Smart tablet screen expansion method, device, equipment and storage medium
By acquiring and comparing the resolution and pixel unit length of the image and screen, and automatically filtering and optimizing the screen expansion of the smart tablet book, the problem that the smart tablet book cannot automatically expand is solved, and efficient image display and resource utilization are achieved.
Patent Information
- Application Number
- CN202411230419.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-04
AI Technical Summary
The smart tablet cannot automatically expand the screen based on the image characteristics to be displayed and available screen resources, resulting in poor image display effect. Users need to manually adjust or find additional devices.
By obtaining the resolution and pixel unit length of the image to be displayed and the screen, filtering the appropriate screen, uniformly and compare sizes, performing intelligent scaling and screen expansion layout optimization, and automatically selecting the best screen expansion solution.
It realizes automatic intelligent screen expansion based on image characteristics and screen resources, improves image display quality and screen resource utilization efficiency, and avoids the cumbersomeness of manual adjustment.
Smart Images

Figure CN118760411B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of display screen technology, and in particular to a method, device, equipment and storage medium for expanding the screen of a smart tablet. Background Art
[0002] Smart tablets are indispensable tools for people's daily life and work. In various application scenarios, users often need to display images of different resolutions and sizes on smart tablets. At present, most smart tablets can only display images on a single screen, or require users to manually set the screen expansion plan. This method is not only cumbersome to operate, but also difficult to make full use of the available screen resources. In particular, when the resolution or size of the image to be displayed does not match the device screen, it often leads to poor image display or even serious distortion. In addition, the existing smart tablets lack the ability to automatically expand the screen according to the characteristics of the image to be displayed and the available screen resources, which causes users to often need to manually adjust or find additional display devices when displaying high-resolution or large-size images. Therefore, the smart tablet in the prior art has the technical problem of being unable to automatically expand the screen according to the characteristics of the image to be displayed and the available screen resources. Summary of the invention
[0003] The present invention aims to solve the technical problem in the prior art that a smart tablet cannot automatically expand the screen according to the characteristics of an image to be displayed and available screen resources, and provides a smart tablet screen expansion method, device, equipment and storage medium to solve the problem.
[0004] The technical solution of the present invention to solve the above technical problems is as follows:
[0005] In a first aspect, the present invention provides a method for expanding the screen of a smart tablet, including: obtaining the resolution of an image to be displayed, the pixel unit length of the image to be displayed, a screen resolution list, and a screen pixel unit length list; traversing the screen pixel unit length list, comparing it with the pixel unit length of the image to be displayed, sorting the initial screen set, and obtaining a first selected screen set; traversing the first selected screen set, unifying the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the screen pixel unit length, and obtaining the image width size and image height size, a screen width size set, and a screen height size set; based on the screen width size set and the screen height size set, comparing with the image width size and the image height size, sorting the first selected screen set to obtain a second selected screen; when the image width size is greater than When the second selected screen width size, or / and the image height size are greater than the second selected screen height size, a scaling optimization analysis is performed on the image to be displayed to obtain the scaled image width size and the scaled image height size; when the scaled image width size is greater than the second selected screen width size, or / and the scaled image height size is greater than the second selected screen height size, the width size of the screen to be expanded and the height size of the screen to be expanded are obtained; according to the width size of the screen to be expanded and the height size of the screen to be expanded, the screen expansion layout is optimized for the first selected screen set based on the screen width size set and the screen height size set to obtain a third selected screen set, wherein the third selected screen set has a screen expansion layout position label set; according to the screen expansion layout position label set, the third selected screen set is called to perform screen expansion configuration on the second selected screen.
[0006] In a second aspect, the present invention provides a smart tablet screen expansion device, including: a data acquisition unit, used to obtain the resolution of an image to be displayed, the pixel unit length of the image to be displayed, a screen resolution list, and a screen pixel unit length list; a preliminary screen selection unit, used to traverse the screen pixel unit length list, compare it with the pixel unit length of the image to be displayed, sort the initial screen set, and obtain a first selected screen set; a size unification unit, used to traverse the first selected screen set, unify the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the screen pixel unit length, and obtain the image width size and image height size, the screen width size set and the screen height size set; a screen reselection unit, used to compare the screen width size set and the screen height size set with the image width size and the image height size, sort the first selected screen set, and obtain a second selected screen; an image scaling unit, used when the image When the image width size is larger than the second selected screen width size, or / and the image height size is larger than the second selected screen height size, a scaling optimization analysis is performed on the image to be displayed to obtain the scaled image width size and the scaled image height size; an expansion demand analysis unit is used to obtain the screen width size to be expanded and the screen height size to be expanded when the scaled image width size is larger than the second selected screen width size, or / and the scaled image height size is larger than the second selected screen height size; an expansion layout optimization unit is used to perform screen expansion layout optimization on the first selected screen set based on the screen width size to be expanded and the screen height size to be expanded, and obtain a third selected screen set, wherein the third selected screen set has a screen expansion layout position label set; a screen configuration unit is used to call the third selected screen set according to the screen expansion layout position label set, and perform screen expansion configuration on the second selected screen.
[0007] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute the smart tablet screen expansion method provided in the present application.
[0008] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute the smart tablet screen expansion method provided by the present application.
[0009] The beneficial effects of the present invention are:
[0010] By obtaining the resolution of the image to be displayed, the pixel unit length of the image to be displayed, the screen resolution list, and the screen pixel unit length list, the basic information required for screen expansion is collected to provide a data basis for subsequent analysis and decision-making; by traversing the screen pixel unit length list and comparing it with the pixel unit length of the image to be displayed, the initial screen set is sorted to obtain the first selected screen set, and the screen whose pixel unit length matches the image to be displayed is screened out, thereby preliminarily narrowing the range of available screens; by traversing the first selected screen set, the screen resolution and the resolution of the image to be displayed are unified according to the pixel unit length of the image to be displayed and the screen pixel unit length, the image width size and the image height size, the screen width size set and the screen height size set are obtained, and the sizes of the image and the screen are standardized, thereby creating a unified basis for subsequent comparison and analysis; by comparing the screen width size set and the screen height size set with the image width size and the image height size, the first selected screen set is sorted to obtain the second selected screen, and the screen whose size is closest to the image to be displayed is further screened out; when the image width size is larger than the second selected screen width size, or / and the image height size is larger than the first selected screen width size, When the second screen height size is selected, the image to be displayed is subjected to scaling optimization analysis to obtain the scaled image width size and the scaled image height size, and intelligent scaling is performed when the image size exceeds the screen size to maintain the image quality as much as possible; when the scaled image width size is greater than the second selected screen width size, or / and the scaled image height size is greater than the second selected screen height size, the screen width size and the screen height size to be expanded are obtained, and the specific size requirements for screen expansion are determined; according to the screen width size to be expanded and the screen height size to be expanded, the first selected screen set is optimized for screen expansion layout based on the screen width size set and the screen height size set to obtain the third selected screen set, wherein the third selected screen set has a screen expansion layout position label set, and the best screen expansion layout scheme is determined; according to the screen expansion layout position label set, the third selected screen set is retrieved, the second selected screen is configured for screen expansion, the optimized screen expansion scheme is implemented, and the configuration of screen expansion is completed, so as to realize the function of automatically performing screen expansion according to the characteristics of the image to be displayed and the available screen resources, and achieve the technical effect of intelligently selecting and configuring the best screen expansion scheme. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A schematic diagram of the process of the smart tablet screen expansion method provided by the present invention;
[0012] Figure 2 A schematic diagram of the structure of the smart tablet screen expansion device provided by the present invention;
[0013] Figure 3A schematic diagram of the structure of an electronic device provided by the present invention;
[0014] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.
[0015] In the accompanying drawings, the components represented by the reference numerals are listed as follows:
[0016] Data acquisition unit 11, preliminary screen selection unit 12, size unification unit 13, screen reselection unit 14, image scaling unit 15, extension demand analysis unit 16, extension layout optimization unit 17, screen configuration unit 18, electronic device 500, memory 510, processor 520, computer program 511, computer readable storage medium 600, computer program 611. DETAILED DESCRIPTION
[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0019] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.
[0020] Embodiment 1:
[0021] like Figure 1As shown, an embodiment of the present invention provides a method for expanding the screen of a smart tablet, including:
[0022] S1: Obtain the resolution of the image to be displayed, the pixel unit length of the image to be displayed, a screen resolution list, and a screen pixel unit length list.
[0023] Specifically, when a user needs to display an image on a smart tablet, the resolution information of the image is first obtained, that is, the resolution of the image to be displayed. The resolution of the image to be displayed is directly obtained by parsing the attribute data of the image file to be displayed, and is expressed as the number of pixels in the width of the image × the number of pixels in the height, for example, 4096×2160. At the same time, the pixel unit length of the image to be displayed is obtained. This parameter represents the physical size of a single pixel in the image. The pixel unit length of the image to be displayed is converted according to the actual size and resolution of the image to be displayed. For example, an image with a width of 400 mm and a resolution of 4096×2160 has a pixel unit length of approximately 0.098 mm / pixel.
[0024] Next, enumerate all available screens in the current smart tablet, obtain the resolution parameters of each screen, and generate a screen resolution list. For example, the resolution of screen A is 2560×1600, the resolution of screen B is 1920×1200, the resolution of screen C is 3840×2160, and the resolution of screen D is 1280×720, then the screen resolution list is {2560×1600, 1920×1200, 3840×2160, 1280×720}. Corresponding to the screen resolution list, obtain the pixel unit length data of each screen to form a screen pixel unit length list. Assuming that the pixel unit length of screen A is 0.12 mm / pixel, the pixel unit length of screen B is 0.15 mm / pixel, the pixel unit length of screen C is 0.09 mm / pixel, and the pixel unit length of screen D is 0.2 mm / pixel, then the screen pixel unit length list is {0.12, 0.15, 0.09, 0.2}.
[0025] By obtaining the key parameters of the image to be displayed and the available screen required for realizing intelligent screen expansion, a data basis is provided for subsequent processing steps such as screen selection and image scaling, so as to find the best screen expansion solution, make full use of screen resources, and present the best image display effect.
[0026] S2: traverse the screen pixel unit length list, compare it with the pixel unit length of the image to be displayed, sort the initial screen set, and obtain a first selected screen set.
[0027] Specifically, after obtaining the pixel unit length of the image to be displayed and the list of screen pixel unit lengths, screen screening is started to find the screen that is most suitable for displaying the image to be displayed. First, all available screens are regarded as the initial screen set. Then, each element in the screen pixel unit length list is traversed and compared with the pixel unit length of the image to be displayed. Through the comparison, a screen whose pixel unit length is close to the pixel unit length of the image to be displayed is selected and added to the first selected screen set, thereby finding a screen whose resolution characteristics are similar to the image to be displayed, so as to ensure that the image will not be excessively distorted or blurred when displayed on the screen.
[0028] The specific screening method sets the screening conditions according to actual needs, for example, selecting a screen whose difference between the pixel unit length and the pixel unit length of the image to be displayed is less than a certain threshold, or directly selecting several screens whose pixel unit length is closest to the pixel unit length of the image to be displayed. For example, assuming that the pixel unit length of the image to be displayed is 0.098 mm / pixel, the following screens are available in the initial screen set: screen A: pixel unit length is 0.12 mm / pixel; screen B: pixel unit length is 0.15 mm / pixel; screen C: pixel unit length is 0.09 mm / pixel; screen D: pixel unit length is 0.2 mm / pixel. Traverse the screen pixel unit length list {0.12, 0.15, 0.09, 0.2}, and compare them one by one with the pixel unit length of the image to be displayed 0.098 mm / pixel. According to the preset screening conditions, for example, select the screen whose difference between the pixel unit length and the pixel unit length of the image to be displayed is less than 0.03 mm / pixel, and obtain the first selected screen set {screen A, screen C}.
[0029] Through the screening operation, a group of screens with resolution characteristics that best match the image to be displayed are selected from the initial screen set, providing a basis for subsequent further screening and determination of screen expansion solutions. The above screening conditions are only examples. In actual applications, different screening strategies and thresholds can be set according to specific needs to balance image quality and screen utilization efficiency.
[0030] S3: traverse the first selected screen set, unify the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the screen pixel unit length, and obtain the image width size and image height size, the screen width size set and the screen height size set.
[0031] Specifically, after obtaining the first selected screen set, the actual display capability of each selected screen is further analyzed, and the screen resolution and the resolution of the image to be displayed are unified into the same size unit, so as to perform accurate comparison of the image and screen size later.
[0032] First, the image width and height of the image to be displayed are obtained. The image width is equal to the number of pixels of the image width to be displayed multiplied by the pixel unit length of the image to be displayed, and the image height is equal to the number of pixels of the image height to be displayed multiplied by the pixel unit length of the image to be displayed. Then, each screen in the first selected screen set is traversed, and the resolution of the image to be displayed and the screen resolution are converted into corresponding actual sizes according to the pixel unit length of the image to be displayed and the pixel unit length of the screen. Specifically, first, the screen width and screen height of the currently traversed screen are calculated. The screen width is equal to the number of pixels of the screen width multiplied by the pixel unit length of the screen, and the screen height is equal to the number of pixels of the screen height multiplied by the pixel unit length of the screen; then, the calculated screen width is added to the screen width size set, and the screen height is added to the screen height size set; then, after traversing all screens in the first selected screen set, the image width, image height, and the corresponding screen width size set and screen height size set can be obtained.
[0033] By unifying the size, the size of the image to be displayed and the selected screen are converted to the same unit of measurement, which facilitates direct comparison of the image size and the screen size in subsequent steps, provides a decision-making basis for the final screen expansion plan, ensures the comparability between the image and screen sizes, and lays the foundation for realizing intelligent screen expansion.
[0034] S4: Based on the screen width size set and the screen height size set, compare with the image width size and the image height size, sort the first selected screen set to obtain second selected screens.
[0035] Specifically, after obtaining the image width size, the image height size, the screen width size set and the screen height size set, the target screen that best suits the image to be displayed is further screened out.
[0036] First, traverse the screen width size set, extract the screen height size corresponding to the current screen width size, and form a screen size pair. Then, calculate the width size deviation between the screen width size and the image width size, and the height size deviation between the screen height size and the image height size. Next, calculate the average value of the width size deviation and the height size deviation to obtain the size deviation mean between the screen size pair and the image size. Repeat the above process until all screen size pairs are traversed and the size deviation mean between each screen size pair and the image size is obtained. Afterwards, among all the size deviation means, select a set of screen size pairs with the smallest value, and use the corresponding screen as the second selected screen.
[0037] Through the screening operation, the screen with the smallest deviation from the size of the image to be displayed and the width and height dimensions closest to the size of the image to be displayed is selected from the first selected screen set as the second selected screen, further narrowing the range of alternative screens and providing the optimal target screen for subsequent image scaling and screen expansion.
[0038] S5: When the image width size is larger than the second selected screen width size, or / and the image height size is larger than the second selected screen height size, a scaling optimization analysis is performed on the image to be displayed to obtain a scaled image width size and a scaled image height size.
[0039] Specifically, after determining the second selected screen, it is determined whether the size of the image to be displayed exceeds the display range of the selected screen. If the image width of the image to be displayed is larger than the width of the second selected screen, or the image height is larger than the height of the second selected screen, it means that the image to be displayed cannot be fully displayed on the selected screen, and the image needs to be scaled and optimized.
[0040] First, according to the image width size and the second selected screen width size, the scaling ratio range in the width direction is calculated to construct the width size scaling interval. Similarly, according to the image height size and the second selected screen height size, the scaling ratio range in the height direction is calculated to construct the height size scaling interval. Next, the aspect ratio of the image to be displayed is obtained, that is, the ratio of the image width size to the image height size. Then, based on the aspect ratio, within the width size scaling interval and the height size scaling interval, the image to be displayed is scaled proportionally according to the preset scaling size step, and a series of scaled images are generated to form a scaled digital image sequence. For each scaled image in the scaled digital image sequence, the semantic similarity is compared with the original image to be displayed through the semantic analysis model, and the semantic similarity coefficient is calculated. When the semantic similarity coefficient of a scaled image is greater than or equal to the preset semantic similarity threshold, the width size and height size of the scaled image are used as the scaled image width size and the scaled image height size to complete the image scaling optimization analysis.
[0041] Through scaling optimization analysis, the most appropriate scaling size is found while minimizing the loss of semantic information of the scaled image, so that the scaled image can be fully displayed on the second selected screen while maintaining a good visual experience. By considering the semantic features of the image content, the information loss problem that may be caused by simple proportional scaling is avoided, and the intelligent level of image scaling is improved.
[0042] S6: When the width size of the zoomed image is larger than the second selected screen width size, or / and the height size of the zoomed image is larger than the second selected screen height size, obtain a screen width size and a screen height size to be expanded.
[0043] Specifically, after completing the image scaling optimization analysis, it is further determined whether the scaled image size is still larger than the size of the second selected screen. If the scaled image width is larger than the second selected screen width, or the scaled image height is larger than the second selected screen height, it means that even after scaling optimization, the image to be displayed cannot be fully displayed on a single screen, and screen expansion is required to achieve full display of the image.
[0044] When it is determined that screen expansion is necessary, first, obtain the width and height of the screen to be expanded. The method for obtaining the width of the screen to be expanded is: subtract the second selected screen width from the scaled image width to obtain the size that needs to be expanded in the width direction. Similarly, the method for obtaining the height of the screen to be expanded is: subtract the second selected screen height from the scaled image height to obtain the size that needs to be expanded in the height direction. The obtained width and height of the screen to be expanded indicate the additional screen size that needs to be increased in the width and height directions to ensure that the expanded screen area can fully accommodate the scaled image, so that the image can be fully displayed on the expanded screen without any content being cropped or blocked.
[0045] By obtaining the width and height of the screen to be expanded, the necessary parameter basis is provided for the generation of subsequent screen expansion solutions, ensuring that the expanded screen area can fully accommodate the scaled image, avoiding loss or deformation of image content, and improving the integrity and accuracy of image display.
[0046] S7: According to the screen width size to be expanded and the screen height size to be expanded, the first selected screen set is optimized for screen expansion layout based on the screen width size set and the screen height size set to obtain a third selected screen set, wherein the third selected screen set has a screen expansion layout position label set.
[0047] Specifically, after obtaining the width and height of the screen to be expanded, the optimal screen combination solution is found in the first selected screen set to meet the size requirements of screen expansion and achieve the best screen utilization efficiency and image display effect.
[0048] First, all screens except the second selected screen in the first selected screen set are taken as candidate screens to form a candidate screen set. Then, one or more screens are selected from the candidate screen set to form a screen expansion scheme, the sum of the width dimensions of all screens in the scheme is greater than or equal to the width dimension of the screen to be expanded, the sum of the height dimensions of all screens in the scheme is greater than or equal to the height dimension of the screen to be expanded, and the width dimensions and height dimensions of all screens in the scheme are from the screen width dimension set and the screen height dimension set, respectively. Next, the screen utilization efficiency of the screen expansion scheme is calculated, that is, the ratio of the sum of the areas of all screens in the scheme to the area of the screen to be expanded (the product of the width dimension of the screen to be expanded and the height dimension of the screen to be expanded). The higher the screen utilization efficiency, the more fully the screen expansion scheme can utilize the screen resources and reduce unnecessary blank areas. Repeat the above steps, enumerate all possible screen expansion schemes, and calculate the screen utilization efficiency of each scheme. Afterwards, a screen expansion scheme with the highest screen utilization efficiency is selected as the optimal screen expansion layout, the screens included in the scheme are taken as the third selected screen set, and a unique screen expansion layout position label is assigned to each screen to indicate the relative position of the screen in the expansion layout, thereby forming a screen expansion layout position label set.
[0049] Through the optimization of screen expansion layout, the optimal screen combination solution is found in the first selected screen set, namely the third selected screen set, so that the expanded screen area can just accommodate the scaled image, while maximizing the use of screen resources and reducing the waste of screen space. Each screen in the third selected screen set is assigned a screen expansion layout position label, which clarifies its relative position in the expansion layout and provides a basis for subsequent screen expansion configuration.
[0050] S8: According to the screen extension layout position tag set, the third selected screen set is retrieved, and screen extension configuration is performed on the second selected screen.
[0051] Specifically, after obtaining the third selected screen set and the screen extended layout position tag set, the screens in the third selected screen set are physically connected and logically configured with the second selected screen according to the relative position relationship indicated in the screen extended layout position tag set to form a complete extended screen area for displaying the image to be presented.
[0052] First, according to the screen extension layout position label set, the spatial position relationship of each screen in the third selected screen set relative to the second selected screen is determined, such as the left side, the right side, the top, the bottom, etc. Secondly, the screens in the third selected screen set are physically connected to the second selected screen according to the determined spatial position relationship to form a physically continuous extended screen area. The physical connection can be achieved by connecting cables, wireless transmission, etc., to ensure that the screens can communicate and transmit image data normally. Logically, the screens in the third selected screen set are coordinated with the second selected screen so that the screens are recognized as a unified extended screen in the operating system or graphics system. Subsequently, according to the scaled image width size and the scaled image height size, the extended screen area is logically divided to determine the specific display position and size of the image to be displayed on the extended screen. Then, the corresponding part of the image to be displayed is sent to each screen in the third selected screen set and the second selected screen, and each screen is controlled to display synchronously to form a complete and continuous image display effect.
[0053] Through screen expansion configuration, multiple independent screens are combined into a logically unified extended screen area according to the third selected screen set and the screen expansion layout position label set, thereby realizing the coordinated display of images to be displayed on multiple screens, breaking through the limitations of a single screen size and resolution, and being able to display ultra-large size and ultra-high resolution images to meet the needs of large display scenarios.
[0054] Furthermore, the embodiment of the present application also includes:
[0055] Collecting an image display sample data set, wherein the image size of any image display sample data is the same as the screen size;
[0056] According to the image display sample data set, extracting an image pixel unit length record data set, a screen pixel unit length record data set and an image distortion rate record data set, wherein any one of the image pixel unit length record data is less than or equal to the screen pixel unit length record data;
[0057] Performing pixel unit length deviation analysis according to the image pixel unit length record data set, the screen pixel unit length record data set and the image distortion rate record data set to obtain a pixel unit length deviation threshold;
[0058] Based on the comparison between the screen pixel unit length list and the pixel unit length of the image to be displayed, a pixel unit length deviation characteristic value list is obtained;
[0059] According to the pixel unit length deviation feature value list, screens having a pixel unit length less than or equal to the pixel unit length deviation threshold, or / and a screen pixel unit length less than or equal to the pixel unit length of the image to be displayed are selected from the initial screen set and added into the first selected screen set.
[0060] In a feasible implementation, in order to evaluate the display effect of an image on the screen under different pixel unit lengths, a set of image display sample data is collected to form an image display sample data set. The image display sample data consists of a pair of images and screens, where the size of the image is the same as the corresponding screen size, thereby simulating the actual display of the image on different screens and providing a data basis for the subsequent pixel unit length deviation analysis. Then, for each collected image display sample data, its image pixel unit length and the corresponding screen pixel unit length are extracted to form an image pixel unit length record data set and a screen pixel unit length record data set, respectively. At the same time, the degree of distortion of the image displayed on the screen is evaluated by expert evaluation and objective measurement to obtain an image distortion rate record data set. In the image display sample data set, the image pixel unit length record data is always less than or equal to the corresponding screen pixel unit length record data to ensure that the image can be fully displayed on the screen.
[0061] Subsequently, the acquired image pixel unit length record data set, screen pixel unit length record data set and image distortion rate record data set are used to analyze the influence of the deviation between the image pixel unit length and the screen pixel unit length on the image distortion rate. For example, a mapping relationship between the pixel unit length deviation and the image distortion rate is established by a statistical method or a machine learning algorithm, and a pixel unit length deviation threshold is determined. When the deviation between the image pixel unit length and the screen pixel unit length is less than or equal to the threshold, the distortion rate of the image displayed on the screen can be controlled within an acceptable range. Then, for a given list of image pixel unit lengths and screen pixel unit lengths to be displayed, the deviation between each screen pixel unit length and the pixel unit length of the image to be displayed is calculated to form a pixel unit length deviation feature value list, which reflects the degree of distortion that may be generated when the image to be displayed is displayed on different screens. Afterwards, according to the pixel unit length deviation feature value list, a screen that meets the following conditions is selected from the initial screen set and added to the first selected screen set: first, the deviation between the screen pixel unit length and the pixel unit length of the image to be displayed is less than or equal to the determined pixel unit length deviation threshold; second, the screen pixel unit length is less than or equal to the pixel unit length of the image to be displayed. These two conditions ensure that the selected screen can display the image to be displayed with a low distortion rate, and the image can also be displayed completely on the screen.
[0062] By accurately and efficiently selecting screens suitable for the images to be displayed from the initial screen set, the accuracy and reliability of screen selection are improved, the distortion rate of image display is reduced, and a better candidate screen set is provided for subsequent screen expansion solutions.
[0063] Furthermore, the embodiment of the present application also includes:
[0064] Calculating the pixel unit length deviations of the image pixel unit length recording data set and the screen pixel unit length recording data set in one-to-one correspondence to obtain a pixel unit length deviation data set;
[0065] Based on the image distortion rate threshold, the pixel unit length deviation data set is matched in combination with the image distortion rate record data set to obtain the pixel unit length deviation threshold.
[0066] In a preferred embodiment, for each pair of data in the image pixel unit length record data set and the screen pixel unit length record data set, the difference between them is calculated to obtain the pixel unit length deviation when the image is displayed on the corresponding screen. The pixel unit length deviations of all image-screen pairs are combined to form a pixel unit length deviation data set, which reflects the distribution of pixel unit length deviations when different images are displayed on different screens. After determining the pixel unit length deviation data set, the relationship between the pixel unit length deviation and the image distortion rate is further analyzed to determine the optimal pixel unit length deviation threshold. First, an image distortion rate threshold is set to represent the acceptable upper limit of image display distortion. Then, the pixel unit length deviation data set is matched with the image distortion rate record data set to find the image distortion rate corresponding to each pixel unit length deviation. Next, in the pixel unit length deviation data set, the maximum deviation value that meets the following conditions is found: the corresponding image distortion rate is less than or equal to the image distortion rate threshold. This maximum deviation value is used as the pixel unit length deviation threshold. This means that when the deviation between the image pixel unit length and the screen pixel unit length is less than or equal to the threshold, the image display distortion rate can be controlled within an acceptable range.
[0067] By establishing a quantitative relationship between the pixel unit length deviation and the image distortion rate, and based on the preset image distortion rate threshold, the optimal pixel unit length deviation threshold is determined, providing a basis for subsequent screen screening, ensuring that the selected screen can display the image to be displayed with a lower distortion rate, thereby improving the image display quality and visual experience.
[0068] Furthermore, the embodiment of the present application also includes:
[0069] Extracting a first screen width size according to the screen width size set, and extracting a first screen height size according to the screen height size set, wherein the first screen width size corresponds to the first screen height size in one-to-one correspondence;
[0070] Calculating a first width dimension deviation between the first screen width dimension and the image width dimension;
[0071] Calculate a first height dimension deviation between the first screen height dimension and the image height dimension;
[0072] Calculate a first screen size deviation average of the first width size deviation and the first height size deviation;
[0073] The analysis is repeated until the mean value of the Nth screen size deviation is obtained;
[0074] Based on the first screen size deviation average value to the Nth screen size deviation average value, the first selected screen set is sorted by minimum value to obtain the second selected screen.
[0075] In a preferred embodiment, first, the width size of each screen is extracted from the screen width size set in sequence to form the first screen width size, the second screen width size, the third screen width size, etc.; similarly, the height size of each screen is extracted from the screen height size set in sequence to form the first screen height size, the second screen height size, the third screen height size, etc. Wherein, the width size and height size of each screen are one-to-one corresponding, that is, the first screen width size and the first screen height size correspond to the same screen, the second screen width size and the second screen height size correspond to the same screen, and so on. For the first screen, the difference between its width size and the width size of the image to be displayed is calculated to obtain the first width size deviation, which reflects the degree of size difference between the first screen and the image to be displayed in the width direction. Similarly, for the first screen, the difference between its height size and the height size of the image to be displayed is calculated to obtain the first height size deviation, which reflects the degree of size difference between the first screen and the image to be displayed in the height direction.
[0076] Then, the first width size deviation and the first height size deviation of the first screen are added and then divided by 2 to obtain the first screen size deviation mean, which comprehensively considers the size difference between the screen and the image to be displayed in both width and height directions, and more comprehensively and accurately evaluates the matching degree between the screen and the image. For each screen in the first selected screen set, the above steps are repeated to calculate the respective screen size deviation mean until the screen size deviation mean of the last screen (the Nth screen) is obtained. Subsequently, the size deviation mean of all screens in the first selected screen set is comprehensively considered to find the screen size deviation mean with the smallest value, and the corresponding screen is used as the second selected screen. The smaller the screen size deviation mean, the closer the screen is to the size of the image to be displayed in the width and height directions, and the screen is the most suitable screen for displaying the image.
[0077] By further selecting the screen that best matches the size of the image to be displayed from the first selected screen set as the second selected screen, the size differences of the screen in both width and height are comprehensively considered, which can more comprehensively and accurately evaluate the matching degree between the screen and the image, thereby improving the accuracy and reliability of screen selection.
[0078] Furthermore, the embodiment of the present application also includes:
[0079] When the size deviation mean minimum value screen has multiple:
[0080] Extracting the minimum value of the first size deviation mean minimum screen width and the first size deviation mean minimum screen height of the screen with the first size deviation mean minimum value to obtain the first size deviation mean minimum screen feature size;
[0081] Until the minimum value of the screen width of the Mth size deviation mean minimum value screen and the screen height of the Mth size deviation mean minimum value screen are extracted to obtain the screen characteristic size of the Mth size deviation mean minimum value screen;
[0082] Based on the first size deviation mean minimum screen feature size up to the Mth size deviation mean minimum screen feature size, the first size deviation mean minimum screen is subjected to minimum value sorting to obtain the second selected screen.
[0083] In a preferred embodiment, when performing minimum value sorting on the first selected screen set, it may happen that the mean size deviations of multiple screens are equal and all are minimum values. In this case, it is impossible to determine which screen is more suitable as the second selected screen based on the mean size deviation of the screen. In this case, additional screening indicators and steps are introduced to further compare and distinguish the advantages and disadvantages of different screens when the mean size deviations are the same, thereby improving the accuracy and reliability of screen selection.
[0084] For multiple screens with the smallest and equal mean size deviations, the first screen is first selected and called the screen with the smallest mean size deviation. Then, the width and height of the screen are compared, and the smaller value is extracted as the feature size of the screen with the smallest mean size deviation, which reflects the minimum difference between the screen and the image size to be displayed in the width and height directions. By introducing the new evaluation index of screen feature size, the adaptation degree of different screens in the width and height directions is further compared when the mean size deviation is the same, providing a more fine-grained reference basis for the final screen selection. All screens with the smallest and equal mean size deviations are processed in sequence until the feature size of the last screen (the Mth screen) is obtained, where M represents the number of screens with the smallest and equal mean size deviations. By calculating the feature size of each screen one by one, the adaptation degree of all candidate screens in the width and height directions is comprehensively and systematically evaluated, providing more sufficient and reliable data support for the final screen selection. After that, the feature sizes of all screens with the smallest and equal mean size deviations are comprehensively considered, and the feature size with the largest value is found, and the corresponding screen is used as the second selected screen. The larger the characteristic size, the closer the screen is to the size of the image to be displayed in at least one dimension in the width and height directions, and the more suitable it is. By comparing the sizes of characteristic sizes, the optimal screen options can be further distinguished when the mean size deviations are the same, thus improving the accuracy and reliability of screen selection.
[0085] When there are multiple screens with the minimum mean size deviation, a new evaluation index, screen feature size, is introduced to further compare and select the best second selected screen. The minimum difference between the screen and the image size to be displayed in both width and height is comprehensively considered, which can more comprehensively and accurately evaluate the matching degree between the screen and the image, and improve the reliability and adaptability of screen selection. At the same time, through multi-level and multi-stage screening and comparison, the screen selection problem when the mean size deviation is the same is effectively solved, ensuring that the screen finally selected can meet the display requirements of the image to be displayed to the greatest extent, and provide the best display effect and user experience.
[0086] Furthermore, the embodiment of the present application also includes:
[0087] Constructing a width size scaling interval according to the image width size and the second selected screen width size;
[0088] Constructing a height size scaling interval according to the image height size and the second selected screen height size;
[0089] Obtaining an image aspect ratio of the image width dimension and the image height dimension;
[0090] Gradual scaling of the image to be displayed according to a preset scaling step length based on the image aspect ratio, the width scaling interval and the height scaling interval to obtain a scaled digital image sequence;
[0091] Through a semantic deviation analysis network, the scaled digital image sequence is traversed, and semantic comparison is performed with the image to be displayed to obtain a semantic deviation coefficient sequence;
[0092] When the kth semantic deviation coefficient of the semantic deviation coefficient sequence is less than or equal to the semantic deviation coefficient threshold, and the k+1th semantic deviation coefficient is greater than the semantic deviation coefficient threshold, the scaled image width dimension and the scaled image height dimension corresponding to the kth semantic deviation coefficient are output.
[0093] In a feasible implementation, the image width is used as the upper limit of the width scaling interval, and the second selected screen width is used as the lower limit of the width scaling interval to construct a continuous numerical interval to form a width scaling interval, which represents the size range in which the image can be scaled in the width direction, ensuring that the image width after scaling does not exceed the corresponding width limit. At the same time, the image height is used as the upper limit of the height scaling interval, and the second selected screen height is used as the lower limit of the height scaling interval to construct a continuous numerical interval to form a height scaling interval, which represents the size range in which the image can be scaled in the height direction, ensuring that the image height after scaling does not exceed the corresponding height limit.
[0094] Then, the ratio of the image width and image height of the image to be displayed is calculated to obtain the image aspect ratio, which reflects the image size ratio in the width and height directions and is a key parameter to ensure that the original aspect ratio is maintained during the image scaling process. Next, with the image aspect ratio as a constraint, within the range of the width scaling interval and the height scaling interval, the image to be displayed is gradually scaled according to the preset scaling step (for example, the size is reduced by 10% each time) until the image width or height reaches the lower limit of the corresponding scaling interval. During the scaling process, the image aspect ratio is kept unchanged to ensure that the image will not be stretched or deformed. Each image obtained by scaling is used as a scaled digital image and arranged in the scaling order to form a scaled digital image sequence. Subsequently, a pre-trained semantic deviation analysis network is used to perform semantic comparison between each scaled image in the scaled digital image sequence and the original image to be displayed. The semantic deviation analysis network is a deep learning model, such as a convolutional neural network or a recurrent neural network, which extracts and compares the semantic features of the image, calculates the semantic similarity between the scaled image and the original image, and obtains a semantic deviation coefficient between 0 and 1. The smaller the semantic deviation coefficient is, the closer the scaled image is to the original image in terms of semantics. All scaled images in the scaled digital image sequence are semantically compared to obtain a semantic deviation coefficient sequence with the same length as the scaled digital image sequence.
[0095] Since the scaling of the image to be displayed starts from the original size and is gradually reduced according to the preset scaling step, the images in the scaled digital image sequence are arranged in order from large to small in terms of scaling size. At the same time, as the image size decreases, the degree of image distortion will gradually increase, resulting in a gradual increase in the semantic deviation coefficient between it and the original image. Therefore, the semantic deviation coefficients in the semantic deviation coefficient sequence are arranged from small to large according to the corresponding relationship with the scaled image. When traversing the semantic deviation coefficient sequence, starting from the starting position of the sequence (corresponding to the image with the largest scaled size), the size relationship between each semantic deviation coefficient and the semantic deviation coefficient threshold is compared one by one until the first position that satisfies the condition of "the kth semantic deviation coefficient is less than or equal to the semantic deviation coefficient threshold, and the k+1th semantic deviation coefficient is greater than the semantic deviation coefficient threshold" is found, ensuring that the search starts from the image with the largest scaled size, and when the first scaled image that meets the semantic deviation coefficient threshold is found, its next scaled image no longer meets the semantic deviation coefficient threshold, thereby obtaining a scaled image with the smallest size relative to the original image and meeting the semantic deviation coefficient threshold. Therefore, the scaled digital image corresponding to the kth semantic deviation coefficient is the required minimum scaled image, and its width and height dimensions are output as the scaled image width and height dimensions, thereby retaining the semantic information of the original image to the greatest extent.
[0096] By determining the optimal image scaling size when the size of the image to be displayed exceeds the second selected screen size limit, the semantic fidelity of the image scaling process is quantitatively evaluated, the semantic information of the image is retained to the maximum extent, an objective and accurate basis is provided for image scaling, and the intelligence level and adaptation performance of image scaling are effectively improved.
[0097] Furthermore, the embodiment of the present application also includes:
[0098] Extracting features of the image to be displayed through a first semantic feature extraction channel of the semantic deviation analysis network to obtain a first feature vector;
[0099] Performing feature extraction on the i-th scaled digital image of the scaled digital image sequence through a second semantic feature extraction channel of the semantic deviation analysis network to obtain a second feature vector, wherein the second semantic feature extraction channel and the first semantic feature extraction channel are twin convolutional neural networks;
[0100] According to the semantic deviation analysis channel, the deviation between the first feature vector and the second feature vector is calculated, and the i-th semantic deviation coefficient is output and added to the semantic deviation coefficient sequence.
[0101] In a preferred embodiment, the semantic deviation analysis network includes two parallel semantic feature extraction channels, respectively referred to as the first semantic feature extraction channel and the second semantic feature extraction channel. First, the first semantic feature extraction channel is constructed. The first semantic feature extraction channel is a convolutional neural network, which is used to extract semantic features from the input image. In order to train the first semantic feature extraction channel, a large-scale image data set is prepared, which contains image samples of various sizes, various scenes, and various semantic categories. These image samples are input into the first semantic feature extraction channel, and the semantic feature vector of each image is obtained by forward propagation calculation. Then, the back propagation algorithm and the gradient descent optimization algorithm are used to continuously adjust the parameters of the convolutional neural network so that it can extract the semantic features of the image as accurately as possible. After multiple rounds of iterative training, the first semantic feature extraction channel learns how to extract effective semantic feature representations from the image. Next, the first semantic feature extraction channel is twinned to obtain the second semantic feature extraction channel. The so-called twinning refers to copying the network structure and parameters of the first semantic feature extraction channel to obtain a completely identical convolutional neural network. In this way, two semantic feature extraction channels with shared parameters are obtained, and feature extraction is performed on the image to be displayed and the scaled digital image, respectively, to obtain the corresponding semantic feature vectors. Afterwards, the first semantic feature extraction channel and the second semantic feature extraction channel are combined together, and the semantic deviation analysis channel is added to form a complete semantic deviation analysis network. The semantic deviation analysis channel receives the semantic feature vectors output by the two semantic feature extraction channels, and calculates the distance or similarity between the two feature vectors to obtain the semantic deviation coefficient, which indicates the degree of semantic difference between the two images.
[0102] The image to be displayed is input into the first semantic feature extraction channel, and a first feature vector representing the semantic features of the image to be displayed is obtained through a series of calculations of neural network layers such as convolution, pooling, and activation. The first feature vector is a high-dimensional real number vector, in which each element represents the value of the image to be displayed on a certain semantic feature dimension. For each scaled digital image in the scaled digital image sequence, feature extraction is performed through the second semantic feature extraction channel to obtain a corresponding second feature vector. The second semantic feature extraction channel and the first semantic feature extraction channel use the same network structure and parameters to form a twin convolutional neural network, ensuring that the semantic feature vectors extracted from the image to be displayed and the scaled digital image are located in the same semantic space, which is convenient for subsequent calculation of the semantic deviation between them. After obtaining the first feature vector of the image to be displayed and the second feature vector of the i-th scaled digital image, the deviation between a feature vector and a second feature vector is calculated through the semantic deviation analysis channel to obtain the i-th semantic deviation coefficient, and the calculated i-th semantic deviation coefficient is added to the semantic deviation coefficient sequence. Among them, the semantic deviation analysis channel can use a variety of metrics, such as Euclidean distance, cosine similarity, etc., to measure the degree of difference between two feature vectors in the semantic space. The value range of the i-th semantic deviation coefficient is between 0 and 1. The smaller the value, the closer the i-th scaled digital image is to the image to be displayed in terms of semantics, and the larger the value, the greater the semantic difference. Repeat the above steps until all images in the scaled digital image sequence are traversed, and obtain a semantic deviation coefficient sequence of the same length as the scaled digital image sequence, which reflects the semantic deviation between images at different scaled sizes and the image to be displayed, and provides a quantitative basis for the subsequent determination of the scaled image.
[0103] The smart tablet screen expansion method provided by the embodiment of the present invention has at least the following technical effects:
[0104] Obtaining the resolution of the image to be displayed, the pixel unit length of the image to be displayed, the screen resolution list, and the screen pixel unit length list provides the necessary information basis for subsequent analysis and decision-making. Traversing the screen pixel unit length list, comparing it with the pixel unit length of the image to be displayed, sorting the initial screen set, and obtaining the first selected screen set, ensures that the screen used in the subsequent analysis matches the image to be displayed in terms of pixel density, laying the foundation for accurate analysis. Traversing the first selected screen set, unifying the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the screen pixel unit length, obtaining the image width size and image height size, the screen width size set and the screen height size set, and obtaining directly comparable image and screen size data, making subsequent size comparison more accurate. Based on the screen width size set and the screen height size set, comparing them with the image width size and image height size, sorting the first selected screen set, obtaining the second selected screen, screening out the screen that is most suitable for displaying the image to be displayed, optimizing the screen selection, and preparing for subsequent expansion. When the image width size is larger than the second selected screen width size, or / and the image height size is larger than the second selected screen height size, a scaling optimization analysis is performed on the image to be displayed to obtain the scaled image width size and the scaled image height size, and an image scaling optimization analysis is performed to determine the optimal scaling size, so as to maintain the image quality as much as possible while ensuring the complete display of the image. When the scaled image width size is larger than the second selected screen width size, or / and the scaled image height size is larger than the second selected screen height size, the screen width size to be expanded and the screen height size to be expanded are obtained to determine whether the scaled image still exceeds the selected screen size, and the screen size to be expanded is determined when necessary, providing specific parameters for subsequent screen expansion decisions. According to the screen width size to be expanded and the screen height size to be expanded, the first selected screen set is optimized for screen expansion layout based on the screen width size set and the screen height size set to obtain a third selected screen set, wherein the third selected screen set has a screen expansion layout position label set, and the first selected screen set is optimized for screen expansion layout to obtain the optimal screen expansion solution to ensure the best visual effect in multi-screen display. According to the screen extension layout position label set, the third selected screen set is called, the screen extension configuration is performed on the second selected screen, and the specific implementation of the entire screen extension is completed. When processing large-size or high-resolution images, the screen extension is intelligently selected and performed according to the image to be displayed and the available screen characteristics.
[0105] Embodiment 2:
[0106] like Figure 2 As shown, based on the same inventive concept as the smart tablet screen expansion method provided in Embodiment 1, an embodiment of the present invention also provides a smart tablet screen expansion device, including:
[0107] A data acquisition unit 11 is used to obtain the resolution of the image to be displayed, the pixel unit length of the image to be displayed, the screen resolution list, and the screen pixel unit length list;
[0108] The initial screen selection unit 12 is used to traverse the screen pixel unit length list, compare it with the pixel unit length of the image to be displayed, sort the initial screen set, and obtain a first selected screen set;
[0109] A size unification unit 13 is used to traverse the first selected screen set, unify the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the pixel unit length of the screen, and obtain an image width size and an image height size, a screen width size set and a screen height size set;
[0110] A screen reselection unit 14, configured to sort the first selected screen set based on the screen width size set and the screen height size set, and compare with the image width size and the image height size to obtain a second selected screen;
[0111] The image scaling unit 15 is used to perform scaling optimization analysis on the image to be displayed to obtain a scaled image width size and a scaled image height size when the image width size is larger than the second selected screen width size, or / and the image height size is larger than the second selected screen height size;
[0112] An expansion demand analysis unit 16, configured to obtain a screen width size to be expanded and a screen height size to be expanded when the zoomed image width size is larger than the second selected screen width size, or / and the zoomed image height size is larger than the second selected screen height size;
[0113] an extended layout optimization unit 17, configured to perform screen extended layout optimization on the first selected screen set based on the screen width size and the screen height size to be extended, to obtain a third selected screen set, wherein the third selected screen set has a screen extended layout position label set;
[0114] The screen configuration unit 18 is used to retrieve the third selected screen set according to the screen extension layout position tag set, and perform screen extension configuration on the second selected screen.
[0115] Furthermore, the preliminary screen selection unit 12 includes the following execution steps:
[0116] Collecting an image display sample data set, wherein the image size of any image display sample data is the same as the screen size;
[0117] According to the image display sample data set, extracting an image pixel unit length record data set, a screen pixel unit length record data set and an image distortion rate record data set, wherein any one of the image pixel unit length record data is less than or equal to the screen pixel unit length record data;
[0118] Performing pixel unit length deviation analysis according to the image pixel unit length record data set, the screen pixel unit length record data set and the image distortion rate record data set to obtain a pixel unit length deviation threshold;
[0119] Based on the comparison between the screen pixel unit length list and the pixel unit length of the image to be displayed, a pixel unit length deviation characteristic value list is obtained;
[0120] According to the pixel unit length deviation feature value list, screens having a pixel unit length less than or equal to the pixel unit length deviation threshold, or / and a screen pixel unit length less than or equal to the pixel unit length of the image to be displayed are selected from the initial screen set and added into the first selected screen set.
[0121] Furthermore, the preliminary selection screen unit 12 further includes the following execution steps:
[0122] Calculating the pixel unit length deviations of the image pixel unit length recording data set and the screen pixel unit length recording data set in one-to-one correspondence to obtain a pixel unit length deviation data set;
[0123] Based on the image distortion rate threshold, the pixel unit length deviation data set is matched in combination with the image distortion rate record data set to obtain the pixel unit length deviation threshold.
[0124] Furthermore, the screen reselection unit 14 includes the following execution steps:
[0125] Extracting a first screen width size according to the screen width size set, and extracting a first screen height size according to the screen height size set, wherein the first screen width size corresponds to the first screen height size in one-to-one correspondence;
[0126] Calculating a first width dimension deviation between the first screen width dimension and the image width dimension;
[0127] Calculate a first height dimension deviation between the first screen height dimension and the image height dimension;
[0128] Calculate a first screen size deviation average of the first width size deviation and the first height size deviation;
[0129] The analysis is repeated until the mean value of the Nth screen size deviation is obtained;
[0130] Based on the first screen size deviation average value to the Nth screen size deviation average value, the first selected screen set is sorted by minimum value to obtain the second selected screen.
[0131] Furthermore, the screen reselection unit 14 further includes the following execution steps:
[0132] When the size deviation mean minimum value screen has multiple:
[0133] Extracting the minimum value of the first size deviation mean minimum screen width and the first size deviation mean minimum screen height of the screen with the first size deviation mean minimum value to obtain the first size deviation mean minimum screen feature size;
[0134] Until the minimum value of the screen width of the Mth size deviation mean minimum value screen and the screen height of the Mth size deviation mean minimum value screen are extracted to obtain the screen characteristic size of the Mth size deviation mean minimum value screen;
[0135] Based on the first size deviation mean minimum screen feature size up to the Mth size deviation mean minimum screen feature size, the first size deviation mean minimum screen is subjected to minimum value sorting to obtain the second selected screen.
[0136] Furthermore, the image scaling unit 15 includes the following execution steps:
[0137] Constructing a width size scaling interval according to the image width size and the second selected screen width size;
[0138] Constructing a height size scaling interval according to the image height size and the second selected screen height size;
[0139] Obtaining an image aspect ratio of the image width dimension and the image height dimension;
[0140] Gradual scaling of the image to be displayed according to a preset scaling step length based on the image aspect ratio, the width scaling interval and the height scaling interval to obtain a scaled digital image sequence;
[0141] Through a semantic deviation analysis network, the scaled digital image sequence is traversed, and semantic comparison is performed with the image to be displayed to obtain a semantic deviation coefficient sequence;
[0142] When the kth semantic deviation coefficient of the semantic deviation coefficient sequence is less than or equal to the semantic deviation coefficient threshold, and the k+1th semantic deviation coefficient is greater than the semantic deviation coefficient threshold, the scaled image width dimension and the scaled image height dimension corresponding to the kth semantic deviation coefficient are output.
[0143] Furthermore, the image scaling unit 15 further includes the following execution steps:
[0144] Extracting features of the image to be displayed through a first semantic feature extraction channel of the semantic deviation analysis network to obtain a first feature vector;
[0145] Performing feature extraction on the i-th scaled digital image of the scaled digital image sequence through a second semantic feature extraction channel of the semantic deviation analysis network to obtain a second feature vector, wherein the second semantic feature extraction channel and the first semantic feature extraction channel are twin convolutional neural networks;
[0146] According to the semantic deviation analysis channel, the deviation between the first feature vector and the second feature vector is calculated, and the i-th semantic deviation coefficient is output and added to the semantic deviation coefficient sequence.
[0147] Embodiment three:
[0148] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, a method for expanding the screen of a smart tablet is implemented.
[0149] Embodiment 4:
[0150] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600 on which a computer program 611 is stored. When the computer program 611 is executed by a processor, a method for expanding the screen of a smart tablet is implemented.
[0151] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0152] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0153] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0154] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0156] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.
[0157] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.
Claims
1. A method for expanding the screen of a smart tablet, characterized in that: include: Get the resolution of the image to be displayed, the pixel unit length of the image to be displayed, the screen resolution list, and the screen pixel unit length list; Traversing the screen pixel unit length list, comparing it with the pixel unit length of the image to be displayed, sorting the initial screen set, and obtaining a first selected screen set; Traversing the first selected screen set, unifying the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the pixel unit length of the screen, and obtaining an image width size and an image height size, a screen width size set, and a screen height size set; Based on the screen width size set and the screen height size set, the screen width size and the image height size are compared to sort the first selected screen set to obtain second selected screens; When the image width is larger than the second selected screen width, or / and the image height is larger than the second selected screen height, performing scaling optimization analysis on the image to be displayed to obtain a scaled image width and a scaled image height; When the width of the zoomed image is larger than the second selected screen width, or / and the height of the zoomed image is larger than the second selected screen height, obtaining a screen width and a screen height to be expanded; According to the screen width size to be expanded and the screen height size to be expanded, based on the screen width size set and the screen height size set, screen expansion layout optimization is performed on the first selected screen set to obtain a third selected screen set, wherein the third selected screen set has a screen expansion layout position label set; According to the screen extension layout position tag set, calling the third selected screen set, and performing screen extension configuration on the second selected screen; The process of traversing the screen pixel unit length list, comparing it with the pixel unit length of the image to be displayed, sorting the initial screen set, and obtaining the first selected screen set includes: Collecting an image display sample data set, wherein the image size of any image display sample data is the same as the screen size; According to the image display sample data set, extracting an image pixel unit length record data set, a screen pixel unit length record data set and an image distortion rate record data set, wherein any one of the image pixel unit length record data is less than or equal to the screen pixel unit length record data; Performing pixel unit length deviation analysis according to the image pixel unit length record data set, the screen pixel unit length record data set and the image distortion rate record data set to obtain a pixel unit length deviation threshold; Based on the comparison between the screen pixel unit length list and the pixel unit length of the image to be displayed, a pixel unit length deviation characteristic value list is obtained; According to the pixel unit length deviation feature value list, screens having a length less than or equal to the pixel unit length deviation threshold, or / and a screen pixel unit length less than or equal to the pixel unit length of the image to be displayed are selected from the initial screen set, and added into the first selected screen set; The pixel unit length deviation analysis is performed according to the image pixel unit length record data set, the screen pixel unit length record data set and the image distortion rate record data set to obtain the pixel unit length deviation threshold, including: Calculating the pixel unit length deviations of the image pixel unit length recording data set and the screen pixel unit length recording data set in one-to-one correspondence to obtain a pixel unit length deviation data set; Based on the image distortion rate threshold, the pixel unit length deviation data set is matched in combination with the image distortion rate record data set to obtain the pixel unit length deviation threshold; The step of comparing the screen width size set and the screen height size set with the image width size and the image height size, sorting the first selected screen set, and obtaining the second selected screen includes: Extracting a first screen width size according to the screen width size set, and extracting a first screen height size according to the screen height size set, wherein the first screen width size corresponds to the first screen height size in one-to-one correspondence; Calculating a first width dimension deviation between the first screen width dimension and the image width dimension; Calculate a first height dimension deviation between the first screen height dimension and the image height dimension; Calculate a first screen size deviation average of the first width size deviation and the first height size deviation; The analysis is repeated until the mean value of the Nth screen size deviation is obtained; Based on the first screen size deviation average value to the Nth screen size deviation average value, the first selected screen set is sorted by minimum value to obtain the second selected screen.
2. The method according to claim 1, characterized in that Based on the first screen size deviation average value to the Nth screen size deviation average value, performing minimum value sorting on the first selected screen set to obtain the second selected screen, further comprising: When the size deviation mean minimum value screen has multiple: Extracting the minimum value of the first size deviation mean minimum screen width and the first size deviation mean minimum screen height of the screen with the first size deviation mean minimum value to obtain the first size deviation mean minimum screen feature size; Until the minimum value of the screen width of the Mth size deviation mean minimum value screen and the screen height of the Mth size deviation mean minimum value screen are extracted to obtain the screen characteristic size of the Mth size deviation mean minimum value screen; Based on the first size deviation mean minimum screen feature size up to the Mth size deviation mean minimum screen feature size, the first size deviation mean minimum screen is subjected to minimum value sorting to obtain the second selected screen.
3. The method according to claim 1, characterized in that When the image width is larger than the second selected screen width, or / and the image height is larger than the second selected screen height, performing scaling optimization analysis on the image to be displayed to obtain a scaled image width and a scaled image height, including: Constructing a width size scaling interval according to the image width size and the second selected screen width size; Constructing a height size scaling interval according to the image height size and the second selected screen height size; Obtaining an image aspect ratio of the image width dimension and the image height dimension; Gradual scaling of the image to be displayed according to a preset scaling step length based on the image aspect ratio, the width scaling interval and the height scaling interval to obtain a scaled digital image sequence; Through a semantic deviation analysis network, the scaled digital image sequence is traversed, and semantic comparison is performed with the image to be displayed to obtain a semantic deviation coefficient sequence; When the kth semantic deviation coefficient of the semantic deviation coefficient sequence is less than or equal to the semantic deviation coefficient threshold, and the k+1th semantic deviation coefficient is greater than the semantic deviation coefficient threshold, the scaled image width dimension and the scaled image height dimension corresponding to the kth semantic deviation coefficient are output.
4. The method according to claim 3, characterized in that The scaled digital image sequence is traversed through a semantic deviation analysis network, and semantic comparison is performed with the image to be displayed to obtain a semantic deviation coefficient sequence, including: Extracting features of the image to be displayed through a first semantic feature extraction channel of the semantic deviation analysis network to obtain a first feature vector; Performing feature extraction on the i-th scaled digital image of the scaled digital image sequence through a second semantic feature extraction channel of the semantic deviation analysis network to obtain a second feature vector, wherein the second semantic feature extraction channel and the first semantic feature extraction channel are twin convolutional neural networks; According to the semantic deviation analysis channel, the deviation between the first feature vector and the second feature vector is calculated, and the i-th semantic deviation coefficient is output and added to the semantic deviation coefficient sequence.
5. A smart tablet screen expansion device, characterized in that: The method for implementing the screen expansion method of a smart tablet according to any one of claims 1 to 4 comprises: A data acquisition unit, the data acquisition unit is used to obtain the resolution of the image to be displayed, the pixel unit length of the image to be displayed, the screen resolution list, and the screen pixel unit length list; Preliminary screen unit selection, wherein the preliminary screen unit selection is used to traverse the screen pixel unit length list, compare with the pixel unit length of the image to be displayed, sort the initial screen set, and obtain a first selected screen set; a size unification unit, the size unification unit being used to traverse the first selected screen set, unify the screen resolution and the resolution of the image to be displayed according to the pixel unit length of the image to be displayed and the pixel unit length of the screen, and obtain an image width size and an image height size, a screen width size set and a screen height size set; a screen reselection unit, the screen reselection unit being used to sort the first selected screen set based on the screen width size set and the screen height size set, comparing with the image width size and the image height size, to obtain a second selected screen; An image scaling unit, wherein the image scaling unit is used to perform scaling optimization analysis on the image to be displayed to obtain a scaled image width size and a scaled image height size when the image width size is larger than the second selected screen width size, or / and the image height size is larger than the second selected screen height size; an expansion demand analysis unit, the expansion demand analysis unit being used for obtaining a screen width size to be expanded and a screen height size to be expanded when the width size of the scaled image is larger than the second selected screen width size, or / and the height size of the scaled image is larger than the second selected screen height size; an extended layout optimization unit, the extended layout optimization unit being configured to perform screen extended layout optimization on the first selected screen set based on the screen width size and the screen height size to be extended, to obtain a third selected screen set, wherein the third selected screen set has a screen extended layout position label set; A screen configuration unit, the screen configuration unit is used to call the third selected screen set according to the screen extension layout position label set, and perform screen extension configuration on the second selected screen.
6. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the smart tablet screen expansion method described in any one of claims 1-4.
7. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the smart tablet screen expansion method as described in any one of claims 1 to 4 is implemented.
