Image enhancement method for display screen images

Abstract

The present invention discloses an image enhancement method for display screen images, and relates to the field of image enhancement technology. The method comprises: preprocessing the input display screen image, removing noise and enhancing edges, and optimizing the pixel value of the image by using a quantum annealing algorithm. The display screen image enhancement method of the present invention utilizes quantum computing, has high efficiency, accuracy and innovation, optimizes pixel values ​​and color space by a quantum annealing algorithm, combines traditional algorithms and monitors and adjusts in real time, can quickly process a large amount of image data, find the global optimal solution, ensure that parameters such as image contrast, brightness, and color saturation are adjusted most accurately, discover image features and patterns that are difficult to detect with traditional algorithms, adapt to different environmental parameters and user needs, so that images maintain good visual effects in different scenes, improve user viewing experience, and provide a powerful and innovative solution for improving the image quality of display screens.

Description

Technical Field

[0001] The present invention relates to the technical field of image enhancement, and in particular to an image enhancement method for display screen images. Background Art

[0002] As an important carrier of modern information dissemination, display screens play a vital role in various fields. Display screens are an electronic device composed of numerous pixels. Through precise control of each pixel, they can present colorful images and text information. Image display is the process of converting digital or analog signals into visual images. In this process, the display screen receives information from various signal sources, such as computers, cameras, mobile phones, etc., and then converts this information into light signals, and presents images through the light emission of pixels. The quality of image display directly affects people's acquisition and understanding of information. Images with high definition, true color reproduction and smooth dynamic effects can better convey information and improve people's work efficiency and quality of life.

[0003] However, due to various reasons, the images displayed on the display screen often have some shortcomings. For example, the image may be disturbed by noise, resulting in blurry images; or the contrast and brightness of the image are not ideal, making it difficult to distinguish the details of the image; or the color saturation of the image is insufficient, making the image not bright and vivid enough. In order to solve these problems, image enhancement is required. The purpose of image enhancement is to improve the quality of the image by processing the image so that it better meets people's visual needs. The effects and significance of image enhancement are multifaceted.

[0004] In the prior art, the traditional image enhancement methods still have certain deficiencies when used. The traditional image enhancement methods mainly include methods based on the spatial domain and methods based on the frequency domain. Although these methods are simple and easy to implement, the processing effect is limited, it is difficult to adapt to complex image scenes, the calculation complexity is high, the processing speed is slow, and it takes a long time to process a large amount of image data. Moreover, these methods often find it difficult to find the global optimal solution when adjusting the pixel value and color space of the image, resulting in an unsatisfactory image enhancement effect. Therefore, it is necessary to propose an image enhancement method for display screen images to solve the problems in the prior art. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and provide an image enhancement method for display screen images. It can utilize quantum computing, has high efficiency, accuracy and innovation, optimizes pixel values ​​and color space through quantum annealing algorithm, combines traditional algorithms and monitors and adjusts in real time, can quickly process large amounts of image data, find the global optimal solution, discover image features and patterns that are difficult to detect with traditional algorithms, adapt to different environmental parameters and user needs, so that images maintain good visual effects in different scenarios, enhance user viewing experience, and provide a powerful and innovative solution for improving the image quality of display screens.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an image enhancement method for display screen images, the method comprising the following steps:

[0007] Preprocess the input display screen image to remove noise and enhance edges;

[0008] The quantum annealing algorithm is used to optimize the pixel values ​​of the image. The pixel values ​​of the image are regarded as quantum bits. The state of the quantum bits is adjusted to optimize the pixel values ​​to enhance the contrast and brightness. For color images, the pixel values ​​of the three color channels are optimized simultaneously.

[0009] Optimize the color space of the image, use the parallel computing power of quantum computing to process multiple color channels at the same time, and select the appropriate color space for optimization according to different needs;

[0010] Combine quantum computing with traditional image enhancement algorithms. First, use traditional algorithms to preliminarily process the image, and then use quantum computing to further optimize the processed image.

[0011] During the image display process, the environmental parameters of the display screen and the image display effect are monitored in real time, and the quantum computing parameters and image enhancement effects are dynamically adjusted based on the monitored data.

[0012] Furthermore, when preprocessing the image, a method combining median filtering and Gaussian filtering is used to remove noise. Specifically, a median filtering operation is first performed to determine the filter window size, which is adjusted according to the noise type and intensity of the image. For each pixel, the pixel values ​​in its surrounding neighborhood are sorted, and the middle value is taken as the new value of the pixel. Then, a Gaussian filter is performed. According to the characteristics of the image and the degree of noise, the appropriate Gaussian kernel size and standard deviation are calculated. The orderly combination of median filtering and Gaussian filtering comprehensively removes different types of noise.

[0013] Furthermore, when the quantum annealing algorithm is used to optimize the pixel value, the objective function is defined as: F = w 1 ×(C target -C current) 2 +w 2 ×(B target -B current ) 2 , where C target and C current Represent the target contrast and current contrast respectively, B target and B current Represent the target brightness and current brightness respectively, w 1 and w 2 is the weight coefficient. During the optimization process, the state of the quantum bit is first initialized. According to the pixel value range of the image and the target values ​​of contrast and brightness, the initial probability amplitude of the quantum bit is determined. Then the parameters of the quantum annealing algorithm are set. By continuously adjusting the state of the quantum bit, the objective function is minimized to enhance the contrast and brightness of the image.

[0014] Furthermore, when optimizing the color space, the following formula is used for the process of converting from the RGB color space to the HSV color space: Where R, G, and B represent the red, green, and blue color values ​​of the pixel respectively, V represents the brightness value, S represents the saturation value, and H represents the hue value. When performing quantum computing optimization on the saturation and hue channels, the saturation and hue values ​​are regarded as the probability amplitude of the quantum bit respectively. First, the target range of saturation and hue is determined, and adjusted according to the theme of the image and user needs. Then, the saturation and hue are changed by adjusting the state of the quantum bit. During the adjustment process, the quantum rotating gate operation is used to determine the rotation angle according to the difference between the target value and the current value, and the quantum bit is rotated to gradually approach the target value, making the color of the image more vivid and natural.

[0015] Furthermore, when combining quantum computing with traditional algorithms, the preliminary processing of traditional algorithms, in addition to median filtering, Gaussian filtering and edge detection, also includes histogram equalization. The specific steps are:

[0016] First, calculate the grayscale histogram of the image and count the number of pixels at each grayscale level in the image;

[0017] Then, the cumulative distribution function is calculated according to the grayscale histogram, and the number of pixels at each grayscale level is accumulated to obtain the cumulative distribution function value;

[0018] Finally, each pixel value of the image is mapped through the cumulative distribution function, the original pixel value is converted into a new grayscale value and the grayscale distribution of the image is adjusted to improve the contrast of the image.

[0019] Furthermore, when monitoring the environmental parameters of the display screen in real time, for monitoring the ambient light intensity, a photosensitive sensor is used to adjust the brightness and contrast of the image according to the change of the ambient light intensity. When the ambient light intensity increases, the brightness and contrast of the image are adjusted by the following formula: L new =L current +k 1 ×(I current -I target ), C new =C current +k 2 ×(I carrent -I largel ), where L n ew and C n ew represent the adjusted brightness and contrast, L current and C currvent Represents the current brightness and contrast respectively, I current Indicates the current ambient light intensity, I target Indicates the target ambient light intensity, k 1 and k 2 To determine the adjustment coefficient, the image is tested under different lighting conditions, the variation of brightness and contrast is analyzed, and the functional relationship between the adjustment coefficient and the ambient light intensity is determined.

[0020] Furthermore, when monitoring the environmental parameters of the display screen in real time, a gyroscope is used to monitor the viewing angle. When the viewing angle changes, the image is corrected and enhanced for viewing angle distortion according to the angle change detected by the gyroscope. The specific steps are as follows:

[0021] First, according to the angle of view change, the transformation matrix of the image is calculated. Through trigonometric functions and geometric relationships, the coordinate transformation relationship of the image at different view angles is determined to obtain the transformation matrix.

[0022] Then, the image is interpolated using the transformation matrix to correct the perspective distortion. Bilinear interpolation and bicubic interpolation methods are used to interpolate the transformed coordinate values ​​and the values ​​of the surrounding pixels to obtain new pixel values.

[0023] Finally, quantum computing is used to further optimize the corrected image to enhance its details and clarity, and a quantum convolutional neural network method is used to extract and enhance the image features.

[0024] Furthermore, when monitoring the environmental parameters of the display screen in real time, a distance sensor is used to monitor the viewing distance. When the viewing distance changes, the degree of detail enhancement of the image is adjusted. The specific adjustment method is: according to the proportional relationship between the viewing distance and the preset optimal viewing distance, the detail enhancement coefficient is determined. When the viewing distance is twice the optimal viewing distance, the detail enhancement coefficient is set to 0.5; when the viewing distance is half of the optimal viewing distance, the detail enhancement coefficient is set to 1.5. This coefficient is applied to the image detail enhancement algorithm to process the image.

[0025] Furthermore, when monitoring the display effect of the image in real time, the image quality assessment algorithm is used to evaluate the clarity, contrast and color saturation of the image in real time, and the image quality assessment index is defined as: Q = w 3 ×C+w 4 ×B+w 5 ×S+w 6 ×D, where C represents contrast, B represents brightness, S represents color saturation, D represents clarity, and w 3、 w 4、 w 5、 w 6 is the weight coefficient. When determining the weight coefficient, it is adjusted according to the user's preference and the type of image. Landscape images pay more attention to color saturation and clarity, and improve w 5 and w 6 The value of w is more important for human images, and the contrast and brightness are increased. 3 and w 4 The value of will automatically start the quantum computing optimization algorithm according to the image quality assessment result to enhance the image again.

[0026] Compared with the prior art, the image enhancement method for display screen images has the following beneficial effects:

[0027] The display screen image enhancement method of the present invention utilizes quantum computing and is efficient, accurate and innovative. It optimizes pixel values ​​and color space through a quantum annealing algorithm, combines traditional algorithms with real-time monitoring and adjustment, can quickly process a large amount of image data, find the global optimal solution, ensure that image parameters such as contrast, brightness, and color saturation are adjusted most accurately, discover image features and patterns that are difficult to detect with traditional algorithms, adapt to different environmental parameters and user needs, and enable images to maintain good visual effects in different scenarios, thereby enhancing user viewing experience and providing a powerful and innovative solution for improving display screen image quality.

[0028] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 The present invention is a flow chart of an image enhancement method for display screen images. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Embodiment 1

[0033] The image enhancement method is applied on the display screen of a high-end tablet computer. A designer is using the tablet computer to display his works and needs to obtain clear, vivid and accurate image display effects in different environments so as to better show the design details and creativity to customers.

[0034] When a designer opens a picture of a design work, the tablet first starts the traditional preprocessing process, uses median filtering to remove pulse noise such as salt and pepper noise in the image, and selects an appropriate filter window size. For example, for high-resolution design images, a 7×7 window can be used. For each pixel point, the pixel values ​​in its surrounding neighborhood are carefully sorted, and the middle value is accurately taken as the new value of the pixel point.

[0035] Then, Gaussian filtering is performed. By analyzing the grayscale histogram of the image, the grayscale distribution range of the image is determined. According to the distribution range and the complexity of the image, the appropriate Gaussian kernel size and standard deviation are selected, and the image is convolved to make the image smoother and effectively remove random noise such as Gaussian noise. At the same time, advanced edge detection algorithms, such as the Canny operator, are used to enhance the edge information of the image, making the outline of the design work clearer and sharper, laying a solid foundation for subsequent processing.

[0036] The preprocessed image pixel values ​​are used as optimization variables of the quantum annealing algorithm. For color images, the RGB color values ​​of each pixel are represented by three quantum bits respectively, and the objective function is carefully defined as: F = w 1 ×(Ctarget -C current ) 2 +w 2 ×(B target -B current ) 2 , where C target and C current Represent the target contrast and current contrast respectively, B target and B current Represent the target brightness and current brightness respectively, w 1 and w 2 It is the weight coefficient determined after multiple experiments.

[0037] When initializing the state of the quantum bit, the pixel value range and the target values ​​of contrast and brightness of the image are fully considered. The initial probability amplitude of the quantum bit is determined by analyzing a large number of different types of images. When setting the parameters of the quantum annealing algorithm, adjustments are made based on the size and complexity of the image and the processing power of the tablet. For example, for complex design images, a higher initial temperature can be selected to allow for a wider search in the quantum state. At the same time, the annealing rate is reasonably adjusted to ensure the best convergence speed and optimization effect of the algorithm. By continuously adjusting the state of the quantum bit, the objective function is minimized, thereby achieving precise enhancement of image contrast and brightness and optimization of color space.

[0038] The color space of the image is carefully optimized and converted from RGB color space to HSV color space using the following precise formula: R, G, and B represent color values, V represents brightness values, S represents saturation values, and H represents hue values. The saturation and hue values ​​are respectively regarded as the probability amplitudes of quantum bits. When determining the target ranges of saturation and hue, adjustments are made based on the theme of the design work and the needs of the designer. For example, for design works with natural scenery as the theme, a higher saturation and warmer hue range can be selected to highlight the charm of natural colors.

[0039] By adjusting the state of quantum bits to change the saturation and hue, and using quantum rotating gate operation, the rotation angle is accurately calculated based on the difference between the target value and the current value, and the quantum bits are rotated to make the color of the image more vivid and natural, better presenting the artistic appeal of the design work.

[0040] First, the image is processed comprehensively using traditional algorithms, which includes histogram equalization in addition to the previous median filtering, Gaussian filtering and edge detection.

[0041] First, carefully calculate the grayscale histogram of the image and count the number of pixels at each grayscale level in the image. Then, based on the grayscale histogram, use a complex mathematical model to calculate the cumulative distribution function, add up the number of pixels at each grayscale level, and get the cumulative distribution function value. Finally, map each pixel value of the image through the cumulative distribution function, adjust the grayscale distribution of the image, and significantly improve the contrast of the image.

[0042] After the initial processing by the traditional algorithm, quantum computing is used to further optimize the processed image. If the contrast in some areas of the image is still low, the quantum annealing algorithm can be used to fine-tune the pixel values ​​of these areas. When determining the areas that need to be adjusted, the image is intelligently segmented and divided into different areas based on multiple factors such as contrast differences and color characteristics. For areas with unsaturated colors, quantum computing is used to optimize the color space and increase the color vividness. By deeply analyzing the distribution of color channels, the areas with low saturation can be accurately determined, and then these areas can be optimized by quantum computing to make the colors of the design works richer and more vivid.

[0043] During the image display process, the tablet computer's various sensors are used to monitor the environmental parameters of the display screen and the image display effect in real time. For monitoring the ambient light intensity, a highly sensitive photosensor is used.

[0044] When the ambient light intensity increases, the formula C new =C current +k 2 ×(I current -I largel ) adjusts the brightness and contrast of the image, where L new and C new Represent the adjusted brightness and contrast, L current and C current Represents the current brightness and contrast respectively, I current Indicates the current ambient light intensity, I turget Indicates the target ambient light intensity, k 1 and k 2 It is an adjustment factor determined based on a large amount of actual test data.

[0045] For viewing angle monitoring, a high-precision gyroscope is used. When the viewing angle changes, the image is corrected and enhanced for viewing angle distortion based on the angle change detected by the gyroscope. First, the image transformation matrix is ​​accurately calculated based on the angle of viewing angle change through complex trigonometric functions and geometric relationships. Then, advanced interpolation methods such as bicubic interpolation are used to interpolate the image based on the transformation matrix to correct the viewing angle distortion. Finally, the corrected image is further optimized through quantum computing to enhance the image details and clarity.

[0046] Advanced methods such as quantum convolutional neural networks can be used to extract and enhance image features and improve image quality. For monitoring the viewing distance, precise distance sensors are used to adjust the degree of image detail enhancement when the viewing distance changes. If the viewing distance is far, the degree of image detail enhancement is reduced to avoid jagged and blurred images; if the viewing distance is close, the degree of image detail enhancement is increased to make the image clearer and sharper. The specific adjustment method is: determine the detail enhancement coefficient based on the proportional relationship between the viewing distance and the preset optimal viewing distance, and then apply the coefficient to the image detail enhancement algorithm, such as using the quantum sharpening algorithm to process the image.

[0047] In the quantum sharpening algorithm, the edges and details of the image can be enhanced by adjusting the state of the quantum bits to make the image clearer. At the same time, an advanced image quality assessment algorithm is used to conduct real-time assessment of the image clarity, contrast, color saturation, etc. The image quality assessment index is defined as: Q = w 3 ×C+w 4 ×B+w 5 ×S+w 6 ×D, where C represents contrast, B represents brightness, S represents color saturation, D represents clarity, and w 3 、w 4 、w 5 、w 6 The weight coefficient is adjusted according to user preference and image type. According to the image quality evaluation result, the quantum computing optimization algorithm is automatically started to enhance the image again. If the image quality evaluation index is lower than the preset threshold, the parameters that need to be optimized are determined according to the evaluation result, such as contrast, brightness, color saturation or clarity, and then the corresponding quantum computing method is used for optimization.

[0048] Through the image enhancement method of this embodiment, when designers use tablet computers to display their works, they can obtain excellent image display effects no matter what environment they are in. The noise of the image is efficiently removed, the edges are clearer and sharper, the contrast and brightness are extremely accurately enhanced, the colors are more vivid and natural, and the brightness and contrast of the image can be automatically adjusted under different ambient light intensities to ensure that it can be clearly seen under various lighting conditions. When the designer views the tablet computer screen from different angles, the perspective distortion of the image is corrected and enhanced in time, and the image will not be deformed. Moreover, when the viewing distance changes, the degree of detail enhancement of the image is automatically adjusted, so that the image can present the best effect at different distances. At the same time, through real-time image quality evaluation and optimization, it is ensured that the image always maintains a high-quality display state, which brings the ultimate visual enjoyment to designers and customers, better displays the details and creativity of the design works, and improves the communication and display effects.

[0049] Embodiment 2

[0050] The image enhancement method is applied on the display screen of a medical imaging diagnosis workstation. Doctors need to diagnose diseases and formulate treatment plans through high-definition and accurately displayed medical images.

[0051] When a doctor opens a medical image (such as a CT scan image, MRI image, etc.), the workstation first starts the traditional preprocessing process and uses median filtering to remove random noise in the image, especially the impulse noise that may be generated during the equipment acquisition process. For high-resolution medical images, a suitable filter window size is selected, such as an 8×8 window, to ensure that important image details are not lost while removing noise.

[0052] Next, Gaussian filtering is performed to analyze the grayscale features of the image, determine the appropriate Gaussian kernel size and standard deviation, further smooth the image, and reduce the impact of noise on subsequent processing. At the same time, an edge detection algorithm specifically for medical images is used to enhance the edge information of organs and tissues in the image, allowing doctors to more clearly distinguish the boundaries of different structures, providing a basis for accurate diagnosis.

[0053] The preprocessed medical image pixel values ​​are used as optimization variables of the quantum annealing algorithm. For color medical images (such as some special angiography images), the RGB color value of each pixel is represented by three quantum bits respectively, and the objective function is defined as: F = w 1 ×(C target -C current ) 2 +w 2 ×(B target -B current ) 2 , where Ctarget and C current Represent the target contrast and current contrast respectively, B target and B current Represent the target brightness and current brightness respectively, w 1 and w 2 The weight coefficient is determined through repeated discussions and tests based on the characteristics of medical images and the visual needs of doctors.

[0054] When initializing the state of the quantum bit, the pixel value range and the target values ​​of contrast and brightness of the image are fully considered to ensure that the difference between the lesion area and normal tissue can be highlighted. In the process of setting the parameters of the quantum annealing algorithm, adjustments are made according to the size and complexity of the image and the processing power of the workstation. For example, for complex multi-organ medical images, a higher initial temperature can be selected to allow for a wider search in the quantum state. At the same time, the annealing rate is reasonably adjusted to ensure that the convergence speed and optimization effect of the algorithm are optimal, allowing doctors to observe the lesion area more clearly.

[0055] The color space of medical images is carefully optimized. For some images that need to emphasize specific tissues or lesions, they can be converted from the standard color space to a color space that is more suitable for diagnosis, such as converting the RGB color space to a specific color space dedicated to medical images.

[0056] Precise formulas are used to calculate various parameters in the new color space. The saturation and hue values ​​are regarded as the probability amplitude of the quantum bit, respectively. When determining the target range of saturation and hue, adjustments are made based on the diagnostic needs of medical images and the habits of doctors. For example, for angiography images showing blood vessels, a higher saturation and a specific hue range can be selected to highlight the morphology and pathological conditions of the blood vessels. The saturation and hue are changed by adjusting the state of the quantum bit. The quantum rotating gate operation is used to accurately calculate the rotation angle based on the difference between the target value and the current value, and the quantum bit is rotated to make the color of the medical image more conducive to diagnosis and improve the doctor's diagnostic accuracy.

[0057] First, the medical image is comprehensively and preliminarily processed using traditional algorithms. In addition to the previous median filtering, Gaussian filtering and edge detection, it also includes a histogram equalization method customized according to the characteristics of medical images. First, the grayscale histogram of the medical image is carefully calculated, and the number of pixels at each grayscale level in the image is counted. Then, based on the grayscale histogram, the cumulative distribution function is calculated using a mathematical model specially designed for medical images. The number of pixels at each grayscale level is accumulated to obtain the cumulative distribution function value. Finally, each pixel value of the image is mapped through the cumulative distribution function, and the grayscale distribution of the image is adjusted, which significantly improves the contrast of the image and makes the lesion area more obvious.

[0058] After preliminary processing by traditional algorithms, quantum computing is used to further optimize the processed medical images. If the contrast in some areas of the image is still low, the quantum annealing algorithm can be used to fine-tune the pixel values ​​of these areas. When determining the areas that need to be adjusted, the image is intelligently segmented and divided into different areas based on multiple factors such as contrast differences and tissue characteristics. For areas with unsaturated colors, quantum computing is used to optimize the color space and increase the vividness of the color to better display specific tissues or lesions.

[0059] During the display of medical images, the workstation uses a variety of sensors to monitor the environmental parameters of the display screen and the image display effects in real time. For monitoring the ambient light intensity, a highly sensitive photosensor is used. When the ambient light intensity changes, the brightness and contrast of the image are adjusted using a formula specially designed for medical images to ensure that doctors can clearly observe the image under different lighting conditions.

[0060] For viewing angle monitoring, a high-precision gyroscope is used. When the doctor views the display screen from different angles, the image is corrected and enhanced for viewing angle distortion based on the angle changes detected by the gyroscope. First, the image transformation matrix is ​​accurately calculated based on the angle of viewing angle change through complex trigonometric functions and geometric relationships. Then, advanced interpolation methods, such as bicubic interpolation, are used to interpolate the image based on the transformation matrix to correct for viewing angle distortion. Finally, quantum computing is used to further optimize the corrected image to enhance the details and clarity of the image, allowing doctors to diagnose diseases more accurately.

[0061] For monitoring the viewing distance, a precise distance sensor is used. When the viewing distance changes, the detail enhancement level of the image is adjusted. If the viewing distance is far, the detail enhancement level of the image is reduced to avoid jagged and blurred images. If the viewing distance is close, the detail enhancement level of the image is increased to make the image clearer and sharper. At the same time, an image quality assessment algorithm specially designed for medical images is used to perform real-time assessment of the clarity, contrast, color saturation, etc. of the image.

[0062] Define the image quality assessment index as Q = w 3 ×C+w 4 ×B+w 5 ×S+w 6 ×D, where C represents contrast, B represents brightness, S represents color saturation, D represents clarity, and w 3 、w 4 、w 5 、w 6The weight coefficient is adjusted according to the doctor's visual preference and the type of medical image. According to the image quality assessment results, the quantum computing optimization algorithm is automatically started to enhance the image again. If the image quality assessment index is lower than the preset threshold, the parameters that need to be optimized are determined according to the assessment results, such as contrast, brightness, color saturation or clarity, and then the corresponding quantum computing method is used for optimization.

[0063] Through the image enhancement method of this embodiment, when doctors use the medical imaging diagnosis workstation, no matter what environment they are in, they can obtain high-quality medical image display effects. The noise in the image is efficiently removed, the edges are clearer and sharper, the contrast and brightness are extremely accurately enhanced, and the color is more conducive to diagnosis. Under different ambient light intensities, the brightness and contrast of the image can be automatically adjusted to ensure that the doctor can clearly observe the lesion area under various lighting conditions. When the doctor views the display screen from different angles, the visual angle distortion of the image is corrected and enhanced in time, and the image will not be deformed. Moreover, when the viewing distance changes, the degree of detail enhancement of the image will be automatically adjusted, so that the image can present the best effect at different distances. At the same time, through real-time image quality evaluation and optimization, it is ensured that the medical image always maintains a high-quality display state, providing a more accurate and reliable basis for the doctor's diagnosis and treatment decisions, and improving the accuracy and efficiency of medical diagnosis.

[0064] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An image enhancement method for display screen images, characterized in that: The method comprises the following steps: Preprocess the input display screen image to remove noise and enhance edges; The quantum annealing algorithm is used to optimize the pixel values ​​of the image. The pixel values ​​of the image are regarded as quantum bits. The state of the quantum bits is adjusted to optimize the pixel values ​​to enhance the contrast and brightness. For color images, the pixel values ​​of the three color channels are optimized simultaneously. Optimize the color space of the image, use the parallel computing power of quantum computing to process multiple color channels at the same time, and select the appropriate color space for optimization according to different needs; Combine quantum computing with traditional image enhancement algorithms. First, use traditional algorithms to preliminarily process the image, and then use quantum computing to further optimize the processed image. During the image display process, the environmental parameters of the display screen and the image display effect are monitored in real time, and the quantum computing parameters and image enhancement effects are dynamically adjusted based on the monitored data.

2. The image enhancement method for display screen images according to claim 1, characterized in that: When preprocessing the image, a combination of median filtering and Gaussian filtering is used to remove noise. Specifically, a median filtering operation is performed first to determine the filter window size, which is adjusted according to the noise type and intensity of the image. For each pixel, the pixel values ​​in its surrounding neighborhood are sorted, and the middle value is taken as the new value of the pixel. Then a Gaussian filter is performed. According to the characteristics of the image and the degree of noise, the appropriate Gaussian kernel size and standard deviation are calculated. The orderly combination of median filtering and Gaussian filtering can comprehensively remove different types of noise.

3. The image enhancement method for display screen images according to claim 1, characterized in that: When the quantum annealing algorithm is used to optimize the pixel value, the objective function is defined as: F = w1×(C target -C current ) 2 +w2×(B target -B current ) 2 , where C target and C current Represent the target contrast and current contrast respectively, B target and B current Represent the target brightness and current brightness respectively, w1 and w2 are weight coefficients. During the optimization process, the state of the quantum bit is first initialized. According to the pixel value range of the image and the target values ​​of contrast and brightness, the initial probability amplitude of the quantum bit is determined. Then, the parameters of the quantum annealing algorithm are set. By continuously adjusting the state of the quantum bit, the objective function is minimized to enhance the image contrast and brightness.

4. The image enhancement method for display screen images according to claim 1, characterized in that: When optimizing the color space, the following formula is used for the process of converting from RGB color space to HSV color space: Where R, G, and B represent the red, green, and blue color values ​​of the pixel respectively, V represents the brightness value, S represents the saturation value, and H represents the hue value. When performing quantum computing optimization on the saturation and hue channels, the saturation and hue values ​​are regarded as the probability amplitude of the quantum bit respectively. First, the target range of saturation and hue is determined, and adjusted according to the theme of the image and user needs. Then, the saturation and hue are changed by adjusting the state of the quantum bit. During the adjustment process, the quantum rotating gate operation is used to determine the rotation angle according to the difference between the target value and the current value, and the quantum bit is rotated to gradually approach the target value, making the color of the image more vivid and natural.

5. The image enhancement method for display screen images according to claim 1, characterized in that: When combining quantum computing with traditional algorithms, the initial processing of traditional algorithms, in addition to median filtering, Gaussian filtering and edge detection, also includes histogram equalization. The specific steps are: First, calculate the grayscale histogram of the image and count the number of pixels at each grayscale level in the image; Then, the cumulative distribution function is calculated according to the grayscale histogram, and the number of pixels at each grayscale level is accumulated to obtain the cumulative distribution function value; Finally, each pixel value of the image is mapped through the cumulative distribution function, the original pixel value is converted into a new grayscale value and the grayscale distribution of the image is adjusted to improve the contrast of the image.

6. The image enhancement method for display screen images according to claim 1, characterized in that: When monitoring the environmental parameters of the display screen in real time, for the monitoring of the ambient light intensity, a photosensitive sensor is used to adjust the brightness and contrast of the image according to the change of the ambient light intensity. When the ambient light intensity increases, the brightness and contrast of the image are adjusted by the following formula: L new =L current +k1×(I current -I target ), C new =C current +k2×(I carrent -I largel ), where L n ew and C n ew represent the adjusted brightness and contrast, L current and C currvent Represents the current brightness and contrast respectively, I current Indicates the current ambient light intensity, I target represents the target ambient light intensity, k1 and k2 are adjustment coefficients. When determining the adjustment coefficients, the image is tested under different lighting conditions, the variation of brightness and contrast is analyzed, and the functional relationship between the adjustment coefficient and the ambient light intensity is determined.

7. The image enhancement method for display screen images according to claim 1, characterized in that: When monitoring the environmental parameters of the display screen in real time, a gyroscope is used to monitor the viewing angle. When the viewing angle changes, the image is corrected and enhanced for viewing angle distortion based on the angle change detected by the gyroscope. The specific steps are as follows: First, according to the angle of view change, the transformation matrix of the image is calculated. Through trigonometric functions and geometric relationships, the coordinate transformation relationship of the image at different view angles is determined to obtain the transformation matrix. Then, the image is interpolated using the transformation matrix to correct the perspective distortion. Bilinear interpolation and bicubic interpolation methods are used to interpolate the transformed coordinate values ​​and the values ​​of the surrounding pixels to obtain new pixel values. Finally, quantum computing is used to further optimize the corrected image to enhance its details and clarity, and a quantum convolutional neural network method is used to extract and enhance the image features.

8. The image enhancement method for display screen images according to claim 1, characterized in that: When monitoring the environmental parameters of the display screen in real time, a distance sensor is used to monitor the viewing distance. When the viewing distance changes, the detail enhancement degree of the image is adjusted. The specific adjustment method is: the detail enhancement coefficient is determined according to the proportional relationship between the viewing distance and the preset optimal viewing distance. When the viewing distance is twice the optimal viewing distance, the detail enhancement coefficient is set to 0.

5. When the viewing distance is half of the optimal viewing distance, the detail enhancement coefficient is set to 1.

5. This coefficient is applied to the image detail enhancement algorithm to process the image.

9. The image enhancement method for display screen images according to claim 1, characterized in that: When monitoring the display effect of the image in real time, the image quality assessment algorithm is used to evaluate the clarity, contrast and color saturation of the image in real time. The image quality assessment index is defined as: Q = w3×C+w4×B+w5×S+w6×D, where C represents contrast, B represents brightness, S represents color saturation, D represents clarity, and w 3、 w 4、 w 5、 w6 is the weight coefficient. When determining the weight coefficient, it is adjusted according to the user's preference and the type of image. Landscape images pay more attention to color saturation and clarity, and the values ​​of w5 and w6 are increased. Portrait images pay more attention to contrast and brightness, and the values ​​of w3 and w4 are increased. According to the image quality evaluation results, the quantum computing optimization algorithm is automatically started to enhance the image again.

Images