting texture data; The full-view oil painting image is converted into Lab color space through oil painting texture data to generate a digital oil painting color reconstructed image; oil painting brush strokes are simulated on the digital oil painting color reconstructed image to generate digital oil painting brush stroke simulation data; image details of the digital oil painting color reconstructed image are enhanced based on the digital oil painting brush stroke simulation data to generate a standard digital oil painting image.

[0040] In an embodiment of the present invention, a high-resolution camera or scanner is used to shoot from multiple perspectives. Multiple angles are selected for shooting, such as the front, side, and oblique surfaces, so as to obtain the details of the oil painting from different perspectives. Images that meet the quality requirements are screened out from the acquired image set, and low-quality images caused by factors such as light and focus are removed. Multi-perspective images are fused using image stitching technology (such as image stitching based on feature point matching, panoramic stitching, and other methods). Image feature points are extracted and matched by algorithms such as SURF, SIFT, or ORB to achieve seamless stitching. Color matching, exposure adjustment, and other technologies are used to ensure that the transition of image stitching is natural and rich in details. Image fusion algorithms (such as Laplace pyramid fusion) are used to reduce stitching traces and enhance the continuity and realism of the image. Wavelet transform, Gabor filtering, gray level co-occurrence matrix (GLCM), and other methods are used to analyze the texture features of the image. Local texture, surface roughness, brushstroke direction, detail level, and other information of the image are extracted. Through statistical analysis, the texture data of the image is extracted to generate a texture feature set of the digital oil painting, such as the size, shape, density, and direction of the brushstroke. The texture data is converted into parameters and descriptors that can be used in subsequent steps. The fused full-view oil painting image is converted from the RGB color space to the Lab color space. The Lab color space has better color perception and is suitable for accurate color processing. The color space conversion formula is used: L=0.2126R+0.7152G+0.0722B; where L is the lightness, and A and B are the color difference components. Based on the oil painting texture data, the color difference components (A and B) in the Lab space are adjusted to restore the color of the oil painting to make it closer to the performance of the real oil painting. The color correction algorithm is used to ensure the natural transition and delicate performance of the color. The image processing algorithm is used to simulate the oil painting brushstroke effect. For example, the brushstroke generation algorithm based on local texture and color information is used to simulate the heavy brushstrokes and brush strokes in real oil paintings. Different brush styles in oil paintings (such as thin brushstrokes, thick brushstrokes, etc.) are simulated through artificial intelligence or deep learning technology. The simulated brushstroke information is extracted, including the size, direction, thickness, and smearing method of the brushstroke. The simulated brushstroke effect data is applied to the image to generate a more detailed performance with a sense of oil painting. Use image enhancement technology (such as local contrast enhancement, edge enhancement, etc.) to enhance the details of oil paintings, enhance light and shadow effects, layering and brushstroke details. According to the brushstroke simulation data, adjust the details of local areas to make them more in line with the expressiveness of oil paintings. Optimize the details of oil paintings, especially in the processing of textures and brushstrokes, increase the layering and visual impact. Use image sharpening, noise control and other technologies to further improve the quality of the image, making it more in line with the artistic effect of digital oil paintings.

[0041] As an example of the present invention, refer to Figure 2As shown, in this example, step S2 includes: Step S21: Decomposing the standard digital oil painting image using the digital oil painting multi-dimensional spatial feature data to generate oil painting scale decomposition data; constructing an image pyramid layer according to the oil painting scale decomposition data to generate a multi-scale pyramid image; Step S22: performing image hierarchical division on the multi-scale pyramid image to generate oil painting hierarchical division data; performing brightness enhancement on the multi-scale pyramid image based on the oil painting hierarchical division data to generate a digital oil painting brightness enhanced image; Step S23: performing local detail region recognition on the digital oil painting brightness enhanced image to obtain local detail region data of the digital oil painting; performing regional fuzzy separation on the digital oil painting brightness enhanced image using the local detail region data of the digital oil painting to generate a detail enhanced texture layer; Step S24: optimizing the standard digital oil painting image in the oil painting space domain through a detail enhancement texture layer to generate a digital space domain optimized image.

[0042] In an embodiment of the present invention, a standard digital oil painting image is decomposed by using multi-scale analysis techniques (such as wavelet transform, multi-scale Retinex, Laplacian pyramid, etc.). Through these algorithms, the image can be decomposed at different scale levels to extract detail information at different resolutions. By extracting the spatial feature data (such as texture, edge, color change, etc.) of the digital oil painting image, it is analyzed at multiple scale levels. Each scale level will contain different details of the image, such as rough outlines, delicate textures, etc. According to the scale decomposed data, a pyramid construction algorithm (such as a Gaussian pyramid or a Laplacian pyramid) is used to create image layers of different scales. Each level contains information of different resolutions extracted from the original image. From the original image to the minimum resolution image, a multi-level image pyramid is constructed. The resolution of each level image gradually decreases in the spatial scale, but it can retain important structural and texture information. The pyramid image is layered using a hierarchical division method (such as K-means clustering, image segmentation algorithm or feature-based hierarchical division technology). Each level contains different image details (coarse, fine, etc.). Assign a weight or label to each level of image to indicate its importance or level of detail. These division data will be used for specific brightness and detail adjustments in subsequent enhancement steps. Based on the oil painting level division data, brightness enhancement is performed for different image levels. At the image level with lower resolution, the visual effects such as brightness and contrast of the image are enhanced, while the accuracy of details is maintained at the level with higher resolution. Use brightness enhancement algorithms (such as histogram equalization, gamma correction or adaptive brightness adjustment, etc.) to enhance the brightness of different levels, so that the overall brightness of the image is more balanced and the details are more prominent. Use edge detection techniques (such as Canny edge detection, Sobel operator, etc.) to identify local detail areas in the image, which are usually areas where the oil painting brushstrokes are more obvious or the local texture is more delicate. Combined with texture analysis, local illumination and other information, identify areas with high details, such as subtle brushstrokes and shadow transitions in oil paintings. Use regional blur algorithms (such as Gaussian blur, mean blur, bilateral filtering, etc.) to blur the detail areas in the image. Through regional selection, the local details remain clear, while the remaining areas are blurred to reduce unnecessary texture noise. The blurred area is superimposed on the original image as a separate layer. The fine texture of the painting is highlighted by the detail enhancement texture layer without affecting the overall image structure. The standard digital painting image is further processed using a spatial domain optimization algorithm. Methods such as bilateral filtering, local contrast enhancement or adaptive filtering can be used to optimize the spatial structure in the image, especially to enhance the details. The detail enhancement texture layer is combined with the original image, and the influence of different layers on the image is controlled by weights, thereby improving the local detail of the image while ensuring that the overall spatial structure is not destroyed.Use detail enhancement texture layers to further enhance the oil painting texture of the image, such as by simulating the roughness of brushstrokes, pen tip details, etc., to enhance the handmade artistic effect of the image. The optimized digital oil painting image should show a more realistic oil painting style, retain the layering and details of the oil painting, and maintain natural lighting and shadow effects.

[0043] Preferably, constructing an image pyramid layer according to the oil painting scale decomposition data includes: Gaussian filtering is performed on the multi-dimensional spatial feature data of the digital oil painting according to the oil painting scale decomposition data to generate oil painting spatial level filtering data; the resolution of the oil painting spatial level filtering data is recursively reduced to generate oil painting spatial resolution recursive levels; the oil painting spatial resolution recursive levels are output at the image level to generate an oil painting fuzzy pyramid image; The oil painting fuzzy pyramid image is subjected to Laplace scale reduction to generate oil painting scale detail data; the oil painting fuzzy pyramid image is subjected to image reconstruction according to the oil painting scale detail data to generate an oil painting detail pyramid image; wherein the formula of Laplace scale reduction is as follows:

[0044] In the formula, Represented as a painting detail pyramid image, Expressed as Layer length is Width Oil painting of blurred pyramid image, Represented as oil painting level, Expressed as Layer length is Width Oil painting of blurred pyramid image, It is indicated as upsampling; The oil painting fuzzy pyramid image and the oil painting detail pyramid image are fused to generate a multi-scale pyramid image.

[0045] In an embodiment of the present invention, the multi-dimensional spatial feature data of the digital oil painting is smoothed by using a Gaussian filter. Specifically, a two-dimensional Gaussian filter is applied to convolve the oil painting image, aiming to reduce the noise and details of the image and retain relatively smooth regional features. After applying the filter, the image obtained is the spatial hierarchical filtering data of the oil painting, and the smaller detail information in the image is smoothly removed, leaving the main structure and texture information. A pyramid algorithm (such as a Gaussian pyramid) is used to gradually reduce the resolution of the image to obtain image hierarchies of different scales. Each time the resolution is recursively reduced, the size of the image will be reduced, for example, by reducing the size of the image by half each time (half in the horizontal and vertical directions), so as to generate different image hierarchies. For each layer, its size is recursively reduced until the required minimum scale is reached. Each layer of the output image will represent a spatial hierarchy from a lower resolution to a higher resolution, gradually approaching the full picture of the image, while also reducing the detail information in the image. After recursively reducing the resolution, a group of images of different scales will be obtained. The image at each scale will represent the blur effect of that level. These images with reduced resolution are output as different levels of the pyramid, that is, a blurred pyramid image of the oil painting is generated. The blur degree of each layer of the image depends on its resolution and the degree of reduction. By combining the images of each resolution level according to their corresponding pyramid structure, a complete blur pyramid is finally generated. The Laplacian pyramid data of each image level is calculated. The generation of the Laplacian pyramid is achieved by subtracting the upsampling result of the Gaussian image of the current level from the Gaussian image of the upper level. The formula of Laplacian scale reduction is as follows: ; In the formula, Represented as a painting detail pyramid image, Expressed as Layer length is Width Oil painting of blurred pyramid image, Represented as oil painting level, Expressed as Layer length is Width Oil painting of blurred pyramid image, Represented as upsampling; each level of the Laplacian pyramid represents the detail information of the original image at that scale, emphasizing high-frequency information such as edges and texture details. Recombining the data of the Laplacian pyramid levels to restore the details of the painting. Image reconstruction is achieved by adding the Laplacian detail data of each layer to the upsampled Gaussian pyramid image layer by layer. Fusion of the oil painting blur pyramid image with the oil painting detail pyramid image. Through weighted fusion or other fusion algorithms, the blur information and detail information of different scales are combined to preserve the blurred background and detailed texture of the image. Fusion is performed according to the weights of different levels, for example, the detail information of a higher resolution level can be combined with the blur information of a lower resolution level. Through the fused multi-scale information, an image pyramid structure with rich details and blur levels is finally obtained, ensuring that the artistic sense and detail levels of the oil painting are effectively expressed.

[0046] Preferably, step S23 includes the following steps: Step S231: Calculate the pixel brightness change rate of the digital oil painting brightness enhanced image to obtain pixel brightness change rate data; perform adjacent pixel brightness difference analysis on the pixel brightness change rate data to generate adjacent pixel brightness difference data; perform oil painting edge area analysis on the digital oil painting brightness enhanced image according to the adjacent pixel brightness difference data to generate oil painting edge area data and oil painting core area data; Step S232: performing region marking on the edge region data and the core region data of the oil painting to generate the edge region marking data and the core region marking data of the oil painting; performing local detail region recognition on the core region marking data of the oil painting to obtain the local detail region data of the digital oil painting; performing edge region chromaticity analysis on the local detail region data of the digital oil painting to generate edge region chromaticity data; Step S233: performing regional texture sharpening on the edge region chromaticity data to generate edge region texture sharpening data; performing detail texture enhancement on the digital oil painting brightness enhanced image using the edge region texture sharpening data to generate oil painting core region texture enhancement data; Step S234: regional texture smoothing is performed on the oil painting edge area marking data to generate oil painting edge area texture blur data; regional layer fusion is performed on the digital oil painting brightness enhanced image through the oil painting core area texture enhancement data and the oil painting edge area texture blur data to generate a detail enhancement texture layer.

[0047] In an embodiment of the present invention, the brightness of each pixel in the digital oil painting brightness enhancement image is calculated. The gray value of the image is used as a brightness metric to calculate the brightness change rate between adjacent pixels. Assuming that the brightness value in the image is I(x, y), the brightness change rate of two adjacent pixels can be defined as: R(x, y)=I(x, y)−I(x+1, y); wherein R(x, y) is the pixel brightness change rate, and I(x, y) is the brightness value of the pixel position (x, y). By traversing each pixel in the image, the pixel brightness change rate data is calculated to obtain an image reflecting the brightness change. The brightness change rate of each pixel is analyzed for differences, with particular attention paid to areas with large or small brightness changes. Using threshold segmentation technology, the image can be divided into "high difference" and "low difference" areas. By calculating the average or standard deviation of the brightness difference of adjacent pixels, the brightness difference data of adjacent pixels of the image is obtained. Based on the brightness difference data of adjacent pixels, the image is processed using an edge detection algorithm (such as Canny edge detection) to identify the edge area in the image. The edge area usually corresponds to the part with large brightness change in the image. The edge strength of the image is calculated using a gradient operator (such as the Sobel operator), and a threshold is set. The area above the threshold is determined as the edge area. The core area is the area outside the edge area, which usually has a small brightness change and a relatively uniform texture. This can be achieved by defining the non-edge area in the image as the core area. Output the oil painting edge area data and the oil painting core area data, which represent the high-contrast and low-contrast areas in the image, respectively. Use an image segmentation algorithm (such as the connected domain labeling algorithm) to label the edge area and the core area. Each connected pixel will be assigned a unique label to generate the oil painting edge area labeling data and the oil painting core area labeling data, which represent the pixel positions marked as the edge and core areas in the image, respectively. By analyzing the local texture features of the core area of ​​the oil painting (such as texture direction, texture roughness, etc.), the detail area that needs further processing is identified. The local texture analysis algorithm (such as Gabor filtering, LBP, etc.) can be used to extract local texture features. Identify and mark the local detail area in the image to prepare for subsequent color analysis and texture enhancement. Perform color analysis on the edge area in the image, paying special attention to the hue, saturation and brightness of the edge. The image can be converted from RGB color space to Lab color space to better analyze the chromaticity features. In the Lab color space, extract the chromaticity information in the L, a, and b channels, and calculate the chromaticity features of the edge area. C(x, y) = (a(x, y), b(x, y)), where C(x, y) is the chromaticity data of the edge area, a(x, y) and b(x, y) are the a channel and b channel values ​​of the point in the image, respectively, to obtain the chromaticity data of the edge area for subsequent texture sharpening. Sharpen the chromaticity data of the edge area to enhance the texture features of the edge area. Sharpening can be achieved using the Laplacian operator or a high-pass filter.S(x, y) = C(x, y) + λ⋅HighPass(C(x, y)); where S(x, y) is the texture data of the edge area after sharpening, and λ is a parameter that controls the degree of sharpening. The texture sharpening data of the edge area is fused with the brightness enhanced image to enhance the details in the image. Texture is enhanced using weighted average or other synthesis methods. The edge area is smoothed to reduce the unnatural feeling caused by over-sharpening. Gaussian blur or other smoothing algorithms can be used to process the edge area. Layer fusion is performed using the texture enhancement data of the core area of ​​the painting and the texture blur data of the edge area of ​​the painting. Fusion techniques such as weighted average and Laplace pyramid can be used to balance the detail enhancement and smoothing effects of the image to obtain the final detail enhanced texture layer, providing detail enhancement effects for the final display of the digital painting.

[0048] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: collecting ambient light perception data of the digital spatial domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; Step S32: performing a digital oil painting color depth analysis on the digital space domain optimized image to generate digital oil painting color depth data; performing a chromaticity variation range analysis on the digital space domain optimized image according to the digital oil painting color depth data to generate digital oil painting chromaticity variation range data; Step S33: performing oil painting chromaticity gradient adjustment on the digital oil painting chromaticity change data according to the digital oil painting ambient light intensity data, thereby generating an ambient brightness color gradient adjustment strategy; Step S34: using the environment brightness and color gradient adjustment strategy to perform dynamic interactive environment perception enhancement on the digital space domain optimized image to generate a digital oil painting dynamically adjusted image.

[0049] In an embodiment of the present invention, ambient light perception is performed based on the light source information and texture details in the image. A deep learning model (such as a convolutional neural network) can be used to extract the distribution and direction of light in the image, or a traditional image processing method (such as an optical flow method, a light estimation algorithm, etc.) can be used. The ambient light perception data of each pixel is obtained by calculating the intensity distribution of light in each area of ​​the image. For each pixel I (x, y) in the image, the light intensity L (x, y) of the surrounding area is calculated, and the ambient light perception data is output based on the light distribution pattern of the image. L (x, y) = f (I (x, y)); wherein f (I (x, y)) is an estimation function of light intensity, which can be estimated according to the grayscale, texture or color change of the image to obtain the ambient light perception data of the digital oil painting, reflecting the light intensity of each area in the image, which will be used to calculate the adjustment of light intensity and chromaticity later. The color depth of a digital oil painting refers to the richness of the colors in the image. When performing color depth analysis on a digital spatial domain optimized image, the color level of the image can be evaluated using the chromaticity and saturation indicators of the color space. Use Lab color space or HSV color space for color depth analysis, calculate the chroma and saturation of each pixel, and generate the color depth data of the image. Color depth formula (taking HSV as an example): D(x, y) = S(x, y) = 1- (min(R, G, B) ÷ max(R, G, B)); where S(x, y) is the saturation (color depth index), and R, G, and B are the RGB values ​​of a pixel in the image. Based on the above analysis, the color depth data of the digital oil painting is obtained to describe the richness and layering of the colors in the image. According to the color depth data, the range of chromaticity changes in the image is analyzed. By analyzing the color changes in different areas of the image, it is determined which areas have a larger chromaticity range and which areas have a smaller chromaticity change. The range of chromaticity can be calculated using the color difference of the image. For example, in the HSV color space, the chromaticity distribution range (ΔH) and saturation change range (ΔS) of each area are calculated. By calculating the chromaticity change range of each area of ​​the image, the chromaticity change range data is obtained to reflect the distribution of color changes in the image. R=max(H(x, y))−min(H(x, y)); where R represents the chromaticity variation range, and H(x, y) is the hue value of a pixel in the image. Use the digital oil painting ambient light perception data (i.e., light intensity data) and chromaticity variation range data to adjust the chromaticity gradient of the oil painting. Based on the areas with lower light intensity in the image, the saturation and brightness of the color can be increased to make these areas brighter and more layered; while in areas with stronger light, the saturation and brightness of the color can be reduced to maintain a natural visual effect. C′(x, y)=C(x, y)×(1+α⋅L(x, y)); where C′(x, y) is the adjusted color value, C(x, y) is the original color value, L(x, y) is the ambient light intensity, and α is the adjustment coefficient.Combined with the illumination distribution and chromaticity changes of the image, a color gradient adjustment strategy is generated to guide how to adjust the color and brightness of different areas to enhance the overall visual effect. Based on the ambient brightness color gradient adjustment strategy, the digital spatial domain optimized image is dynamically and interactively enhanced. By combining the ambient lighting perception data of the image, real-time adjustments are made to make the brightness, color, and texture of the image more natural and realistic under different lighting conditions. This step can be achieved by using interactive image editing tools or rendering engines, allowing users to adjust different areas of the image to make it more in line with the desired visual effect. Combining the adjustment strategies of all the above steps, the final digital oil painting dynamic adjustment image is generated. This image will show the color and brightness effects after environmental perception enhancement, making it more vivid and delicate, in line with the performance of oil painting style.

[0050] Preferably, step S33 includes the following steps: Step S331: performing intensity change time series analysis on the digital oil painting ambient light intensity data to generate light intensity time series change time series data; performing change trend analysis on the light intensity time series change time series data to generate light intensity time series change trend data; Step S332: using the light intensity time series change trend data to divide the digital oil painting ambient light intensity data into light source modes, generating a natural light source mode and an artificial light source mode; performing three primary color gradient adjustment on the digital oil painting chromaticity change data according to the natural light source mode, thereby generating natural light source brightness color gradient adjustment data; Step S333: performing light source hue analysis on the digital oil painting chromaticity change data through an artificial light source mode to generate artificial light source hue analysis data, wherein the artificial light source hue analysis data includes warm-tone light source data and cold-tone light source data; performing red-yellow color component adjustment on the digital oil painting chromaticity change data through the warm-tone light source data to generate artificial light source warm-tone adjustment data; Step S334: adjusting the blue-purple color component of the digital oil painting chromaticity change data through the cold-tone light source data to generate artificial light source cold-tone adjustment data; integrating the artificial light source cold-tone adjustment data and the artificial light source warm-tone adjustment data to generate artificial light source brightness color gradient adjustment data; integrating the natural light source brightness color gradient adjustment data and the artificial light source brightness color gradient adjustment data to generate an environment brightness color gradient adjustment strategy.

[0051] In an embodiment of the present invention. By extracting the information on the change of the ambient light intensity over time for each pixel or each area in the image from the ambient light intensity data of the digital oil painting. The time series change of the light intensity can be analyzed by a time series analysis method (for example, a moving average method, a time difference method, etc.). The light intensity data of each area is represented as a time series Lt(x, y), where t represents the time index, and x, y are spatial coordinates. Lt(x, y)=f(I(x, y, t)); where I(x, y, t) is the pixel value of the image at different times t, and f is the calculation function of the light intensity. The light intensity data of each pixel or area is subjected to a time series analysis to obtain the light intensity time series change time series data, which is used to describe the light intensity change trend of each area in the image. A trend analysis method (for example, linear regression, smooth curve fitting, etc.) is used to perform a trend analysis on the light intensity time series change data to understand the change trend of the light intensity over time. According to the trend analysis results, light intensity time series change trend data is generated for subsequent light source mode division. According to the light intensity change trend data, determine whether the lighting in each area of ​​the image meets the characteristics of natural light sources (such as relatively smooth and regular changes over time) or the characteristics of artificial light sources (such as relatively stable or sudden changes in lighting). Using a certain threshold or pattern recognition method, the light intensity change mode is divided into natural light source mode and artificial light source mode. Natural light source mode: usually has obvious day and night changes, and the light intensity changes greatly over time. Artificial light source mode: the light intensity is relatively stable, usually does not change over time, or changes slightly. For the area of ​​natural light source mode, the chromaticity is gradually adjusted according to its ambient light intensity. Usually, natural light sources show the lighting changes under daylight, with a relatively gentle color transition. Using the color gradient algorithm, the red, green, and blue channels (or channels in other color spaces) of the image are gradually adjusted so that the chromaticity transitions smoothly in the area of ​​light intensity change to avoid abrupt color changes. Based on the light intensity data, the chromaticity of the natural light source area is gradually adjusted to obtain the natural light source brightness color gradient adjustment data for subsequent color fusion. For the area of ​​artificial light source mode, the light source hue is analyzed. Artificial light sources (such as indoor lighting) usually present specific hues, such as warm light sources (yellow, orange) and cool light sources (blue, purple). Use chromaticity component analysis (such as RGB or HSV color space) to adjust the chromaticity according to different light source hues. Adjust the red-yellow color component of the digital oil painting chromaticity change data based on the warm light source data obtained by analysis. The warm tones in the image can be enhanced by increasing the saturation of the red and yellow channels to make it appear warmer. Adjust the blue-purple color component of the digital oil painting chromaticity change data based on the cool light source data. Make the cool tones in the image more prominent by increasing the saturation of the blue and purple channels.

[0052] Preferably, step S4 comprises the following steps: Step S41: performing image rendering on the digital oil painting dynamically adjusted image to generate a digital oil painting rendered image; Step S42: uploading the digital oil painting rendering image to the cloud platform for image storage, thereby generating a digital oil painting storage image; performing transmission resolution detection on the digital oil painting storage image to generate digital oil painting transmission resolution data; Step S43: the image display resolution of the digital oil painting storage image is constant through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image.

[0053] In an embodiment of the present invention, by dynamically adjusting the image of the digital oil painting, rendering processing is first performed, and the brushstrokes, lighting and texture effects of the oil painting are simulated by using an image rendering engine (such as OpenGL, Vulkan or other graphics rendering API). The rendering process includes: applying the texture information of the oil painting to the surface of the 3D model to enhance the visual effect of the picture. Simulating the reflection, refraction and shadow effects under different light source conditions to make the details of the oil painting more vivid. Simulating the real oil painting brushstroke effect to show the thickness, curvature and heavy feeling of the brushstrokes. The rendered digital oil painting rendering image is compressed and uploaded to the cloud platform, and distributed storage technology is used to ensure high availability and fast retrieval of image data. The cloud platform should support the storage and management of large-capacity images, and object storage (such as AWS S3) or cloud database system can be used to save these image data. The uploaded image is the digital oil painting storage image. After the image is uploaded, the transmission resolution detection is performed, which ensures that the quality of the uploaded image under different network conditions can meet the display requirements. The detection process generates digital oil painting transmission resolution data by analyzing the pixel distribution, compression ratio and network bandwidth of the image. The transmission resolution data includes the current resolution, compression level, transmission delay and other information of the image, which provides a basis for the next step of image display adjustment. Based on the transmission resolution data of the digital oil painting, the resolution of the image is adjusted to ensure that the clarity and details of the image display are retained on different display devices (such as mobile phones, computers or TV screens). A super-resolution algorithm (such as SRGAN or VDSR based on convolutional neural networks) is used to enhance the image at high resolution to supplement the details lost in the image at low resolution. The adjusted image is a high-resolution digital oil painting display image, which can ensure that it can show the best visual effects on various terminal devices, especially on large screens or high-resolution devices, the artistic effects and details of the image will not be distorted.

[0054] In this specification, a visual imaging optimization system for digital oil painting is provided, which is used to execute the visual imaging optimization method for digital oil painting. The visual imaging optimization system for digital oil painting includes: The spatial feature extraction module is used to obtain an initial oil painting image set; perform digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; perform multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; The spatial domain optimization module is used to construct an image pyramid layer for a standard digital oil painting image using multi-dimensional spatial feature data of a digital oil painting to generate a multi-scale pyramid image; perform regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; perform oil painting spatial domain optimization on the standard digital oil painting image through the detail enhanced texture layer to generate a digital spatial domain optimized image; The environment perception enhancement module is used to collect environment light perception data of the digital space domain optimized image to obtain environment light perception data of the digital oil painting; calculate the environment light intensity of the digital oil painting environment light perception data to generate the digital oil painting environment light intensity data; perform interactive environment perception enhancement of the digital space domain optimized image through the digital oil painting environment light intensity data to generate a digital oil painting dynamically adjusted image; The image storage module is used to store the digital oil painting dynamically adjusted image, thereby generating a digital oil painting storage image; perform transmission resolution detection on the digital oil painting storage image, and generate digital oil painting transmission resolution data; perform image display resolution constant on the digital oil painting storage image through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; The 3D printing module is used to use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining the digital oil painting 3D printing image to perform the paper box manufacturing process operation.

[0055] The beneficial effect of the present invention is that through multi-dimensional spatial feature extraction and image pyramid layer construction, the details of the oil painting image are richer, and the artistic level and texture details of the oil painting can be better expressed. By enhancing the texture layer and optimizing the spatial domain, the oil painting image can be clearer and more vivid while retaining the artistic sense, presenting a more layered effect. By collecting ambient light perception data and calculating the light intensity, the image can be dynamically adjusted according to the actual environmental changes, the naturalness and interactivity of the image are improved, and the viewing experience of the audience under different lighting conditions is more realistic. During the transmission and display process, the high resolution and constant display effect of the image are maintained to avoid the image quality degradation caused by the resolution change. Through the transmission resolution detection and display resolution constant technology, the clarity and detail restoration of the digital oil painting are guaranteed, and the visual effect of the image is improved, especially the performance on large-screen display and high-definition display. This process enables the oil painting image to be personalized and dynamically adjusted on different display platforms (such as display, projector, etc.). According to the ambient light and device characteristics, the brightness, contrast, etc. of the image are automatically optimized to provide a better viewing experience. By using the image storage and transmission resolution detection technology, it is ensured that the digital oil painting image will not lose quality when transmitted under different network conditions, while reducing the storage space occupied and improving the efficiency of data processing. Therefore, the present invention improves the authenticity and flexibility of the visual imaging of digital oil paintings through multi-scale detail enhancement, ambient light perception and high-resolution display optimization.

[0056] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0057] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A visual imaging optimization method for digital oil painting, characterized in that: The following steps are involved: Step S1: obtaining an initial oil painting image set; performing digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; performing multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; Step S2: constructing an image pyramid layer for the standard digital oil painting image using the multi-dimensional spatial feature data of the digital oil painting to generate a multi-scale pyramid image; performing regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; optimizing the standard digital oil painting image in the oil painting space domain through the detail enhanced texture layer to generate a digital space domain optimized image; Step S3: collecting ambient light perception data of the digital space domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; performing interactive environmental perception enhancement of the digital space domain optimized image through the ambient light intensity data of the digital oil painting to generate a dynamic adjustment image of the digital oil painting; Step S4: storing the digital oil painting dynamically adjusted image, thereby generating a digital oil painting storage image; Performing transmission resolution detection on the digital oil painting storage image to generate digital oil painting transmission resolution data; The image display resolution of the digital oil painting storage image is constant through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; Step S5: Use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining a digital oil painting 3D printed image to perform a paper box manufacturing process operation.

2. The visual imaging optimization method of digital oil painting according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using a camera to obtain an initial oil painting image set; Step S12: performing image cropping on the initial oil painting captured image set to generate an initial captured cropped image set; performing image filtering on the initial captured cropped image set to generate an initial captured filtered image set; Step S13: performing image color balancing on the initial shot filter image set to generate an initial shot balanced image set; performing image contrast adjustment on the initial shot balanced image set to generate a standard oil painting shot image set; Step S14: performing digital image conversion on the standard oil painting image set to generate a standard digital oil painting image; performing multi-dimensional space feature extraction on the standard digital oil painting image to obtain digital oil painting multi-dimensional space feature data.

3. The visual imaging optimization method of digital oil painting according to claim 2, characterized in that: Digital image conversion of standard oil painting images includes: Perform multi-perspective image screening on the standard oil painting image set to obtain multi-perspective oil painting images; perform perspective image fusion on the multi-perspective oil painting images to generate full-perspective oil painting images; perform oil painting texture analysis on the full-perspective oil painting fusion images to generate oil painting texture data; The full-view oil painting image is converted into Lab color space through oil painting texture data to generate a digital oil painting color reconstructed image; oil painting brush strokes are simulated on the digital oil painting color reconstructed image to generate digital oil painting brush stroke simulation data; image details of the digital oil painting color reconstructed image are enhanced based on the digital oil painting brush stroke simulation data to generate a standard digital oil painting image.

4. The visual imaging optimization method of digital oil painting according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Decomposing the standard digital oil painting image using the digital oil painting multi-dimensional spatial feature data to generate oil painting scale decomposition data; constructing an image pyramid layer according to the oil painting scale decomposition data to generate a multi-scale pyramid image; Step S22: performing image hierarchical division on the multi-scale pyramid image to generate oil painting hierarchical division data; performing brightness enhancement on the multi-scale pyramid image based on the oil painting hierarchical division data to generate a digital oil painting brightness enhanced image; Step S23: performing local detail region recognition on the digital oil painting brightness enhanced image to obtain local detail region data of the digital oil painting; performing regional fuzzy separation on the digital oil painting brightness enhanced image using the local detail region data of the digital oil painting to generate a detail enhanced texture layer; Step S24: optimizing the standard digital oil painting image in the oil painting space domain through a detail enhancement texture layer to generate a digital space domain optimized image.

5. The visual imaging optimization method of digital oil painting according to claim 4, characterized in that: The construction of the image pyramid layer based on the oil painting scale decomposition data includes: Gaussian filtering is performed on the multi-dimensional spatial feature data of the digital oil painting according to the oil painting scale decomposition data to generate oil painting spatial level filtering data; the resolution of the oil painting spatial level filtering data is recursively reduced to generate oil painting spatial resolution recursive levels; the oil painting spatial resolution recursive levels are output at the image level to generate an oil painting fuzzy pyramid image; The oil painting fuzzy pyramid image is subjected to Laplace scale reduction to generate oil painting scale detail data; the oil painting fuzzy pyramid image is subjected to image reconstruction according to the oil painting scale detail data to generate an oil painting detail pyramid image; wherein the formula of Laplace scale reduction is as follows: ； In the formula, Represented as a painting detail pyramid image, Expressed as Layer length is Width Oil painting of blurred pyramid image, Represented as oil painting level, Expressed as Layer length is Width Oil painting of blurred pyramid image, It is indicated as upsampling; The oil painting fuzzy pyramid image and the oil painting detail pyramid image are fused to generate a multi-scale pyramid image.

6. The visual imaging optimization method of digital oil painting according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: Calculate the pixel brightness change rate of the digital oil painting brightness enhanced image to obtain pixel brightness change rate data; perform adjacent pixel brightness difference analysis on the pixel brightness change rate data to generate adjacent pixel brightness difference data; perform oil painting edge area analysis on the digital oil painting brightness enhanced image according to the adjacent pixel brightness difference data to generate oil painting edge area data and oil painting core area data; Step S232: performing region marking on the edge region data and the core region data of the oil painting to generate the edge region marking data and the core region marking data of the oil painting; performing local detail region recognition on the core region marking data of the oil painting to obtain the local detail region data of the digital oil painting; performing edge region chromaticity analysis on the local detail region data of the digital oil painting to generate edge region chromaticity data; Step S233: performing regional texture sharpening on the edge region chromaticity data to generate edge region texture sharpening data; performing detail texture enhancement on the digital oil painting brightness enhanced image using the edge region texture sharpening data to generate oil painting core region texture enhancement data; Step S234: regional texture smoothing is performed on the oil painting edge area marking data to generate oil painting edge area texture blur data; regional layer fusion is performed on the digital oil painting brightness enhanced image through the oil painting core area texture enhancement data and the oil painting edge area texture blur data to generate a detail enhancement texture layer.

7. The visual imaging optimization method of digital oil painting according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: collecting ambient light perception data of the digital spatial domain optimized image to obtain ambient light perception data of the digital oil painting; calculating ambient light intensity of the digital oil painting ambient light perception data to generate ambient light intensity data of the digital oil painting; Step S32: performing a digital oil painting color depth analysis on the digital space domain optimized image to generate digital oil painting color depth data; performing a chromaticity variation range analysis on the digital space domain optimized image according to the digital oil painting color depth data to generate digital oil painting chromaticity variation range data; Step S33: performing oil painting chromaticity gradient adjustment on the digital oil painting chromaticity change data according to the digital oil painting ambient light intensity data, thereby generating an ambient brightness color gradient adjustment strategy; Step S34: using the environment brightness and color gradient adjustment strategy to perform dynamic interactive environment perception enhancement on the digital space domain optimized image to generate a digital oil painting dynamically adjusted image.

8. The visual imaging optimization method of digital oil painting according to claim 7, characterized in that: Step S33 includes the following steps: Step S331: performing intensity change time series analysis on the digital oil painting ambient light intensity data to generate light intensity time series change time series data; performing change trend analysis on the light intensity time series change time series data to generate light intensity time series change trend data; Step S332: using the light intensity time series change trend data to divide the digital oil painting ambient light intensity data into light source modes, generating a natural light source mode and an artificial light source mode; performing three primary color gradient adjustment on the digital oil painting chromaticity change data according to the natural light source mode, thereby generating natural light source brightness color gradient adjustment data; Step S333: performing light source hue analysis on the digital oil painting chromaticity change data through an artificial light source mode to generate artificial light source hue analysis data, wherein the artificial light source hue analysis data includes warm-tone light source data and cold-tone light source data; performing red-yellow color component adjustment on the digital oil painting chromaticity change data through the warm-tone light source data to generate artificial light source warm-tone adjustment data; Step S334: adjusting the blue-purple color component of the digital oil painting chromaticity change data through the cold-tone light source data to generate artificial light source cold-tone adjustment data; integrating the artificial light source cold-tone adjustment data and the artificial light source warm-tone adjustment data to generate artificial light source brightness color gradient adjustment data; integrating the natural light source brightness color gradient adjustment data and the artificial light source brightness color gradient adjustment data to generate an environment brightness color gradient adjustment strategy.

9. The visual imaging optimization method of digital oil painting according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing image rendering on the digital oil painting dynamically adjusted image to generate a digital oil painting rendered image; Step S42: uploading the digital oil painting rendering image to the cloud platform for image storage, thereby generating a digital oil painting storage image; performing transmission resolution detection on the digital oil painting storage image to generate digital oil painting transmission resolution data; Step S43: the image display resolution of the digital oil painting storage image is constant through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image.

10. A visual imaging optimization system for digital oil painting, characterized in that: The method for optimizing the visual imaging of a digital oil painting according to claim 1 is used to implement the method, the visual imaging optimization system of the digital oil painting comprising: The spatial feature extraction module is used to obtain an initial oil painting image set; perform digital image conversion on the initial oil painting image set to generate a standard digital oil painting image; perform multi-dimensional spatial feature extraction on the standard digital oil painting image to obtain multi-dimensional spatial feature data of the digital oil painting; The spatial domain optimization module is used to construct an image pyramid layer for a standard digital oil painting image using multi-dimensional spatial feature data of a digital oil painting to generate a multi-scale pyramid image; perform regional fuzzy separation on the multi-scale pyramid image to generate a detail enhanced texture layer; perform oil painting spatial domain optimization on the standard digital oil painting image through the detail enhanced texture layer to generate a digital spatial domain optimized image; The environment perception enhancement module is used to collect environment light perception data of the digital space domain optimized image to obtain environment light perception data of the digital oil painting; calculate the environment light intensity of the digital oil painting environment light perception data to generate the digital oil painting environment light intensity data; perform interactive environment perception enhancement of the digital space domain optimized image through the digital oil painting environment light intensity data to generate a digital oil painting dynamically adjusted image; The image storage module is used to store the digital oil painting dynamically adjusted image, thereby generating a digital oil painting storage image; perform transmission resolution detection on the digital oil painting storage image, and generate digital oil painting transmission resolution data; perform image display resolution constant on the digital oil painting storage image through the digital oil painting transmission resolution data, thereby generating a high-resolution digital oil painting display image; The 3D printing module is used to use 3D printing technology to perform three-dimensional imaging printing on the high-resolution digital oil painting display image, thereby obtaining the digital oil painting 3D printing image to perform the paper box manufacturing process operation.

Images