Image processing method and device, equipment and storage medium
By entering the screenshot data of the vehicle machine and screen feature data into the preset model, calculating the adaptation degree and adjusting the screenshot data of the vehicle machine, the screenshot data adaptation problem in the automation test of the vehicle machine is solved, and the debugging cost is reduced.
Patent Information
- Application Number
- CN202510001069.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-02
- Publication Date
- 2025-05-27
AI Technical Summary
In the automation test of the car machine UI, the adjusted car machine screenshots are difficult to apply to screens of different resolutions and sizes, resulting in high testing and debugging costs.
By obtaining the screenshot data of the current car machine and the screen feature data of the screen to be displayed, input it into the preset model, calculate the adaptability, and adjust the screenshot data of the car machine according to the adaptability to make it adaptable to different screens.
The adaptation of vehicle screenshot data is realized, reducing the debugging cost of vehicle UI automation testing.
Smart Images
Figure CN120045261A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the technical field of image processing, and particularly relates to an image processing method, apparatus, device, and storage medium. Background Art
[0002] With the continuous progress of automotive interaction technology, the diversity of in-vehicle functions has been significantly improved. Users can, according to their own needs, control the in-vehicle system to achieve in-vehicle functions such as driving and entertainment.
[0003] Currently, when conducting in-vehicle UI automated testing, it is usually necessary to use the OpenCV library to compare the restoration degree of some elements in the in-vehicle screenshot, and adjust the corresponding elements in the in-vehicle screenshot based on the comparison result. The in-vehicle screenshot adjusted by the above solution still cannot be applied to screens with different resolutions and sizes. Testers need to debug the adjusted in-vehicle screenshot to make it adapt to the screen before testing. Therefore, there is a problem of high debugging cost in in-vehicle UI automated testing. Summary of the Invention
[0004] Embodiments of this application provide an image processing method, apparatus, device, and storage medium, which can, to at least a certain extent, obtain in-vehicle screenshot data adapted to different screens, and reduce the debugging cost of in-vehicle UI automated testing.
[0005] Other features and advantages of this application will become apparent through the following detailed description, or will be partially learned through the practice of this application.
[0006] According to the first aspect of the embodiments of this application, an image processing method is provided, including:
[0007] Obtain the current in-vehicle screenshot data and the current screen feature data of the screen to be displayed;
[0008] Input the current in-vehicle screenshot data and the current screen feature data into a preset model to obtain the adaptation degree between the current in-vehicle screenshot data and the screen to be displayed output by the preset model;
[0009] Adjust the current in-vehicle screenshot data to be adapted to the screen to be displayed according to the adaptation degree.
[0010] In some embodiments, the adaptation degree is the sum of a plurality of first data, where the first data is the difference between each parameter index value of the current in-vehicle screenshot data and the corresponding parameter index value of the current screen feature data multiplied by the corresponding weight. Adjusting the current in-vehicle screenshot data to be adapted to the screen to be displayed according to the adaptation degree includes:
[0011] Determine whether the adaptation degree is greater than a first preset value;
[0012] When the adaptation degree is greater than the first preset value, determine the maximum value in the first data;
[0013] Adjust the parameter index value of the current in-vehicle screenshot data corresponding to the maximum value, and return the step of inputting the current in-vehicle screenshot data and the current screen feature data into the preset model until the adaptation degree is less than or equal to the first preset value.
[0014] In some embodiments, the parameter index values include color index values, screen resolution index values, and screen size index values.
[0015] In some embodiments, before inputting the current in-vehicle screenshot data and the current screen feature data into the preset model, the image processing method further includes:
[0016] Obtain historical in-vehicle screenshot data and historical screen feature data;
[0017] Reconstruct the low-frequency component and the high-frequency component of the historical in-vehicle screenshot data to obtain a new low-frequency component and a new high-frequency component respectively;
[0018] Aggregate the new low-frequency component and the new high-frequency component by using wavelet transform to obtain new historical in-vehicle screenshot data;
[0019] Train the initial model by using the new historical in-vehicle screenshot data and the historical screen feature data to obtain the preset model.
[0020] In some embodiments, reconstructing the low-frequency component and the high-frequency component of the historical in-vehicle screenshot data to obtain a new low-frequency component and a new high-frequency component respectively includes:
[0021] Determine a set of target pixel blocks from the low-frequency component of the historical in-vehicle screenshot data, where the similarity between each target pixel block in the set of target pixel blocks and the preset pixel block is greater than the second preset value;
[0022] Denoise each target pixel block by using the principal component analysis algorithm to obtain a new low-frequency component.
[0023] In some embodiments, reconstructing the low-frequency component and the high-frequency component of the historical in-vehicle screenshot data to obtain a new low-frequency component and a new high-frequency component respectively includes:
[0024] Divide the high-frequency component of the historical in-vehicle screenshot data into overlapping blocks of the same size;
[0025] Group the overlapping blocks according to the Euclidean distance between the overlapping blocks;
[0026] Determine the adaptive learning dictionary for each group by using singular value decomposition;
[0027] Determine the sparse coding of the high-frequency component by using the convex optimization algorithm;
[0028] Based on the adaptive learning dictionary and sparse coding, a new high-frequency component is obtained.
[0029] In some embodiments, the initial model is trained using the new historical in-vehicle infotainment (IVI) screenshot data and historical screen feature data to obtain a preset model, including:
[0030] Extract text feature data and page element feature data from the new historical IVI screenshot data;
[0031] Input the text feature data, page element feature data, and historical screen feature data into the initial model constructed by a feedforward neural network for training to obtain a preset model.
[0032] According to the second aspect of the embodiments of the present application, an image processing apparatus is provided, including:
[0033] A data acquisition module for acquiring current IVI screenshot data and current screen feature data of the screen to be displayed;
[0034] A fitness determination module for inputting the current IVI screenshot data and current screen feature data into the preset model to obtain the fitness of the current IVI screenshot data and the screen to be displayed output by the preset model;
[0035] An image adjustment module for adjusting the current IVI screenshot data to be adapted to the screen to be displayed according to the fitness.
[0036] According to the third aspect of the embodiments of the present application, an image processing device is provided, including a processor and a memory. The memory stores computer program instructions that can be executed by the processor. When the processor executes the computer program instructions, the steps of the method according to any one of the first aspects described above are implemented.
[0037] According to the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores computer program instructions. When the computer program instructions are executed by the processor, the processor is prompted to implement the steps of the method according to any one of the first aspects described above.
[0038] In the present application, by acquiring current IVI screenshot data and current screen feature data of the screen to be displayed; inputting the current IVI screenshot data and current screen feature data into the preset model to obtain the fitness of the current IVI screenshot data and the screen to be displayed output by the preset model; and adjusting the current IVI screenshot data to be adapted to the screen to be displayed according to the fitness. Through the technical solution provided by the present application, IVI screenshot data adapted to different screens can be obtained, reducing the debugging cost of IVI UI automated testing.
[0039] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application. Obviously, the drawings in the following description are only some embodiments of this application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:
[0041] Figure 1 A schematic flowchart of an image processing method in one embodiment is shown;
[0042] Figure 2 A schematic flowchart of an image processing method in another embodiment is shown;
[0043] Figure 3 A block diagram of an image processing apparatus in one embodiment is shown;
[0044] Figure 4 A schematic structural diagram of an image processing device in one embodiment is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0045] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part rather than all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.
[0046] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of this application. However, those skilled in the art will realize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of this application.
[0047] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0048] The flowchart shown in the accompanying drawings is only an exemplary illustration, and does not necessarily include all the content and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined. Therefore, the actual execution order may change according to the actual situation.
[0049] It should also be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned accompanying drawings of the present application are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that the objects used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described.
[0050] Figure 1 The flowchart of the image processing method in an embodiment is shown. As Figure 1 shown, a method for image processing is provided, and the method may include the following steps 101 to 103.
[0051] In step 101, current in-vehicle head unit screenshot data and current screen feature data of the screen to be displayed are acquired.
[0052] It can be understood that the in-vehicle head unit is the abbreviation of the in-vehicle infotainment product installed in the vehicle. The in-vehicle head unit screenshot refers to the screenshot of the in-vehicle infotainment product, such as the screenshot of the music playing interface, etc. The current in-vehicle head unit screenshot data refers to the in-vehicle head unit screenshot data that needs to be displayed on the screen to be displayed at the current moment.
[0053] The current screen feature data refers to the feature data of the screen to be displayed at the current moment, including data such as screen resolution characteristics, screen size characteristics, and screen interface colors.
[0054] In step 102, the current in-vehicle head unit screenshot data and the current screen feature data are input into a preset model, and the adaptation degree of the current in-vehicle head unit screenshot data to the screen to be displayed output by the preset model is obtained.
[0055] Among them, the preset model is trained based on historical in-vehicle head unit screenshot data and historical screen feature data. After the model is trained, it can be used to predict the adaptation degree of the current in-vehicle head unit screenshot data to the screen to be displayed.
[0056] In step 103, the current in-vehicle head unit screenshot data is adjusted to be adapted to the screen to be displayed according to the adaptation degree.
[0057] In some embodiments, the adaptation degree is the sum of a plurality of first data, where the first data is the difference between each parameter index value of the current in-vehicle head unit screenshot data and the corresponding parameter index value of the current screen feature data multiplied by the corresponding weight.
[0058] Among them, the parameter index values include color index values, screen resolution index values, and screen size index values.
[0059] It can be understood that before the preset model outputs the adaptation degree, it will assign indicators to the current in-vehicle infotainment system screenshot data and the current screen feature data according to the set rules to obtain one or more parameter index values corresponding to each style parameter, then calculate the similarity of each style parameter between the current in-vehicle infotainment system screenshot data and the current screen feature data according to the similarity calculation formula, and finally attach different weights to each style parameter and calculate the adaptation degree according to the adaptation degree calculation formula.
[0060] Among them, the similarity calculation formula can refer to the following formula 1:
[0061]
[0062] Among them, S i is the similarity of the i-th style parameter between the current in-vehicle infotainment system screenshot data and the current screen feature data, w ij is the j-th parameter index value of the i-th style parameter of the current in-vehicle infotainment system screenshot data, v ij is the j-th parameter index value of the i-th style parameter of the current screen feature data, and n is the total number of parameter index values of the i-th style parameter.
[0063] The adaptation degree calculation formula can refer to the following formula 2:
[0064]
[0065] Among them, C is the adaptation degree of the style between the current in-vehicle infotainment system screenshot data and the screen to be displayed, α i is the weight of the i-th style parameter, m is the total number of style parameters, α i S i is the first data.
[0066] A style parameter usually has different parameter index values. For example, for the color parameter, its general parameter indicators include the RGB three-color parameter indicators. The similarity between the current in-vehicle infotainment system screenshot data and the screen interface of the screen to be displayed is represented by calculating the differential distance of the parameter index values between the current in-vehicle infotainment system screenshot data and the current screen feature data. The larger the value of S i , the greater the differential distance of the parameter index values between the current in-vehicle infotainment system screenshot data and the current screen feature data, and the lower the similarity between the current in-vehicle infotainment system screenshot data and the screen interface.
[0067] For different screen interface requirements, the importance of each style parameter is different. Therefore, in the process of calculating the adaptation degree, different weights are applied to different style parameters.
[0068] According to the adaptability calculation formula, the greater the difference between the parameter index values of the current vehicle computer screenshot data and the current screen feature data, the lower the adaptability between the current vehicle computer screenshot data and the screen interface. Therefore, it is possible to determine whether the current vehicle computer screenshot data needs to be adjusted based on the adaptability.
[0069] In some embodiments, it can be determined whether the degree of adaptation is greater than a first preset value; when the degree of adaptation is greater than the first preset value, the maximum value in the first data is determined; the parameter index value of the current vehicle screenshot data corresponding to the maximum value is adjusted, and the step of inputting the current vehicle screenshot data and the current screen feature data into the preset model is returned until the degree of adaptation is less than or equal to the first preset value.
[0070] It can be understood that when the adaptability is greater than the first preset value, it can be determined that the adaptability between the current vehicle computer screenshot data and the screen interface is low, and the current vehicle computer screenshot data needs to be adjusted; when the adaptability is less than or equal to the first preset value, it can be determined that the adaptability between the current vehicle computer screenshot data and the screen interface is high, and the current vehicle computer screenshot data does not need to be adjusted.
[0071] When the degree of adaptation is greater than the first preset value, S i The larger the value of , the greater the difference distance between the parameter index value of the current screenshot data and the current screen feature data, and the lower the similarity between the current screenshot data and the screen interface. i The larger the value, the more important the parameter index value is. Therefore, when adjusting the current screenshot data, i S i The parameter index value corresponding to the maximum value in is adjusted. If the adaptation degree of the current screenshot data after adjustment is less than or equal to the first preset value, no further adjustment is made. Otherwise, the adjustment is continued. In this way, the adaptation degree between the current car screenshot data and the screen interface can be effectively and quickly improved. The adjusted current car screenshot data can be suitable for different screen resolutions, screen sizes, and screens to be displayed with different UE designs, and the result recognition of UI automation can be directly performed.
[0072] The embodiment of the present application obtains the current vehicle computer screenshot data and the current screen feature data of the screen to be displayed; inputs the current vehicle computer screenshot data and the current screen feature data into a preset model to obtain the adaptability of the current vehicle computer screenshot data output by the preset model and the screen to be displayed; and adjusts the current vehicle computer screenshot data to adapt to the screen to be displayed according to the adaptability. The technical solution provided by the present application can obtain vehicle computer screenshot data adapted to screens with different resolutions, different sizes and different UE designs, thereby reducing the debugging cost of vehicle computer UI automation testing.
[0073] Figure 2 FIG. 2 shows a flow chart of an image processing method in another embodiment.Figure 2 As shown in Figure 2 , the image processing method may further include the following steps:
[0074] Step 201, obtaining historical in-vehicle infotainment (IVI) screenshot data and historical screen feature data;
[0075] Step 202, reconstructing the low-frequency component and the high-frequency component of the historical IVI screenshot data to respectively obtain a new low-frequency component and a new high-frequency component;
[0076] Step 203, aggregating the new low-frequency component and the new high-frequency component by using wavelet transform to obtain new historical IVI screenshot data;
[0077] Step 204, training an initial model by using the new historical IVI screenshot data and the historical screen feature data to obtain a preset model.
[0078] It can be understood that the historical IVI screenshot data refers to the IVI screenshot data displayed on the screen before the current moment, and the screen can be the screen to be displayed or other screens. The historical screen feature data refers to the feature data of the screen before the current moment, including data such as screen resolution features, screen size features, and screen interface colors.
[0079] The low-frequency component generally refers to the part where the image intensity changes gently, such as large color blocks, and the high-frequency component generally refers to the part where the image intensity changes violently, such as the contour part.
[0080] In some embodiments, a set of target pixel blocks may be determined from the low-frequency component of the historical IVI screenshot data, where the similarity between each target pixel block in the set of target pixel blocks and a preset pixel block is greater than a second preset value; the principal component analysis algorithm is used to denoise each target pixel block to obtain a new low-frequency component.
[0081] During implementation, local pixel grouping processing may be performed on the pixel points of the low-frequency component to obtain local pixel blocks, and the unbiased estimation of the error is used to approximately represent the similarity between the local pixel blocks and the preset pixel block, so as to obtain multiple target pixel blocks with a similarity greater than the second preset value, that is, the set of target pixel blocks.
[0082] Each target pixel block in the set of target pixel blocks is traversed, and the principal component analysis algorithm is used to denoise each target pixel block in turn. By calculating the covariance matrix, an orthogonal transformation matrix is obtained, and then the dimensions containing little information in the target pixel block are removed in combination with the eigenvalue matrix to obtain a reconstructed low-frequency component.
[0083] In some embodiments, the high-frequency components of the historical in-vehicle infotainment system screenshot data can be divided into overlapping blocks of the same size; the overlapping blocks can be grouped according to the Euclidean distance between the overlapping blocks; an adaptive learning dictionary for each group can be determined through singular value decomposition; a sparse coding of the high-frequency components can be determined using a convex optimization algorithm; and a new high-frequency component can be obtained based on the adaptive learning dictionary and the sparse coding.
[0084] In the implementation process, overlapping blocks with similar or equal Euclidean distances can be grouped into the same group, and singular value decomposition can be performed on each group. The result of the singular value decomposition is used to construct an adaptive learning dictionary for each group. The atoms in the dictionary are composed of singular value vectors, and these vectors can effectively represent the characteristics of each group of overlapping blocks.
[0085] Through the split Bregman iteration algorithm in the convex optimization algorithm, the sparse coding of the high-frequency components can be calculated, and then the high-frequency components can be reconstructed using the adaptive learning dictionary and the sparse coding.
[0086] By using the principal component analysis algorithm to reconstruct the low-frequency components, and during the process of reconstructing the high-frequency components, the natural image is sparsely represented in the group domain, and the inherent local sparsity and non-local self-similarity of the natural image are clearly and effectively characterized in a unified manner. The high-frequency part of the historical in-vehicle infotainment system screenshot data can be reconstructed without being affected by noise. While effectively removing noise, the image details are retained, achieving high sparsity and high recovery quality, and improving the visual performance, peak signal-to-noise ratio, and structural similarity of the image.
[0087] In some embodiments, text feature data and page element feature data can be extracted from the new historical in-vehicle infotainment system screenshot data; the text feature data, page element feature data, and historical screen feature data are input into an initial model constructed by a feedforward neural network for training to obtain a preset model.
[0088] It can be understood that the feedforward neural network is a type of artificial neural network, adopting a one-way multi-layer structure. The 0th layer is called the input layer, the last layer is called the output layer, and the other intermediate layers are called hidden layers. The hidden layer can be one layer or multiple layers. Each hidden layer contains several neurons. Each neuron can receive the signals from the neurons in the previous layer and generate outputs to the next layer. There is no feedback in the entire network, and the signals propagate unidirectionally from the input layer to the output layer.
[0089] After feature - marking multiple text feature data, multiple page - element feature data, and multiple screen feature data, they are randomly divided into a training set, a validation set, and a test set according to a certain ratio, and the divided training set, validation set, and test set are labeled. In some embodiments, the ratio of the training set, the validation set, and the test set is 8:1:1. Among them, the training set is used to train the initial model, that is, to determine learning parameters such as the weights and biases of the initial model; the validation set is used to validate each model after multiple models are trained by the training set, record the model accuracy, and then select the model with the best effect and its corresponding parameters; the test set is used only once, that is, it is used to evaluate the final model after training is completed. It neither participates in the process of learning parameters nor participates in the process of hyperparameter selection, but is only used for model evaluation. Based on a feed - forward neural network, the initial model is supervised - trained by the training set, the obtained model is validated by the validation set, and the trained - completed model is evaluated by the test set. The hyperparameters are continuously adjusted until the accuracy meets the preset requirements to obtain a preset model.
[0090] The following introduces the device embodiments of the present application, which can be used to execute the image - processing method in the above - mentioned embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the embodiments of the above - mentioned image - processing method of the present application.
[0091] Figure 3 shows a block diagram of an image - processing device in an embodiment. As Figure 3 shown, the image - processing device according to the embodiment of the present application includes: a data - acquisition module 301, a fitness - prediction module 302, and an image - adjustment module 303. Among them, the data - acquisition module 301 is used to acquire the current in - vehicle infotainment (IVI) screenshot data and the current screen feature data of the screen to be displayed; the fitness - prediction module 302 is used to input the current IVI screenshot data and the current screen feature data into a preset model to obtain the fitness of the current IVI screenshot data and the screen to be displayed output by the preset model; the image - adjustment module 303 is used to adjust the current IVI screenshot data to be adapted to the screen to be displayed according to the fitness.
[0092] In some embodiments, the fitness is the sum of multiple first data. Among them, the first data is the difference between each parameter index value of the current IVI screenshot data and the corresponding parameter index value of the current screen feature data multiplied by the corresponding weight. The image - adjustment module 303 is further used to determine whether the fitness is greater than a first preset value; in the case where the fitness is greater than the first preset value, determine the maximum value in the first data; adjust the parameter index value of the current IVI screenshot data corresponding to the maximum value, and return to the step of inputting the current IVI screenshot data and the current screen feature data into the preset model until the fitness is less than or equal to the first preset value.
[0093] In some embodiments, the parameter index values include color index values, screen resolution index values, and screen size index values.
[0094] In some embodiments, the image processing apparatus further includes a model training module (not shown in the figure) configured to obtain historical in-vehicle screenshot data and historical screen feature data; reconstruct the low-frequency component and the high-frequency component of the historical in-vehicle screenshot data to respectively obtain a new low-frequency component and a new high-frequency component; aggregate the new low-frequency component and the new high-frequency component by using wavelet transform to obtain new historical in-vehicle screenshot data; and train an initial model by using the new historical in-vehicle screenshot data and the historical screen feature data to obtain a preset model.
[0095] In some embodiments, the model training module is further configured to determine a set of target pixel blocks from the low-frequency component of the historical in-vehicle screenshot data, wherein the similarity between each target pixel block in the set of target pixel blocks and a preset pixel block is greater than a second preset value; and denoise each target pixel block by using a principal component analysis algorithm to obtain a new low-frequency component.
[0096] In some embodiments, the model training module is further configured to divide the high-frequency component of the historical in-vehicle screenshot data into overlapping blocks of the same size; group the overlapping blocks according to the Euclidean distance between the overlapping blocks; determine an adaptive learning dictionary for each group by using singular value decomposition; determine a sparse coding of the high-frequency component by using a convex optimization algorithm; and obtain a new high-frequency component according to the adaptive learning dictionary and the sparse coding.
[0097] In some embodiments, the model training module is further configured to extract text feature data and page element feature data from the new historical in-vehicle screenshot data; and input the text feature data, the page element feature data, and the historical screen feature data into an initial model constructed by a feedforward neural network for training to obtain a preset model.
[0098] Based on the same inventive concept, an embodiment of the present application further provides an image processing device. Refer to Figure 4 , which shows a schematic structural diagram of the image processing device in the embodiment of the present application. The image processing device includes one or more memories 404, one or more processors 402, and at least one computer program (computer program instructions) stored on the memory 404 and executable on the processor 402. When the processor 402 executes the computer program, the method described above is implemented.
[0099] Among them, in Figure 4In [the figure], there is a bus architecture (represented by bus 400). Bus 400 may include any number of interconnected buses and bridges. Bus 400 links together various circuits including one or more processors represented by processor 402 and a memory represented by memory 404. Bus 400 may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and thus will not be further described herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 may be used to store data used by processor 402 when performing operations.
[0100] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are executed by a processor, the processor is caused to implement the steps of the method as described above.
[0101] Based on the same inventive concept, an embodiment of the present application provides a computer program product including a computer program. When the computer program product is executed by a processor, the processor is caused to implement the steps of the method as described above.
[0102] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or code on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination thereof. In addition, each functional unit may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.
[0103] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.
[0104] The units described as separate components may or may not be physically separated. The components serving as control devices may or may not be physical units, that is, they can be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0105] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store computer program instructions.
[0106] The above is only the embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.
Claims
1. An image processing method, characterized in that: include: Obtain the current vehicle computer screenshot data and the current screen feature data of the screen to be displayed; Inputting the current vehicle computer screenshot data and the current screen feature data into a preset model to obtain the compatibility between the current vehicle computer screenshot data output by the preset model and the screen to be displayed; The current vehicle computer screenshot data is adjusted to be compatible with the screen to be displayed according to the degree of adaptability.
2. The image processing method according to claim 1, characterized in that: The adaptability is the sum of multiple first data, wherein the first data is the difference between each parameter index value of the current vehicle computer screenshot data and the corresponding parameter index value of the current screen feature data multiplied by the corresponding weight, and adjusting the current vehicle computer screenshot data to adapt to the screen to be displayed according to the adaptability includes: Determining whether the degree of adaptation is greater than a first preset value; When the degree of adaptation is greater than the first preset value, determining a maximum value in the first data; Adjust the parameter index value of the current vehicle screenshot data corresponding to the maximum value, and return to the step of inputting the current vehicle screenshot data and the current screen feature data into the preset model until the degree of adaptation is less than or equal to the first preset value.
3. The image processing method according to claim 2, characterized in that: The parameter index values include a color index value, a screen resolution index value, and a screen size index value.
4. The image processing method according to claim 1, characterized in that: Before inputting the current vehicle computer screenshot data and the current screen feature data into the preset model, the method further includes: Obtain historical vehicle screenshot data and historical screen feature data; Reconstructing the low-frequency component and the high-frequency component of the historical vehicle computer screenshot data to obtain a new low-frequency component and a new high-frequency component accordingly; Aggregating the new low-frequency component and the new high-frequency component using wavelet transform to obtain new historical vehicle computer screenshot data; The new historical vehicle screenshot data and the historical screen feature data are used to train the initial model to obtain the preset model.
5. The image processing method according to claim 4, characterized in that: The reconstructing the low-frequency component and the high-frequency component of the historical vehicle computer screenshot data to obtain a new low-frequency component and a new high-frequency component accordingly includes: Determine a target pixel block set from the low-frequency components of the historical vehicle computer screenshot data, wherein the similarity between each target pixel block in the target pixel block set and the preset pixel block is greater than a second preset value; Each target pixel block is denoised using a principal component analysis algorithm to obtain the new low-frequency component.
6. The image processing method according to claim 4, characterized in that: The reconstructing the low-frequency component and the high-frequency component of the historical vehicle computer screenshot data to obtain a new low-frequency component and a new high-frequency component accordingly includes: Dividing the high-frequency components of the historical vehicle computer screenshot data into overlapping blocks of the same size; Grouping the overlapping blocks according to the Euclidean distances between the overlapping blocks; Determine the adaptive learning dictionary for each group by singular value decomposition; Determining the sparse coding of the high frequency component using a convex optimization algorithm; The new high-frequency component is obtained according to the adaptive learning dictionary and the sparse coding.
7. The image processing method according to claim 4, characterized in that: The using the new historical vehicle screenshot data and the historical screen feature data to train the initial model to obtain the preset model includes: Extracting text feature data and page element feature data from the new historical vehicle computer screenshot data; The text feature data, the page element feature data and the historical screen feature data are input into an initial model constructed by a feedforward neural network for training to obtain the preset model.
8. An image processing device, characterized in that: include: A data acquisition module is used to acquire the current vehicle computer screenshot data and the current screen feature data of the screen to be displayed; A compatibility determination module, used for inputting the current vehicle-mounted screenshot data and the current screen feature data into a preset model, and obtaining the compatibility between the current vehicle-mounted screenshot data output by the preset model and the screen to be displayed; The image adjustment module is used to adjust the current vehicle computer screenshot data to be compatible with the screen to be displayed according to the adaptability.
9. An image processing device, comprising a processor and a memory, characterized in that: The memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, prompt the processor to implement the steps of the method according to any one of claims 1 to 7.