Image display processing method, display device, medium and program product

Abstract

The present invention discloses an image display processing method, a display device, a medium and a program product, and relates to the field of image data processing technology. The method comprises: obtaining local characteristics of a distorted image; determining at least one area to be processed from the distorted image according to the local characteristics, and the area to be processed corresponds to at least one type of distortion; determining a target image correction model from an image correction model library according to the type of distortion of the area to be processed; performing correction processing on the area to be processed by the target image correction model to obtain a corrected image; and sending the corrected image to a display panel by scanning line by line, so that the display panel displays the corrected image. The present invention significantly improves the processing quality and display effect of distorted images by intelligently analyzing the local characteristics of the image and applying a customized correction model, and effectively responds to the challenges brought about by the continuous improvement of image resolution, complexity and image size.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to an image display processing method, a display device, a medium and a program product. Background Art

[0002] In the field of modern image display processing, with the rapid development and widespread application of display technology, improving image quality has become the focus of research.

[0003] Before the display panel displays an image, it is necessary to perform distortion correction processing on the image to eliminate the negative impact of image distortion on the display effect of the image on the display panel.

[0004] Related technologies often use a global unified correction strategy for distorted images. However, with the continuous improvement of image resolution, complexity and image size, the traditional global unified correction strategy is unable to cope with large-scale image data, and the processing speed and effect are difficult to meet the requirements of real-time and high quality. Summary of the invention

[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide an image display processing method, a display device, a medium and a program product, which significantly improve the processing quality and display effect of distorted images by intelligently analyzing the local characteristics of the image and applying a customized correction model, and effectively respond to the challenges brought about by the continuous improvement of image resolution, complexity and image size.

[0006] To achieve the above-mentioned objectives, in a first aspect, the present invention provides an image display processing method, comprising: obtaining local characteristics of a distorted image; determining at least one area to be processed from the distorted image according to the local characteristics, and the area to be processed corresponds to at least one distortion type; determining a target image correction model from an image correction model library according to the distortion type of the area to be processed; performing correction processing on the area to be processed by using the target image correction model to obtain a corrected image; and sending the corrected image to a display panel by means of line-by-line scanning so that the display panel displays the corrected image.

[0007] The present invention achieves personalized and optimized correction processing of the processing area by accurately acquiring and analyzing the local characteristics of the distorted image. Compared with the existing global unified correction strategy, the present invention significantly improves the accuracy and flexibility of image processing. By performing detailed characteristic analysis and identification on different areas of the distorted image, the most suitable image correction model can be selected for processing according to different distortion types. This method not only effectively avoids inappropriate processing of areas that do not require correction or require different types of correction, but also ensures that each part of the image can obtain the correction that best suits its characteristics. By applying the target image correction model to correct only the area to be processed, rather than the entire image, computing resources and processing time are greatly saved, efficiency is improved, and the challenges of increasing image resolution, complexity and image size can be effectively addressed.

[0008] In combination with the embodiment provided in the first aspect, in some embodiments, the step of determining the target image correction model from the image correction model library according to the distortion type of the area to be processed includes: determining a distortion degree corresponding to at least one distortion type of the area to be processed; determining at least one main distortion type according to the distortion degree; and determining the target image correction model from the image correction model library according to the main distortion type.

[0009] By adopting the technical solution of the above embodiment, the concept of distortion degree is introduced by refining the evaluation process of the distortion type, so that the selection of the correction model is more accurate and personalized. This method not only improves the correction effect, but also optimizes the use of processing time and resources by effectively correcting the main distortion types, thereby improving the quality and efficiency of the overall image processing.

[0010] In combination with the embodiment provided in the first aspect, in some embodiments, the distortion type includes noise, and the distortion degree includes noise degree; the step of determining a distortion degree corresponding to at least one distortion type of the area to be processed includes: determining a noise evaluation value of the area to be processed according to a noise evaluation formula, and the mathematical form of the noise evaluation formula is,

[0011] ;

[0012] Where V is the noise evaluation value, MAX I is the maximum pixel value of the area to be processed, MSE is the mean square error, Λ represents the spectral range that the human eye is sensitive to, and w(λ) is the visual weight function corresponding to the wavelength λ;

[0013] The noise level in the distortion level is determined according to the noise evaluation value.

[0014] By adopting the technical solution of the above embodiment, a noise evaluation formula based on human visual perception can be proposed for noise distortion, which takes into account the sensitivity of the human eye to different spectra, thereby more accurately evaluating the noise level. This evaluation method makes the noise reduction process more in line with human visual perception and improves the image quality, especially in complex or sensitive visual scenes.

[0015] In combination with the embodiment provided in the first aspect, in some embodiments, the distortion type includes distortion, and the distortion degree includes distortion degree; the step of determining a distortion degree corresponding to at least one distortion type of the area to be processed includes: determining a distortion evaluation value of the area to be processed according to a distortion evaluation formula, and the mathematical form of the distortion evaluation formula is,

[0016] ;

[0017] Where O is the distortion evaluation value, I(x, y) and I′(x′, y′) are the pixel coordinates in the original image and the distorted image corresponding to the area to be processed, Ω is the image domain, T represents the distortion field, R(T) is the regularization term of the distortion field, and α is the parameter that controls the regularization strength;

[0018] The distortion degree in the distortion degree is determined according to the distortion evaluation value.

[0019] By adopting the technical solution of the above embodiment, a distortion evaluation formula can be proposed for distortion distortion, and the degree of image distortion can be quantitatively evaluated by calculating the distortion field. This method allows the system to more accurately identify and correct geometric distortion in the image, such as barrel distortion or pincushion distortion, thereby improving the geometric accuracy and visual effect of the image.

[0020] In combination with the embodiment provided in the first aspect, in some embodiments, before the step of obtaining the local characteristics of the distorted image, it also includes: classifying the image to be displayed through a distorted image classification model to obtain a classification result; and confirming that the image to be displayed is a distorted image based on the classification result.

[0021] By adopting the technical solution of the above embodiment, the distorted image classification model is introduced to realize the automatic pre-processing classification of the image. This step selects the images that need to be corrected in advance, avoids unnecessary processing, improves the efficiency and response speed of the processing flow, and also provides an accurate starting point for the subsequent correction steps.

[0022] In combination with the embodiment provided in the first aspect, in some embodiments, after the step of correcting the area to be processed by the target image correction model to obtain a corrected image, it also includes: obtaining the display characteristics of the display panel; adjusting the corrected image according to the display characteristics to obtain an adjusted corrected image.

[0023] By adopting the technical solution of the above embodiment, a step of adjusting the image according to the characteristics of the display panel is added after the image correction process, ensuring that the corrected image can adapt to the characteristics of different display devices. This adjustment not only optimizes the performance of the image on a specific display device, but also enhances the versatility and compatibility of the image.

[0024] In combination with the embodiment provided in the first aspect, in some embodiments, after the step of sending the corrected image to the display panel by line-by-line scanning so that the display panel displays the corrected image, it also includes: obtaining the display effect of the corrected image on the display panel; adjusting the model parameters in the target image correction model according to the display effect.

[0025] By adopting the technical solution of the above embodiment, a closed-loop optimization system is formed by obtaining the display effect after the image is displayed and feeding it back to the correction model. This feedback mechanism enables the correction model to continuously optimize itself according to the actual display effect, improves the long-term accuracy and adaptability of the correction, and ensures the continuous improvement of the image display quality.

[0026] In a second aspect, an embodiment of the present invention provides a display device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the display device to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0027] In a third aspect, the present invention provides a computer-readable storage medium, comprising instructions, which, when executed on a display device, enable the display device to execute the method described in the first aspect and any possible implementation of the first aspect.

[0028] In a fourth aspect, the present invention provides a computer program product comprising instructions, and when the computer program product is run on a display device, the display device executes the method described in the first aspect and any possible implementation of the first aspect.

[0029] It can be understood that the display device provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0030] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0031] 1. The technical solution of the present invention can provide highly targeted and personalized correction capabilities. By accurately analyzing the local characteristics of the distorted image and intelligently identifying the specific distortion types in different areas, the solution can customize the most appropriate correction strategy for each area to be processed. This refined processing method not only significantly improves the image quality, but also improves the efficiency and response speed by optimizing the processing process, meeting the needs of real-time and high-quality display.

[0032] 2. The technical solution of the present invention deeply integrates the characteristics of display devices. The technical solution is not limited to the correction processing of the image, but also includes the acquisition and analysis of the characteristics of the display panel, and then further adjusts the corrected image to ensure that the image can show the best effect on different display devices. This consideration of the characteristics of the display device makes the image display more consistent with the visual perception of the human eye and enhances the versatility and adaptability of the image.

[0033] 3. The technical solution of the present invention realizes a closed-loop optimization mechanism. By obtaining the display effect after the image is displayed and feeding it back to adjust the parameters of the correction model, the solution achieves continuous self-optimization. This dynamic adjustment and iterative improvement ensures the continuous improvement of the image processing effect, while enabling the solution to adapt to different viewing environments and changes in user preferences, achieving a high level of flexibility and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0035] Figure 1 is a flow chart of an image display processing method according to an embodiment of the present invention;

[0036] Figure 2 is a flow chart of another image display processing method according to an embodiment of the present invention;

[0037] Figure 3It is a schematic diagram of the architecture of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.

[0039] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0040] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0041] Traditional techniques mainly rely on a global unified correction strategy when processing distorted images. This strategy attempts to solve various distortion problems in the image by applying the same correction algorithm and parameters to the entire image. In the implementation process, no matter how different the distortion types and degrees may be in different areas of the distorted image, the strategy uses a consistent processing method to correct them.

[0042] For example, blurred areas due to improper focus will receive the same processing flow and parameter configuration as areas that need to be adjusted due to color deviation. Although this global unified processing method simplifies the processing flow and enables rapid correction of the entire image in a shorter time, its disadvantages are also obvious. The most notable is that it cannot carefully distinguish and accurately adapt to differences in local characteristics and complex distortion in the image. Due to the lack of specificity and flexibility, when faced with images with rich details and complex distortion characteristics, this global unified correction strategy often leads to over-correction or under-correction, thus failing to achieve the optimal visual effect.

[0043] Furthermore, this method also has problems in the effective use of resources. It may waste a lot of computing resources on image areas that do not require such intensity correction, while the parts that really need attention may not be adequately processed due to unreasonable resource allocation. Ultimately, the images processed by this strategy often fail to meet the high standards of users in terms of restoring the real scene, maintaining color accuracy, and satisfying the viewing experience. Especially in the application of professional image processing and high-end display devices, its limitations are more prominent.

[0044] Moreover, with the continuous improvement of image resolution, complexity and image size, the traditional global unified correction strategy method is unable to cope with large-scale image data, and the processing speed and effect are difficult to meet the requirements of real-time and high quality.

[0045] Therefore, an embodiment of the present invention provides an image display processing method, which realizes personalized and optimized correction processing of the area to be processed by accurately acquiring and analyzing the local characteristics of the distorted image. Compared with the existing global unified correction strategy, this embodiment significantly improves the accuracy and flexibility of image processing. By performing detailed characteristic analysis and identification on different areas of the distorted image, the most appropriate image correction model can be selected for processing according to different distortion types. This method not only effectively avoids inappropriate processing of areas that do not require correction or require different types of correction, but also ensures that each part of the image can obtain the correction that best suits its characteristics.

[0046] By applying the target image correction model to correct only the area to be processed, rather than the entire image, it greatly saves computing resources and processing time, improves efficiency, and can effectively cope with the challenges of increasing image resolution, complexity, and image size. In addition, this refined processing method also greatly improves image quality, restores images closer to the original scene, maintains color authenticity, and enhances the clarity of details, thereby significantly optimizing the viewing experience.

[0047] The embodiments of the present invention have broad application prospects and important practical value in professional image processing, high-end display equipment, and even image display of daily consumer products. With the continuous advancement of image display technology, the application of the present invention will bring users a richer and more satisfactory visual experience.

[0048] Combine the following Figure 1 The image display processing method of this embodiment is specifically introduced, comprising the following steps:

[0049] Step 101: Obtain local characteristics of a distorted image.

[0050] The local characteristics include, but are not limited to, characteristics such as brightness, color, texture, distortion, and noise level of the image region.

[0051] The display device receives the distorted image through high-precision image scanning technology and converts it into a data format that can be analyzed. Subsequently, different image processing algorithms, including pixel intensity analysis, edge detection, color component analysis, SIFT (scale-invariant feature transform) algorithm, frequency domain analysis and other image processing algorithms, are used to identify the local characteristics of the image in detail, and obtain the characteristics of brightness, color, texture, noise level, distortion and other conditions in different areas. These algorithms can detect and quantify various types of distortion in the image, such as blurriness, noise level, color deviation, geometric distortion, etc.

[0052] By comprehensively analyzing the characteristics of different areas, the display device can generate a detailed distortion map, marking the areas with significant distortion and their distortion types. This stage of work provides precise target information for the subsequent local correction processing, ensuring that the correction work is targeted and efficient.

[0053] In some embodiments, the local characteristics of the distorted image may be obtained by:

[0054] 1) Brightness characteristic acquisition:

[0055] Brightness characteristics are usually reflected in the distribution of grayscale or brightness values ​​of an image. This data can be visualized through a histogram, which shows the distribution of pixels at each brightness level in the image. For example, if the histogram shows that most pixels are concentrated in low-brightness areas, this indicates that the image may be dark overall.

[0056] Brightness analysis is used to quantify the brightness of light in an image to capture brightness characteristics. It is usually evaluated using a histogram equalization algorithm, which shows the distribution of pixels at each brightness level in the image. For example, if the image is too dark, the histogram will show that most of the pixels are concentrated at lower brightness levels. In order to more finely evaluate the brightness, the average brightness can be calculated in local areas of the image or adaptive threshold technology can be used to identify and quantify areas with uneven brightness. In addition, high dynamic range (HDR) imaging technology can provide more detailed brightness information by capturing multiple images at different exposure settings and merging them to enhance details, especially in highlight and shadow areas.

[0057] 2) Color feature acquisition:

[0058] Color characteristics are reflected in the image's RGB (red, green, blue) or more professional CIELAB (color space) color space, described by the value of the color channel. Color can be quantified by statistics such as the mean, variance, histogram, and correlation of the color channels, which reflect the color distribution, saturation, and diversity of the image.

[0059] Color characteristics can be obtained through color space conversion and color moment calculation. For example, converting an image from RGB color space to CIELAB color space can more accurately measure color differences because CIELAB color space is designed to be closer to human visual perception. In CIELAB space, the mean and standard deviation of each color channel can be calculated to evaluate color distribution and consistency. If the standard deviation of a color channel is low, it may indicate that the image has color deviation or distortion in that color.

[0060] 3) Texture feature acquisition:

[0061] Texture characteristics are reflected by texture analysis algorithms that describe repetitive patterns in local areas of images, such as local binary patterns (LBP), gray-level co-occurrence matrix (GLCM), etc. The texture descriptors output by these algorithms, such as energy, contrast, uniformity, and directionality, represent the texture structure of the image in numerical form.

[0062] The acquisition of texture characteristics can be achieved through algorithms such as gray-level co-occurrence matrix or local binary pattern. For example, GLCM quantifies the directionality, roughness, and uniformity of texture by analyzing the relationship between pixels and their neighborhood points in the image. In areas with obvious textures, such as grass or fabric, GLCM will show higher angular second-order moments and consistency values. LBP, on the other hand, captures texture information by comparing the relative intensity of a pixel with its surrounding neighborhood, and is suitable for identifying rough or smooth areas in an image.

[0063] 4) Distortion characteristics acquisition:

[0064] Distortion characteristics are reflected by the output data of the distortion detection algorithm, which may include distortion coefficients, distortion fields, or parameters of distortion models. For example, in lens distortion correction, by measuring the deviation of the image edge and fitting the distortion model, the parameters describing the distortion can be obtained, which guide the distortion correction process.

[0065] Distortion characteristics can be obtained through distortion detection algorithms, such as camera distortion correction based on feature point matching. For example, a corner detection algorithm (such as Harris corner detection) is used to identify key feature points in an image, and then the geometric transformation model of these points is fitted by the least squares method to estimate the distortion parameters. In images taken with a wide-angle lens, barrel distortion may appear at the edges. By fitting the distortion model and applying the inverse transformation, this distortion can be corrected to restore the authenticity of straight lines and angles.

[0066] 5) Noise characteristics acquisition:

[0067] Noise characteristics are characterized by analyzing the power spectral density (PSD) of the image or by estimating the noise level using a noise reduction algorithm. In the frequency domain, noise usually manifests itself as a non-uniform distribution in the PSD, while in the spatial domain, the intensity and distribution of noise can be assessed through measures of local variance or standard deviation.

[0068] The acquisition of noise characteristics can be achieved through noise variance estimation and power spectral density analysis. For example, for Gaussian noise, its standard deviation can be estimated by calculating the variance of the local area of ​​the image. In the flat area of ​​the image, the variance should be close to the standard deviation of the noise. Further, by converting the image to the frequency domain through fast Fourier transform (FFT) and analyzing the PSD, different types of noise can be identified. For example, if the PSD shows a uniform distribution in the high-frequency area, this may indicate that Gaussian noise exists in the image. Through this analysis, an appropriate noise reduction algorithm can be selected to reduce the impact of noise.

[0069] Step 102: determining at least one area to be processed from the distorted image according to the local characteristic.

[0070] The area to be processed corresponds to at least one type of distortion, which includes but is not limited to noise, blur, color deviation and distortion.

[0071] Based on these local characteristics, areas of the image that require special attention can be further identified and defined. These areas may be significantly different from other parts of the image due to various distortion problems, such as noise, blur, color deviation or geometric distortion. Image segmentation technology and image processing algorithms are used to divide the image into multiple regions with similar characteristics, each corresponding to one or more types of distortion. This step requires precise distinction and positioning of these areas to be processed, as they will directly affect the selection of the correction model and the adjustment of the correction parameters. Accurate area determination is a prerequisite for customized correction, which ensures that the correction process can solve the specific problems of the image in a targeted manner.

[0072] Step 103: Determine a target image correction model from an image correction model library according to the distortion type of the area to be processed.

[0073] Among them, the image correction model library is a collection of various correction algorithms and models, each model is designed to solve specific types of image distortion problems, such as denoising, deblurring, color correction, and geometric deformation correction. When selecting the target correction model, the display device will automatically match the optimal model based on the type and degree of distortion of the area to be processed and the image content characteristics through a set of complex decision-making logic or artificial intelligence-assisted reasoning mechanism. This selection process takes into account multiple factors such as the correction effect of the model, processing efficiency, and the degree of protection of the image content to ensure that the selected model can not only solve the problem efficiently, but also maintain the natural texture and details of the image. After selecting the model, the display device will adjust and optimize its necessary parameters to more accurately deal with specific distortion problems.

[0074] It should be noted that in the image correction model library of this embodiment, each image correction model adopts an existing image processing model. This embodiment does not make any special improvements to these models. Those skilled in the art can obtain these models through various open source channels and use them directly.

[0075] In some embodiments, step 103 specifically includes the following steps:

[0076] S1, determining a distortion degree corresponding to at least one distortion type of the area to be processed.

[0077] Specifically, in the preliminary stage of image correction, the display device first needs to perform a detailed distortion degree analysis on the area to be processed. This step is a crucial foundation for the entire correction process because it directly determines the accuracy of subsequent model selection and correction strategies. The display device will use advanced image analysis techniques, such as pixel intensity histogram analysis, frequency domain analysis, edge detection, etc., to evaluate the specific performance of the area to be processed in various distortion types. For example, in noise distortion, the display device will calculate the distribution density and frequency of the noise; in blur distortion, the sharpness of the image edge will be evaluated. Through these quantitative analyses, the display device can generate an accurate distortion degree score for each distortion type, thereby clearly identifying the severity of various distortions in the area to be processed.

[0078] In some embodiments, the distortion degree may include the noise degree, and this step may specifically include: firstly determining the noise evaluation value of the area to be processed according to a noise evaluation formula, and then determining the noise degree in the distortion degree according to the noise evaluation value.

[0079] The mathematical form of the noise assessment formula is as follows:

[0080] ;

[0081] Where V is the noise evaluation value, MAX I is the maximum pixel value of the area to be processed, MSE is the mean square error, Λ represents the spectral range that the human eye is sensitive to, w(λ) is the visual weight function corresponding to the wavelength λ, and w(λ) is based on the visual perception characteristics of the human eye, usually based on the CIE standard observer model.

[0082] 20⋅log 10 A commonly used logarithmic operation that converts a ratio into decibel (dB) units, making the values ​​easier to interpret and compare.

[0083] ∫ λ∈Λ It means integrating over a certain spectral range Λ.

[0084] MSE(λ) is the mean square error corresponding to wavelength λ. It is a measure of the difference between the original image and the distorted image. The calculation formula is:

[0085] ;

[0086] Among them, I orig (i,λ) is the intensity of the original image at wavelength λ and pixel i, I dist (i,λ) is the intensity of the distorted image at the same position, and N is the total number of pixels.

[0087] This noise evaluation formula combines the visual perception characteristics of the human eye to evaluate image noise, which can more accurately evaluate image quality, especially when considering the different sensitivities of the human visual system to different image features. By considering the sensitivity of the human eye to different colors and brightness, a more accurate image quality assessment is provided, especially when the distortion mainly affects certain parts of the image. This method can be more consistent with human visual perception.

[0088] After the noise evaluation value is calculated, the display device will determine the noise level of the area. The larger the noise evaluation value, the more serious the noise level.

[0089] In some embodiments, the distortion degree may include a distortion degree. This step may specifically include: first determining a distortion evaluation value of the area to be processed according to a distortion evaluation formula, and then determining the distortion degree in the distortion degree according to the distortion evaluation value.

[0090] The mathematical form of the distortion evaluation formula is as follows:

[0091] ;

[0092] Where O is the distortion evaluation value, I and I′ are the original and deformed images, I(x, y) and I′(x′, y′) are the pixel coordinates in the original image and the distorted image corresponding to the area to be processed, Ω is the image domain, T represents the distortion field, R(T) is the regularization term of the distortion field (such as smoothness), and α is a parameter that controls the regularization strength.

[0093] Furthermore, the machine learning model can be combined to predict and optimize the deformation field T so that it automatically adapts to the image content and deformation characteristics:

[0094] T= f ( I ; θ ) in, f is a trained neural network, θ are network parameters that can learn to map from a large number of deformed images to the optimal deformation field.

[0095] Based on this distortion evaluation formula, by combining visual perception models and optimization theory, an evaluation method that is more in line with human visual perception is provided, and complex image distortion can be evaluated and corrected more accurately. These methods may require more complex mathematical processing and computing resources, but they can significantly improve the quality of image processing results.

[0096] S2: Determine at least one main distortion type according to the distortion degree.

[0097] Specifically, once the degree of distortion of the area to be processed in different distortion types is obtained, the next step is to determine the main distortion type based on these scores. The main distortion type refers to the distortion problem that has a greater and more significant impact on the area to be processed. In this step, the display device compares the scores of each distortion degree and identifies one or more distortion types with the highest score as the main distortion type. This process requires comprehensive consideration of the degree of impact of various distortions on image quality and the audience's visual experience, as well as the interaction between different distortions. For example, if a region has noise, distortion, and blur distortion at the same time, but the degree of blur is more serious and has a relatively greater impact on image quality, the display device will identify blur as the main distortion type and give priority to solving this problem. The decision in this step has a guiding role in the selection of subsequent models, ensuring that correction resources can be invested first in the problems that have the greatest impact on the area to be processed.

[0098] S3, determining a target image correction model from an image correction model library according to the main distortion type.

[0099] Specifically, after determining the main distortion type, the next task is to select the most suitable target image correction model from the image correction model library. The image correction model library contains a variety of correction models designed for different distortion types, each of which has a specific algorithm and parameter settings to solve a certain type of distortion problem in a targeted manner. When selecting an image correction model, the display device will match the most appropriate correction technology based on the determined main distortion type and the distortion characteristics and degree unique to that type.

[0100] This selection process not only considers the correction efficiency of the model, but also its ability to protect image details and computational efficiency. For example, for the main distortion type of blur, the display device may give priority to a deblurring model with an advanced deconvolution algorithm; while for the main distortion of color deviation, a correction model based on color constancy may be selected. The completion of this step indicates that the preparations for image correction are ready, and the actual image correction processing stage will be entered next, in order to ultimately achieve a significant improvement in image quality.

[0101] Step 104: Correct the area to be processed using the target image correction model to obtain a corrected image.

[0102] Once the most suitable target image correction model is determined, the display device will then apply the model to the identified area to be processed for correction. The target image correction model analyzes and corrects each pixel or pixel block to eliminate or reduce the detected distortion. For example, when dealing with blur issues, the model may apply a sharpening filter to enhance edges and details; for color deviation issues, the color balance will be adjusted to restore a more natural color performance. During the processing process, the system will also automatically evaluate the results to ensure that the correction effect meets the expectations. This may require multiple iterative optimizations until the best correction effect is achieved. The resulting corrected image will have significantly improved visual quality and better approach the true performance of the original scene.

[0103] Step 105 , sending the corrected image to a display panel in a line-by-line scanning manner, so that the display panel displays the corrected image.

[0104] In order to ensure stable transmission of image signals and avoid possible errors, the display device uses a line-by-line scanning method for data transmission. This means that the image data will be sent to the display panel line by line in the display order of the display panel. This method ensures data synchronization and integrity and reduces additional distortion that may be introduced during the transmission process. The display panel reconstructs and displays the image line by line based on the received data, and finally presents an optimized, high-quality image. This process not only improves the visual quality of the image, but also ensures the consistency and comfort of the user's viewing experience.

[0105] This embodiment effectively improves the processing quality and efficiency of distorted images through precise local characteristic analysis and intelligent correction model selection. This embodiment can identify different types of distortion in the image and apply the most appropriate correction strategy in a targeted manner, thereby ensuring the personalization and accuracy of the correction process. In this way, even large-scale and highly complex image data can obtain high-quality correction results to meet real-time requirements. In addition, the line-by-line scanning technology used in this embodiment ensures stable transmission and high-quality display of image data, further improving the visual effect of the image on the display panel. In general, the technical solution of this embodiment significantly improves the adaptability, flexibility and user satisfaction of image display processing through its innovative processing flow, and provides strong technical support for the development of modern image display technology.

[0106] Combine the following Figure 2 The method of this embodiment is specifically described, which specifically includes the following steps:

[0107] Step 201 , classify the image to be displayed using a distorted image classification model to obtain a classification result.

[0108] Specifically, the display device uses a pre-trained distorted image classification model to perform a detailed analysis of the image to be displayed. The distorted image classification model is based on machine learning or deep learning algorithms and can identify and distinguish various types of image distortion, such as noise, blur, color deviation, etc. Through rapid scanning and feature extraction of image content, the model divides the image into different categories and generates corresponding classification results. These results reveal the possible types of distortion in the image and provide an important basis for subsequent processing decisions.

[0109] The training method of the distorted image classification model is as follows: First, a large amount of labeled sample data needs to be collected, which includes various types of distorted images and their corresponding classification labels. Then, this data is used to train a preliminary classification model, and through multiple iterations and adjustment of model parameters, it can more accurately identify and classify different types of distortion. During the training process, cross-validation and other techniques are also used to evaluate the performance of the model, and optimization and improvement are performed based on the evaluation results. In addition, in order to improve the generalization ability of the model, data enhancement technology can also be used to expand the training data set so that the model can show good classification performance in a wider range of practical applications.

[0110] Step 202: confirming that the image to be displayed is a distorted image according to the classification result.

[0111] After obtaining the analysis results of the classification model, the display device will further confirm whether the image to be displayed is a distorted image. This process involves interpreting and verifying the classification results to ensure that the distortion type identified is accurate. If the classification results indicate that one or more distortions do exist in the image, the display device will mark the image as a distorted image and continue to perform the subsequent correction process. This confirmation step is key to ensuring that the correction algorithm is only applied to the distorted image, thereby optimizing resource usage and improving the efficiency and accuracy of the entire image processing.

[0112] Step 203: Acquire local characteristics of the distorted image.

[0113] This step refers to step 101 of the above embodiment and will not be described in detail here.

[0114] Step 204: determine at least one area to be processed from the distorted image according to the local characteristic.

[0115] This step refers to step 102 of the above embodiment and will not be described in detail here.

[0116] Step 205: Determine a target image correction model from an image correction model library according to the distortion type of the area to be processed.

[0117] This step refers to step 103 of the above embodiment and will not be described in detail here.

[0118] Step 206: Correct the area to be processed using the target image correction model to obtain a corrected image.

[0119] This step refers to step 104 of the above embodiment and will not be described in detail here.

[0120] Step 207: Obtain display characteristics of the display panel.

[0121] The display characteristics of the display panel can be obtained from the product parameters of the display panel, or can be detected through preliminary experiments, so that the inherent characteristics of the display panel can be fully understood.

[0122] Display characteristics include, but are not limited to, information on key parameters such as panel resolution, color space coverage, brightness range, contrast, response time, and viewing angle. Professional test patterns and color analysis tools can be used to calibrate the display panel. For example, a colorimeter is used to measure the color gamut of the display panel to ensure accurate color reproduction; a brightness meter is used to detect the performance of the display panel at different brightness levels, and an oscilloscope is used to evaluate the response time to determine the display panel's ability to handle rapidly changing content.

[0123] Step 208: adjusting the corrected image according to the display characteristic to obtain an adjusted corrected image.

[0124] The display device will make fine image adjustments. This includes fine-tuning the image's brightness, contrast, color saturation, and hue to match the display panel's capabilities. For example, if the display panel does not display well in certain color ranges, the display device will adjust the distribution of the corresponding colors in the image to optimize the display. In addition, the display panel's brightness curve is taken into account to ensure that the light and dark parts of the image are accurately displayed. Through such adjustments, a corrected image that is optimized and adapted to the characteristics of a specific display panel can be generated, providing a more realistic and satisfying visual experience when it is finally displayed.

[0125] For example, the image can be scaled and color mapped according to the resolution and color characteristics of the panel to ensure that the image is both clear and color-accurate when displayed. For example, if the panel has a wide color gamut, the color range of the image can be adjusted to take advantage of this advantage and enhance the visual impact of the image. For high-resolution panels, the image can be sharpened to enhance the visibility of details. At the same time, the dynamic range of the image can be adjusted to optimize the display effect of light and dark areas based on the brightness and contrast characteristics of the panel. In addition, if the panel has color or brightness changes at a specific viewing angle, the image can be pre-processed by an algorithm to compensate for the effects of viewing angle changes. Ultimately, these adjustments ensure that the image presents the best visual effect on a specific display panel.

[0126] Step 209 : sending the adjusted corrected image to the display panel in a line-by-line scanning manner, so that the display panel displays the corrected image.

[0127] This step refers to step 105 of the above embodiment and will not be described in detail here.

[0128] Step 210: Obtain the display effect of the corrected image on the display panel.

[0129] This step is designed to accurately capture and evaluate how the calibrated image will look on a specific display panel. This process may involve using a high-quality image capture device, such as a high-resolution camera or color scanner, to capture the image directly from the display panel. The captured image is then analyzed and compared with the original image and the calibrated image to evaluate color accuracy, brightness consistency, and contrast performance.

[0130] In addition, the human eye's perception of brightness and color can be simulated through software to further analyze the visual effects of the image. For example, color calibration software and visual models are used to determine the gamma response and color gamut performance of the display panel. By evaluating the display effect under different ambient lighting conditions, it is possible to determine how the image will perform in actual usage scenarios, ensuring that the image maintains high-quality visual effects under different viewing conditions.

[0131] Step 211, determining whether the display effect meets the expected standard.

[0132] If yes, then the process returns to step 210 to continue monitoring the display effect of the calibrated image on the display panel; if no, then the process proceeds to step 212.

[0133] The display device will conduct a detailed analysis of the captured display and compare it with the predetermined quality standards or customer requirements. These standards may include color accuracy, brightness uniformity, contrast, and clarity of details.

[0134] If the display effect meets or exceeds the expected standards in all these aspects, the image correction is considered successful; if any aspect does not meet the standards, the correction model needs to be further adjusted.

[0135] Step 212: adjusting the model parameters in the target image correction model according to the display effect.

[0136] The display device performs an in-depth analysis of the captured image to identify any deviations from the expected effect, such as color saturation, hue deviation, or uneven brightness. Then, based on these analysis results, the parameters in the correction model are adjusted, which may include parameters of the color correction matrix, contrast enhancement algorithm, sharpening filter, or noise reduction algorithm. For example, if the display effect is found to be oversaturated in certain colors, the color correction parameters can be adjusted to reduce the intensity of these colors. If the brightness is inconsistent, the gamma correction curve can be optimized to obtain smoother brightness transitions.

[0137] In this way, the image correction model can continuously adapt to the characteristics of a specific display panel, achieving more accurate and personalized image adjustment. This process may require multiple iterations, with each iteration further optimizing the model parameters based on new display feedback until the best image quality is achieved.

[0138] The method of the embodiment of the present invention can be used for display processing of high-resolution and high-complexity image data, and brings about significant technical effects by adopting a customized correction strategy based on local characteristics.

[0139] First, this embodiment can accurately identify and analyze each local area of ​​the image, thereby accurately determining the type and degree of distortion in different areas. This accuracy is unmatched by traditional global correction methods because it allows targeted correction processing only for areas actually affected by distortion, rather than applying the same correction standard to the entire image.

[0140] Secondly, the local characteristic customized correction strategy of this embodiment finds the most suitable correction model for each part of the distorted image. This means that regardless of different types of distortion such as noise, blur or geometric distortion, the system can select the most suitable one from a series of preset correction models for targeted correction. This not only improves the correction efficiency, but also avoids unnecessary over-processing and retains the original details and quality of the image. Furthermore, since the specific display characteristics of the display panel are taken into account, this method can also ensure that the corrected image presents the best visual effect on a specific display device.

[0141] In addition, the application of progressive scanning transmission not only improves the efficiency of image transmission, but also reduces the additional distortion that may occur during the transmission process. At the same time, by obtaining the actual display effect of the corrected image on the display panel and performing feedback optimization, the system achieves the ability of self-iteration and continuous improvement. This feedback mechanism enables the correction effect to continuously approach the ideal state, and maintains the high quality of image display even in the face of changing display environments and device characteristics.

[0142] In summary, this embodiment achieves accurate correction of distorted images through customized correction strategies of local characteristics, avoids waste of resources, improves processing speed, enhances correction effects, and ensures optimal matching with display devices. This series of technical effects work together to greatly improve the performance and efficiency of image display processing, meet the strict requirements of modern image display processing for real-time and high quality, and provide end users with a more satisfactory visual experience.

[0143] The method provided in the above embodiment can be executed by a display device, which is an electronic device. The following describes the electronic device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0144] It should be noted that Figure 3 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0145] like Figure 3 As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In RAM 403, various programs and data required for system operation are also stored. CPU 401, ROM 402 and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0146] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0147] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0148] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0149] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0150] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0151] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.

[0152] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0153] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0154] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An image display processing method, characterized in that: include: Obtaining local characteristics of the distorted image; Determining at least one area to be processed from the distorted image according to the local characteristics, the area to be processed corresponding to at least one distortion type; Determine a distortion degree corresponding to at least one distortion type of the area to be processed, the distortion type includes noise, and the distortion degree includes noise degree. This step specifically includes: determining a noise evaluation value of the area to be processed according to a noise evaluation formula, and the mathematical form of the noise evaluation formula is, Where V is the noise evaluation value, MAX I is the maximum pixel value of the area to be processed, MSE is the mean square error, Λ represents the spectral range to which the human eye is sensitive, and w(λ) is the visual weight function corresponding to the wavelength λ; determining the noise level in the distortion level according to the noise evaluation value; determining at least one main distortion type according to the distortion level; Determining a target image correction model from an image correction model library according to the main distortion type; Performing correction processing on the area to be processed by using the target image correction model to obtain a corrected image; The corrected image is sent to a display panel in a line-by-line scanning manner, so that the display panel displays the corrected image.

2. The method according to claim 1, characterized in that The distortion type includes distortion, and the distortion degree includes distortion degree; the step of determining a distortion degree corresponding to at least one distortion type of the area to be processed includes: The distortion evaluation value of the area to be processed is determined according to a distortion evaluation formula, wherein the mathematical form of the distortion evaluation formula is: Wherein, O is the distortion evaluation value, I(x, y) and I′(x′, y′) are the pixel coordinates in the original image and the distorted image corresponding to the area to be processed, respectively. and Respectively represent the gradients of the original image and the distorted image at the pixel points (x, y) and (x′, y′), Ω is the image domain, T represents the distortion field, is the regularization term of the distortion field, and α is the parameter that controls the regularization strength; To optimize the operator, we need to find a distortion field T such that the function Reach a minimum value; The distortion degree in the distortion degrees is determined according to the distortion evaluation value.

3. The method according to claim 1, characterized in that Before the step of obtaining the local characteristics of the distorted image, the method further includes: The image to be displayed is classified by using a distorted image classification model to obtain a classification result; According to the classification result, it is confirmed that the image to be displayed is a distorted image.

4. The method according to claim 1, characterized in that After the step of correcting the area to be processed by the target image correction model to obtain a corrected image, the method further includes: Acquiring display characteristics of the display panel; The corrected image is adjusted according to the display characteristics to obtain an adjusted corrected image.

5. The method according to claim 1, characterized in that After the step of sending the corrected image to the display panel in a line-by-line scanning manner so that the display panel displays the corrected image, the method further includes: Acquire a display effect of the corrected image on the display panel; The model parameters in the target image correction model are adjusted according to the display effect.

6. A display device, characterized in that: include: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the display device to execute the method according to any one of claims 1 to 5.

7. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a display device, the display device is caused to execute the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product is executed on a display device, the display device is caused to execute the method according to any one of claims 1 to 5.

Images