CN113515246A - Electronic ink screen display control method, device, equipment and storage medium - Google Patents
Electronic ink screen display control method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113515246A CN113515246A CN202110536133.0A CN202110536133A CN113515246A CN 113515246 A CN113515246 A CN 113515246A CN 202110536133 A CN202110536133 A CN 202110536133A CN 113515246 A CN113515246 A CN 113515246A
- Authority
- CN
- China
- Prior art keywords
- content
- frame
- optimization
- processed
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Human Computer Interaction (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the application discloses a display control method, a display control device, display control equipment and a storage medium for an electronic ink screen. According to the technical scheme, the content recognition module is used for recognizing the content of the frame to be processed in the display waiting queue in the image processor, the content type of the frame to be processed is determined, the content optimization strategy of the frame to be processed is determined based on the content type, the content of the frame to be processed is optimized according to the determined content optimization strategy, the frame to be displayed suitable for being displayed on the electronic ink screen is obtained, the parallel processing capacity of the image processor is used, the display measurement and calculation delay of image processing is reduced, the readability of the display of the electronic ink screen is effectively improved, and the user experience is optimized.
Description
Technical Field
The embodiment of the application relates to the technical field of display, in particular to a display control method, device and equipment for an electronic ink screen and a storage medium.
Background
The electronic ink screen technology utilizes the electrophoresis technology to realize the display of pictures, and the display effect of the screen is very close to that of the traditional paper, so the screen is also called as 'electronic paper'. Electronic ink is generally made of a thin film composed of a plurality of microcapsules, in which pigment particles having different charges are suspended, and in an initial state, when an electric field in a certain direction is applied, the corresponding pigment particles are pushed to the top, and the microcapsules show different colors, and the microcapsules having different colors constitute various characters and patterns.
Due to the nature of electronic ink, most electronic ink screens only support 255 levels of gray scale display. When the method is used for dealing with the display content which is not subjected to color optimization on the electronic ink screen, the readability is reduced, and the user experience is influenced.
Disclosure of Invention
The embodiment of the application provides a display control method, a display control device, display control equipment and a storage medium for an electronic ink screen, so that the content to be displayed is optimized, the readability is improved, and the user experience is optimized.
In a first aspect, an embodiment of the present application provides an electronic ink screen display control method, including:
utilizing a trained content identification model in an image processor to identify the content of a frame to be processed in a display waiting queue so as to determine the content type of the frame to be processed;
determining a content optimization strategy for the frame to be processed based on the content type, wherein different content types correspond to different content optimization strategies, and the content optimization strategies are used for indicating an optimization mode for the frame to be processed;
and according to the determined content optimization strategy, performing content optimization on the frame to be processed to obtain a frame to be displayed, and displaying the frame to be displayed in an electronic ink screen.
Further, the content type comprises a scene type and/or an object type;
the method for identifying the content of the frame to be processed in the display waiting queue by using the trained content identification model in the image processor to determine the content type of the frame to be processed comprises the following steps:
utilizing a trained content recognition model in an image processor to perform scene content recognition on a frame to be processed in a display waiting queue so as to determine the scene type in the frame to be processed; and/or
And utilizing the trained content recognition model in the image processor to perform object content recognition on the frames to be processed in the display waiting queue so as to determine the object types in the frames to be processed.
Further, the content optimization strategy comprises a scene optimization strategy and/or an object content optimization strategy, the scene optimization strategy is used for indicating an optimization mode of the scene content of the frame to be processed, and the object optimization strategy is used for indicating an optimization mode of the object content of the frame to be processed;
the determining a content optimization policy for the frame to be processed based on the content type includes:
determining that the content optimization strategy for the frame to be processed is a scene optimization strategy based on the content type as a scene type; and/or
And determining the content optimization strategy of the frame to be processed as an object optimization strategy based on the content type as an object type.
Further, the scene type includes a text scene type, an image scene type and/or an image-text scene type, and correspondingly, the scene optimization policy includes a text scene optimization policy, an image scene optimization policy and/or an image-text scene optimization policy, and the image-text scene optimization policy is used to instruct that the text scene optimization policy is adopted for the text scene content in the frame to be processed, and the image scene optimization policy is adopted for the image scene content in the frame to be processed;
the object type comprises an entity object type and/or a graphic object type, and correspondingly, the object optimization strategy comprises an entity object optimization strategy and/or a graphic object optimization strategy.
Further, the content optimization of the frame to be processed based on the determined content optimization policy to obtain a frame to be displayed includes:
based on the determined scene optimization strategy, performing content optimization on the scene content in the frame to be processed to obtain a frame to be displayed after the scene optimization; and/or
And based on the determined object optimization strategy, performing content optimization on the object content in the frame to be processed to obtain a frame to be displayed after the content optimization.
Further, the optimization includes one or more of color replacement, color inversion, edge delineation, contrast enhancement, edge enhancement, and image sharpening.
Further, the method for controlling display of the electronic ink screen further includes:
determining a software strategy data packet corresponding to a software image frame based on the software image frame to be displayed, wherein the software strategy data packet records the content type corresponding to the software image frame;
and determining the corresponding content type when the content of the frame to be processed is identified based on the content type corresponding to the software strategy data packet.
In a second aspect, an embodiment of the present application provides an electronic ink screen display control apparatus, including a content identification module, a policy determination module, and a content optimization module, where:
the content identification module is used for identifying the content of the frame to be processed in the display waiting queue by utilizing a trained content identification model in the image processor so as to determine the content type of the frame to be processed;
the policy determining module is configured to determine a content optimization policy for the frame to be processed based on the content type, where different content types correspond to different content optimization policies, and the content optimization policy is used to indicate an optimization manner for the frame to be processed;
and the content optimization module is used for optimizing the content of the frame to be processed according to the determined content optimization strategy to obtain the frame to be displayed and displaying the frame to be displayed in the electronic ink screen.
Further, the content type comprises a scene type and/or an object type;
the content identification module is specifically configured to:
utilizing a trained content recognition model in an image processor to perform scene content recognition on a frame to be processed in a display waiting queue so as to determine the scene type in the frame to be processed; and/or
And utilizing the trained content recognition model in the image processor to perform object content recognition on the frames to be processed in the display waiting queue so as to determine the object types in the frames to be processed.
Further, the content optimization strategy comprises a scene optimization strategy and/or an object content optimization strategy, the scene optimization strategy is used for indicating an optimization mode of the scene content of the frame to be processed, and the object optimization strategy is used for indicating an optimization mode of the object content of the frame to be processed;
the policy determination module is specifically configured to:
determining that the content optimization strategy for the frame to be processed is a scene optimization strategy based on the content type as a scene type; and/or
And determining the content optimization strategy of the frame to be processed as an object optimization strategy based on the content type as an object type.
Further, the scene type includes a text scene type, an image scene type and/or an image-text scene type, and correspondingly, the scene optimization policy includes a text scene optimization policy, an image scene optimization policy and/or an image-text scene optimization policy, and the image-text scene optimization policy is used to instruct that the text scene optimization policy is adopted for the text scene content in the frame to be processed, and the image scene optimization policy is adopted for the image scene content in the frame to be processed;
the object type comprises an entity object type and/or a graphic object type, and correspondingly, the object optimization strategy comprises an entity object optimization strategy and/or a graphic object optimization strategy.
Further, the content optimization module is specifically configured to:
based on the determined scene optimization strategy, performing content optimization on the scene content in the frame to be processed to obtain a frame to be displayed after the scene optimization; and/or
And based on the determined object optimization strategy, performing content optimization on the object content in the frame to be processed to obtain a frame to be displayed after the content optimization.
Further, the optimization includes one or more of color replacement, color inversion, edge delineation, contrast enhancement, edge enhancement, and image sharpening.
Further, the apparatus further comprises a scheme determining module configured to:
determining a software strategy data packet corresponding to a software image frame based on the software image frame to be displayed, wherein the software strategy data packet records the content type corresponding to the software image frame;
and determining the corresponding content type when the content of the frame to be processed is identified based on the content type corresponding to the software strategy data packet.
In a third aspect, an embodiment of the present application provides an electronic ink screen display control apparatus, including: a memory and one or more processors;
the memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the electronic ink screen display control method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the method for controlling display of an electronic ink screen according to the first aspect.
According to the embodiment of the application, the content recognition module is used for recognizing the content of the frame to be processed in the display waiting queue in the image processor, the content type of the frame to be processed is determined, the content optimization strategy of the frame to be processed is determined based on the content type, the content of the frame to be processed is optimized according to the determined content optimization strategy, the frame to be displayed suitable for being displayed on the electronic ink screen is obtained, the parallel processing capacity of the image processor is used, the display measuring and calculating delay of image processing is reduced, the readability of the display of the electronic ink screen is effectively improved, and the user experience is optimized.
Drawings
Fig. 1 is a flowchart of a display control method for an electronic ink screen according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating another method for controlling display of an electronic ink screen according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a display control device of an electronic ink screen according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic ink screen display control device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Fig. 1 is a flowchart of an electronic ink screen display control method provided in an embodiment of the present application, where the electronic ink screen display control method provided in an embodiment of the present application may be executed by an electronic ink screen display control device, and the electronic ink screen display control device may be implemented in hardware and/or software and integrated in an electronic ink screen display control apparatus (e.g., an electronic reader based on an electronic ink screen).
The following description will be given by taking an example of the method for the electronic ink screen display control device to execute the electronic ink screen display control. Referring to fig. 1, the electronic ink screen display control method includes:
s101: and utilizing the trained content recognition model in the image processor to perform content recognition on the frames to be processed in the display waiting queue so as to determine the content type in the frames to be processed.
In the configuration of the display control device for an electronic ink screen provided in this embodiment, a content recognition model trained in advance is configured in an image processor, and the content recognition model is used for performing content recognition processing on a frame to be processed according to a set content analysis scheme, and outputting content included in the frame to be processed and a corresponding content type.
Illustratively, image frames waiting to be displayed are sequentially extracted from a display waiting queue of the electronic ink screen, and the extracted image frames are used as frames to be processed for secondary content analysis of the frames to be processed.
Further, the frame to be processed is input into a content identification model, the content identification model identifies the content of the extracted frame to be processed in an image processing unit (GPU) according to a set content analysis scheme, and the content type corresponding to the frame to be processed is determined according to the identified content.
The content analysis scheme provided by the implementation is used for indicating a mode for identifying and analyzing the content in the frame to be processed, and determining the content type of the frame to be processed according to the identified content. Under different content analysis schemes, the targets for which the content recognition model performs recognition analysis on the frame to be processed are different, wherein the target may be a scene (e.g., a text scene, an image scene, a graphics context scene, etc.), an object (e.g., a solid object, a graphics context object, etc.), and the like in the frame to be displayed.
For example, the content identification model identifies and analyzes a scene in the frame to be processed, identifies scene content contained in the frame to be processed, and determines a scene content type corresponding to the content in the frame to be processed based on the identified scene content. Or the content identification model identifies and analyzes the object in the frame to be processed, identifies the object content contained in the frame to be processed, and determines the object content type corresponding to the content in the frame to be processed based on the identified object content. The content identification model may also perform identification analysis on the scene in the frame to be processed according to the content analysis scheme, identify the scene content contained in the frame to be processed, determine the scene content type corresponding to the content in the frame to be processed, further perform identification analysis on the object in the frame to be processed according to the object content analysis scheme applicable to the scene content type under the determined scene content type, identify the object content contained in the frame to be processed, and determine the object content type corresponding to the content in the frame to be processed based on the identified object content, thereby implementing more accurate content identification analysis. For example, the content type of the current frame to be processed is identified as image-text mixed content/plain text/plain image, and further the contents of human face/animals and plants and the like in the frame to be processed are identified, so as to facilitate the subsequent more detailed content optimization strategy adaptation.
S102: and determining a content optimization strategy for the frame to be processed based on the content type, wherein different content types correspond to different content optimization strategies, and the content optimization strategies are used for indicating an optimization mode for the frame to be processed.
Illustratively, after the content type of the frame to be processed is determined, a content optimization strategy corresponding to content optimization of the frame to be processed is determined according to the content type corresponding to the frame to be processed. The content optimization strategy is used for indicating an optimization mode of the content of the frame to be processed, and different content types correspond to different content optimization strategies.
It can be understood that, for frames to be processed corresponding to different content types, where the content to be displayed is different, a suitable content optimization manner is predetermined for the different content types, a content optimization policy is set based on the corresponding content optimization manner, and the content optimization policies corresponding to the different content types are recorded.
S103: and according to the determined content optimization strategy, performing content optimization on the frame to be processed to obtain a frame to be displayed, and displaying the frame to be displayed in an electronic ink screen.
Illustratively, according to the determined content optimization strategy, content optimization is performed on the frame to be processed, so as to obtain the frame to be displayed after content optimization. Wherein the content optimization strategy indicates the optimization mode of the content, which comprises one or more of color replacement, color inversion, edge tracing, contrast enhancement, edge enhancement and image sharpening. That is, the content optimization method indicated by one content optimization policy may be a single content optimization method, or may be a combination of multiple content optimization methods. For example, for a content type in a book or text scene, the indicated content optimization strategy may be color replacement or color inversion, and for a content type in an image, video or movie scene, the indicated content optimization strategy may be a combination of contrast enhancement, edge enhancement and image sharpening.
Furthermore, after the frame to be displayed is obtained by optimizing the content of the frame to be processed, the electronic ink screen can be controlled to display the frame to be displayed, or the frame to be displayed is placed back into the display waiting queue according to the position of the frame to be processed in the display waiting queue to wait for the frame to be displayed in the electronic ink screen.
In one possible embodiment, the frames to be processed may be globally optimized based on the determined content optimization policy, that is, the frames to be processed may be subjected to a unified content optimization process. In a possible embodiment, the frame to be processed may be locally optimized based on the determined content optimization policy, for example, content optimization is performed on the content identified on the frame to be processed according to the determined content optimization policy, so as to obtain the frame to be displayed after content optimization, thereby implementing local content optimization on the frame to be processed. The content types corresponding to different contents on one frame to be processed can be respectively identified, different content optimization strategies are determined based on the different content types, the corresponding content optimization strategies are executed aiming at the different types of contents on the same frame to be processed, different content optimization modes are executed on different positions of the frame to be processed, the frame to be displayed after content optimization is obtained, and finer content optimization of the frame to be processed is realized.
In the image processor, the content recognition module is used for recognizing the content of the frame to be processed in the display waiting queue, the content type of the frame to be processed is determined, the content optimization strategy of the frame to be processed is determined based on the content type, and the content of the frame to be processed is optimized according to the determined content optimization strategy, so that the frame to be displayed suitable for being displayed on the electronic ink screen is obtained.
On the basis of the foregoing embodiments, fig. 2 is a flowchart of another electronic ink screen display control method provided in an embodiment of the present application, which is an embodiment of the foregoing electronic ink screen display control method. Referring to fig. 2, the electronic ink screen display control method includes:
s201: and extracting the frame to be processed from the display waiting queue.
The frame to be processed is extracted from a display waiting queue in an electronic ink screen image processor, is synthesized in a display frame synthesizer of the electronic ink screen and is added to the image frame to be displayed in the display waiting queue. According to the scheme, the image frames in the display waiting queue are extracted as the frames to be processed, the frames to be displayed are obtained after secondary content analysis and content optimization are carried out, and then the frames to be displayed are placed back to the display waiting queue to be displayed.
Specifically, according to the order of adding the image frames to the display waiting queue, the image frames which are not optimized in content are extracted from the display waiting queue as the frames to be processed.
In the prior art, a scheme of performing color/resource replacement on content to be displayed by modifying an internal drawing control exists, but the performance requirement of drawing display is high, while the processing logic in the prior art depends on a central processing unit to judge and measure the content, so that the processing sacrifices much display speed, and the design of the central processing unit is not suitable for the processing scene of the frame content actually.
It can be understood that the hardware design of the image processor is suitable for a large amount of parallel computation, the data amount of the frame content is large, the scene that the parallel processing does not affect the result between each frame to be processed is very suitable, and basically, no extra display measurement delay exists on the system. On the other hand, as the frame to be processed is the frame to be updated to the screen, the content on the frame to be processed can be considered as the final result of display, thereby reducing the situation of carrying out unnecessary optimization on a non-visible area (overlapping/shielding), causing loss in performance, and better improving the display effect of the electronic ink screen on the premise of ensuring the display speed.
S202: and utilizing the trained content recognition model in the image processor to perform content recognition on the frames to be processed in the display waiting queue so as to determine the content type in the frames to be processed.
The content identification model provided by this embodiment is used to identify the content of the frame to be processed and output the content type corresponding to the frame to be processed. The content recognition model is built based on a neural network, and model training is carried out on the content recognition model by means of the neural network, machine learning and the like. The content included in the training sample used for training the content recognition model and the content type corresponding to the training sample are recorded, and when the content recognition model is trained, the content included in the training sample and the corresponding content type are used as output, and the training sample is used as input, so that the content recognition model is trained. And a content analysis scheme for identifying the content of the frame to be processed is recorded in the trained content identification model. After the training of the content recognition model is completed, the content recognition model is transplanted to the electronic ink screen display control device, and more specifically, the content recognition model is transplanted to an image processor of the electronic ink screen display control device. After the frame to be processed is input into the content identification model, the content identification analysis is carried out on the frame to be processed through the content identification model in the image processor, and the content contained in the frame to be processed and the corresponding content type are output by the image processor. Wherein the training sample can be provided by cloud big data.
The content type provided by the embodiment includes a scene type and/or an object type. The content contained in the training sample and the frame to be processed comprises scene content and/or object content, further, the scene content comprises text scene content, image scene content and/or image-text scene content, and the object content comprises entity object content and/or image-text object content. Correspondingly, the scene type comprises a text scene type, an image scene type and/or a graphics context scene type, and the object type comprises an entity object type and/or a graphics context object type.
The content analysis scheme includes a scene analysis scheme and an object analysis scheme. The scene analysis scheme is used for indicating the scene content contained in the frame to be processed to be identified and analyzed, and determining the scene type corresponding to the frame to be processed. The object analysis scheme is used for indicating the object content contained in the frame to be processed to be identified and analyzed, and determining the object type corresponding to the frame to be processed. The specific content analysis scheme of the frame to be processed may be determined as a scene analysis scheme or an object analysis scheme by default or according to the setting of a user, or the file type (text, graphics, characters, plants, cartoons, etc.) of the source file may be determined according to the type identifier of the source file of the frame to be processed, and the corresponding content analysis scheme may be determined according to the file type.
In one possible embodiment, where the frame to be processed is a software image frame, the software image frame that may need to be displayed determines the particular content analysis scheme for the frame to be processed. Based on this, when the frame to be processed is determined to be a software image frame, before performing content identification on the frame to be processed in the display waiting queue, the method further includes:
determining a software strategy data packet corresponding to a software image frame based on the software image frame to be displayed, wherein the software strategy data packet records the content type corresponding to the software image frame; and determining the corresponding content type when the content of the frame to be processed is identified based on the content type corresponding to the software strategy data packet.
Specifically, a database is established in advance for software (for example, third-party software), a software policy data packet corresponding to each software and content optimization policies corresponding to different content types are recorded in the database, and the software policy data packet records the corresponding software and the content types corresponding to the software image frames. The software strategy data packet records corresponding software in a packet name (primary key) mode, and can be matched with the corresponding software strategy data packet according to the packet name (primary key) corresponding to the software.
When the frame to be processed comes from the software, the corresponding software strategy data packet is determined according to the packet name (primary key) corresponding to the software, and the corresponding content type when the content of the frame to be processed is identified is determined according to the software strategy data packet, namely, the corresponding content analysis scheme when the content identification model identifies the content of the frame to be processed is determined. For example, when the content displayed by the third-party software is mainly the content of different scenes such as text, image-text mixed arrangement and the like, the content type recorded in the software strategy data packet corresponding to the third-party software is the scene type, and the content identification model identifies the content of the frame to be processed based on the scene analysis scheme; and when the content displayed by the third-party software is mainly the content of different objects such as human faces, animals and plants, entity models, texts, cartoons, drawings and the like, the content type recorded in the software strategy data packet corresponding to the third-party software is the object type, and the content identification model identifies the content of the frame to be processed based on the object analysis scheme.
In a possible embodiment, when the content analysis scheme of the frame to be processed is a scene analysis scheme, performing content identification on the frame to be processed specifically includes: and utilizing the trained content recognition model in the image processor to perform scene content recognition on the frames to be processed in the display waiting queue so as to determine the scene types in the frames to be processed.
Specifically, the frame to be processed is input into a content recognition model, and the content recognition model performs scene content recognition on the frame to be processed by using a trained content recognition model in an image processor so as to determine the scene type in the frame to be processed. When the content recognition model is trained, the training samples of the content recognition model are marked with corresponding scene content and corresponding scene types (including character scene types, image scene types and/or image-text scene types).
In a possible embodiment, when the content analysis scheme of the frame to be processed is an object analysis scheme, performing content identification on the frame to be processed specifically includes: and utilizing the trained content recognition model in the image processor to perform object content recognition on the frames to be processed in the display waiting queue so as to determine the object types in the frames to be processed.
Specifically, the frame to be processed is input into the content recognition model, and the content recognition model performs object content recognition on the frame to be processed by using the trained content recognition model in the image processor, so as to determine the object type in the frame to be processed. When the content recognition model is trained, the training sample of the content recognition model is marked with corresponding object content and a corresponding object type (including an entity object type and/or a graph object type).
Optionally, in this embodiment, a content recognition model for performing recognition analysis based on the scene analysis scheme and the object analysis scheme may be trained respectively, or a content recognition model for performing recognition analysis based on the scene analysis scheme and the object analysis scheme may be trained directly, or a content recognition model for performing recognition analysis based on the scene analysis scheme and then performing recognition analysis based on the object analysis scheme may be trained.
S203: and determining a content optimization strategy for the frame to be processed based on the content type, wherein different content types correspond to different content optimization strategies, and the content optimization strategies are used for indicating an optimization mode for the frame to be processed.
The content optimization strategy provided by the embodiment comprises a scene optimization strategy and/or an object content optimization strategy. The scene optimization strategy is used for indicating an optimization mode of the scene content of the frame to be processed, and the object optimization strategy is used for indicating an optimization mode of the object content of the frame to be processed.
Further, the optimization provided by the present embodiment includes one or more of color replacement, color inversion, edge delineation, contrast enhancement, edge enhancement, and image sharpening. Different optimization manners or a combination of multiple optimization manners can be set for different content optimization strategies.
In a possible embodiment, when determining that the content type of the frame to be processed is a scene type, based on the content type, determining a content optimization policy for the frame to be processed, specifically: and determining the content optimization strategy of the frame to be processed as a scene optimization strategy based on the content type as a scene type.
The scene type provided by the embodiment includes a text scene type, an image scene type and/or an image-text scene type, the scene optimization strategy includes a text scene optimization strategy, an image scene optimization strategy and/or an image-text scene optimization strategy, and the text scene type, the image-text scene optimization strategy, the image scene optimization strategy and the image-text scene optimization strategy are in one-to-one correspondence.
The character scene optimization strategy is used for indicating character content optimization of character scene contents in the frame to be processed, the image scene optimization strategy is used for indicating image content optimization of image scene contents in the frame to be processed, the image-text scene optimization strategy is used for indicating that the character scene contents in the frame to be processed adopt the character scene optimization strategy, and the image scene contents in the frame to be processed adopt the image scene optimization strategy.
And when the content type is determined to be the scene type, determining the content optimization strategy of the frame to be processed to be the scene optimization strategy. Specifically, when the content types are respectively a text scene type, an image scene type, and an image-text scene type, the corresponding content optimization strategies are respectively a text scene optimization strategy, an image scene optimization strategy, and an image-text scene optimization strategy.
In a possible embodiment, when determining that the content type of the frame to be processed is the object type, determining a content optimization policy for the frame to be processed based on the content type specifically includes: and determining the content optimization strategy of the frame to be processed as an object optimization strategy based on the content type as an object type.
The object type provided by this embodiment includes an entity object type and/or a graphics object type, the object optimization policy includes an entity object optimization policy and/or a graphics object optimization policy, and the entity object type, the graphics object type, the entity object optimization policy, and the graphics object optimization policy correspond to each other one to one.
The entity object optimization strategy is used for indicating entity content optimization of entity object content in the frame to be processed, and the image-text object optimization strategy is used for indicating image-text content optimization of image-text object content in the frame to be processed.
S204: and according to the determined content optimization strategy, performing content optimization on the frame to be processed to obtain a frame to be displayed, and displaying the frame to be displayed in an electronic ink screen.
The content optimization strategy provided by this embodiment includes a scene optimization strategy and an object optimization strategy, and for the scene optimization strategy, performing content optimization on the frame to be processed specifically includes: and based on the determined scene optimization strategy, performing content optimization on the scene content in the frame to be processed to obtain a frame to be displayed after the scene optimization.
Specifically, the scene optimization strategy provided by this embodiment includes a text scene optimization strategy, an image scene optimization strategy, and a graphics scene optimization strategy. Wherein the text scene optimization strategy indicates that color replacement and/or color reversal processing is performed on the whole content or text scene content (such as books, texts and the like) in the frame to be processed; the image scene optimization strategy indicates that the whole content or the image scene content (such as images, videos, movies and the like) in the frame to be processed is processed by one or more combinations of contrast enhancement, edge enhancement and image sharpening; the image-text scene optimization strategy indicates that the image scene content in the frame to be processed is subjected to one or more combinations of contrast enhancement, edge enhancement and image sharpening.
For the object optimization strategy, the content optimization of the frame to be processed specifically includes: and based on the determined object optimization strategy, performing content optimization on the object content in the frame to be processed to obtain a frame to be displayed after the content optimization.
And according to the object optimization strategy, optimizing the content of the object content in the frame to be processed, and taking the optimized frame to be processed as the frame to be displayed, so that the electronic ink screen can be controlled to display the frame to be displayed, or the frame to be displayed is added into a display waiting queue to wait for being displayed on the electronic ink screen.
Specifically, the scene optimization strategy provided by this embodiment includes an object optimization strategy including an entity object optimization strategy and a graphics object optimization strategy. The entity object optimization strategy indicates that the whole content or the entity object content in the frame to be processed is subjected to one or more combinations of contrast enhancement, edge enhancement and image sharpening; the teletext object optimization strategy indicates one or more combinations of color replacement, color inversion, edge delineation (edge identification and delineation) of the entire content or teletext object content in the frame to be processed, and one or more combinations of contrast enhancement, edge enhancement, image sharpening of the image scene content in the frame to be processed.
Further, after the content of the scene content in the frame to be processed is optimized, the optimized frame to be processed is used as the frame to be displayed, the frame to be displayed is added into the display waiting queue, and the frame to be displayed is waited to be displayed on the electronic ink screen.
In the image processor, the content recognition module is used for recognizing the content of the frame to be processed in the display waiting queue, the content type of the frame to be processed is determined, the content optimization strategy of the frame to be processed is determined based on the content type, and the content of the frame to be processed is optimized according to the determined content optimization strategy, so that the frame to be displayed suitable for being displayed on the electronic ink screen is obtained. Meanwhile, the training content recognition model is learned through a machine, training samples can be provided through cloud big data, the content recognition model is continuously optimized, and the recognition result and the optimization effect are continuously increased. Compared with the prior art, the optimization performance of the image frame can be greatly improved, the parallel processing capacity of the image processor is utilized, the consumption of various additional measurement and calculation of the image by using a central processing unit in the prior art is well solved, on the other hand, the analysis and optimization speed of the image can be continuously improved and improved by means of machine learning and neural network training, and the participation of a user in optimization configuration is greatly reduced through intelligent scene and object recognition, so that a good display effect can be obtained without the user self-adjusting excessive parameters.
Fig. 3 is a schematic structural diagram of a display control device of an electronic ink screen according to an embodiment of the present disclosure. Referring to fig. 3, the electronic ink screen display control apparatus includes a content recognition module 31, a policy determination module 32, and a content optimization module 33.
The content identification module 31 is configured to perform content identification on a to-be-processed frame in a display waiting queue by using a trained content identification model in an image processor, so as to determine a content type in the to-be-processed frame; the policy determining module 32 is configured to determine a content optimization policy for the frame to be processed based on the content type, where different content types correspond to different content optimization policies, and the content optimization policy is used to indicate an optimization manner for the frame to be processed; and the content optimization module 33 is configured to perform content optimization on the frame to be processed according to the determined content optimization strategy to obtain a frame to be displayed, and display the frame to be displayed in an electronic ink screen.
In the image processor, the content recognition module is used for recognizing the content of the frame to be processed in the display waiting queue, the content type of the frame to be processed is determined, the content optimization strategy of the frame to be processed is determined based on the content type, and the content of the frame to be processed is optimized according to the determined content optimization strategy, so that the frame to be displayed suitable for being displayed on the electronic ink screen is obtained.
In one possible embodiment, the content type includes a scene type and/or an object type;
the content identification module 31 is specifically configured to:
utilizing a trained content recognition model in an image processor to perform scene content recognition on a frame to be processed in a display waiting queue so as to determine the scene type in the frame to be processed; and/or
And utilizing the trained content recognition model in the image processor to perform object content recognition on the frames to be processed in the display waiting queue so as to determine the object types in the frames to be processed.
In one possible embodiment, the content optimization policy includes a scene optimization policy and/or an object content optimization policy, where the scene optimization policy is used to indicate an optimization manner for the scene content of the frame to be processed, and the object optimization policy is used to indicate an optimization manner for the object content of the frame to be processed;
the policy determination module 32 is specifically configured to:
determining that the content optimization strategy for the frame to be processed is a scene optimization strategy based on the content type as a scene type; and/or
And determining the content optimization strategy of the frame to be processed as an object optimization strategy based on the content type as an object type.
In one possible embodiment, the scene type includes a text scene type, an image scene type, and/or an image-text scene type, and correspondingly, the scene optimization policy includes a text scene optimization policy, an image scene optimization policy, and/or an image-text scene optimization policy, and the image-text scene optimization policy is used to instruct that the text scene optimization policy is adopted for the text scene content in the frame to be processed, and the image scene optimization policy is adopted for the image scene content in the frame to be processed;
the object type comprises an entity object type and/or a graphic object type, and correspondingly, the object optimization strategy comprises an entity object optimization strategy and/or a graphic object optimization strategy.
In a possible embodiment, the content optimization module 33 is specifically configured to:
based on the determined scene optimization strategy, performing content optimization on the scene content in the frame to be processed to obtain a frame to be displayed after the scene optimization; and/or
And based on the determined object optimization strategy, performing content optimization on the object content in the frame to be processed to obtain a frame to be displayed after the content optimization.
In one possible embodiment, the optimization includes one or more of color replacement, color inversion, edge delineation, contrast enhancement, edge enhancement, and image sharpening.
In one possible embodiment, the apparatus further comprises a scheme determination module configured to:
determining a software strategy data packet corresponding to a software image frame based on the software image frame to be displayed, wherein the software strategy data packet records the content type corresponding to the software image frame;
and determining the corresponding content type when the content of the frame to be processed is identified based on the content type corresponding to the software strategy data packet.
The embodiment of the application also provides electronic ink screen display control equipment, and the electronic ink screen display control equipment can integrate the electronic ink screen display control device provided by the embodiment of the application. Fig. 4 is a schematic structural diagram of an electronic ink screen display control device according to an embodiment of the present application. Referring to fig. 4, the electronic ink screen display control apparatus includes: an input device 43, an output device 44, a memory 42, and one or more processors 41; the memory 42 for storing one or more programs; when the one or more programs are executed by the one or more processors 41, the one or more processors 41 are caused to implement the electronic ink screen display control method provided in the above embodiment. Wherein the input device 43, the output device 44, the memory 42 and the processor 41 may be connected by a bus or other means, for example, in fig. 4.
The memory 42 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the electronic ink screen display control method according to any embodiment of the present application (for example, the content identification module 31, the policy determination module 32, and the content optimization module 33 in the electronic ink screen display control apparatus). The memory 42 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory 42 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 42 may further include memory located remotely from processor 41, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 43 may be used to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 44 may include a display device such as a display screen.
The processor 41 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 42, that is, implements the above-described electronic ink screen display control method.
The electronic ink screen display control device, the electronic ink screen display control equipment and the computer can be used for executing the electronic ink screen display control method provided by any embodiment, and have corresponding functions and beneficial effects.
Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the electronic ink screen display control method provided in the above embodiments, the electronic ink screen display control method including: utilizing a trained content identification model in an image processor to identify the content of a frame to be processed in a display waiting queue so as to determine the content type of the frame to be processed; determining a content optimization strategy for the frame to be processed based on the content type, wherein different content types correspond to different content optimization strategies, and the content optimization strategies are used for indicating an optimization mode for the frame to be processed; and according to the determined content optimization strategy, performing content optimization on the frame to be processed to obtain a frame to be displayed, and displaying the frame to be displayed in an electronic ink screen.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application and containing computer-executable instructions is not limited to the electronic ink screen display control method described above, and may also perform related operations in the electronic ink screen display control method provided in any embodiments of the present application.
The electronic ink screen display control device, the electronic ink screen display control apparatus, and the storage medium provided in the foregoing embodiments may execute the electronic ink screen display control method provided in any embodiment of the present application, and refer to the electronic ink screen display control method provided in any embodiment of the present application without detailed technical details described in the foregoing embodiments.
The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.
Claims (10)
1. A display control method of an electronic ink screen is characterized by comprising the following steps:
utilizing a trained content identification model in an image processor to identify the content of a frame to be processed in a display waiting queue so as to determine the content type of the frame to be processed;
determining a content optimization strategy for the frame to be processed based on the content type, wherein different content types correspond to different content optimization strategies, and the content optimization strategies are used for indicating an optimization mode for the frame to be processed;
and according to the determined content optimization strategy, performing content optimization on the frame to be processed to obtain a frame to be displayed, and displaying the frame to be displayed in an electronic ink screen.
2. The electronic ink screen display control method of claim 1, wherein the content type includes a scene type and/or an object type;
the method for identifying the content of the frame to be processed in the display waiting queue by using the trained content identification model in the image processor to determine the content type of the frame to be processed comprises the following steps:
utilizing a trained content recognition model in an image processor to perform scene content recognition on a frame to be processed in a display waiting queue so as to determine the scene type in the frame to be processed; and/or
And utilizing the trained content recognition model in the image processor to perform object content recognition on the frames to be processed in the display waiting queue so as to determine the object types in the frames to be processed.
3. The electronic ink screen display control method according to claim 2, wherein the content optimization strategy includes a scene optimization strategy and/or an object content optimization strategy, the scene optimization strategy is used for indicating an optimization manner of the scene content of the frame to be processed, and the object optimization strategy is used for indicating an optimization manner of the object content of the frame to be processed;
the determining a content optimization policy for the frame to be processed based on the content type includes:
determining that the content optimization strategy for the frame to be processed is a scene optimization strategy based on the content type as a scene type; and/or
And determining the content optimization strategy of the frame to be processed as an object optimization strategy based on the content type as an object type.
4. The electronic ink screen display control method according to claim 3, wherein the scene type includes a text scene type, an image scene type and/or a graphics context type, and correspondingly, the scene optimization policy includes a text scene optimization policy, an image scene optimization policy and/or a graphics context optimization policy, and the graphics context optimization policy is used to instruct to adopt the text scene optimization policy for the text scene content in the frame to be processed and adopt the image scene optimization policy for the image scene content in the frame to be processed;
the object type comprises an entity object type and/or a graphic object type, and correspondingly, the object optimization strategy comprises an entity object optimization strategy and/or a graphic object optimization strategy.
5. The method for controlling display of an electronic ink screen according to claim 3, wherein the content optimization of the frame to be processed based on the determined content optimization strategy to obtain the frame to be displayed comprises:
based on the determined scene optimization strategy, performing content optimization on the scene content in the frame to be processed to obtain a frame to be displayed after the scene optimization; and/or
And based on the determined object optimization strategy, performing content optimization on the object content in the frame to be processed to obtain a frame to be displayed after the content optimization.
6. The electronic ink screen display control method of claim 1, wherein the optimization manner includes one or more of color replacement, color inversion, edge tracing, contrast enhancement, edge enhancement, and image sharpening.
7. The electronic ink screen display control method of claim 2, further comprising:
determining a software strategy data packet corresponding to a software image frame based on the software image frame to be displayed, wherein the software strategy data packet records the content type corresponding to the software image frame;
and determining the corresponding content type when the content of the frame to be processed is identified based on the content type corresponding to the software strategy data packet.
8. The display control device of the electronic ink screen is characterized by comprising a content identification module, a strategy determination module and a content optimization module, wherein:
the content identification module is used for identifying the content of the frame to be processed in the display waiting queue by utilizing a trained content identification model in the image processor so as to determine the content type of the frame to be processed;
the policy determining module is configured to determine a content optimization policy for the frame to be processed based on the content type, where different content types correspond to different content optimization policies, and the content optimization policy is used to indicate an optimization manner for the frame to be processed;
and the content optimization module is used for optimizing the content of the frame to be processed according to the determined content optimization strategy to obtain the frame to be displayed and displaying the frame to be displayed in the electronic ink screen.
9. An electronic ink screen display control apparatus, comprising: a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the electronic ink screen display control method of any one of claims 1-7.
10. An electronic ink screen display control apparatus, comprising: a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the electronic ink screen display control method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110536133.0A CN113515246A (en) | 2021-05-17 | 2021-05-17 | Electronic ink screen display control method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110536133.0A CN113515246A (en) | 2021-05-17 | 2021-05-17 | Electronic ink screen display control method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113515246A true CN113515246A (en) | 2021-10-19 |
Family
ID=78064273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110536133.0A Pending CN113515246A (en) | 2021-05-17 | 2021-05-17 | Electronic ink screen display control method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113515246A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114398019A (en) * | 2022-01-24 | 2022-04-26 | 广州文石信息科技有限公司 | Screen updating request processing method and device and electronic ink screen equipment |
| CN114489545A (en) * | 2022-01-28 | 2022-05-13 | 广州文石信息科技有限公司 | Screen updating request scanning method and device, storage medium and related equipment |
| CN115359761A (en) * | 2022-08-16 | 2022-11-18 | 广州文石信息科技有限公司 | Ink screen display control method and device based on key frame |
| CN116364023A (en) * | 2023-04-12 | 2023-06-30 | 广州文石信息科技有限公司 | Method, device, medium and equipment for driving electronic ink screen based on GPU |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764370A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and computer equipment |
| CN109379625A (en) * | 2018-11-27 | 2019-02-22 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and computer-readable medium |
| CN109951627A (en) * | 2017-12-20 | 2019-06-28 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN109961747A (en) * | 2019-04-02 | 2019-07-02 | 上海墨案智能科技有限公司 | Electronic ink screen display methods, device and electronic equipment |
| CN110149517A (en) * | 2018-05-14 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Method, apparatus, electronic equipment and the computer storage medium of video processing |
| CN110163810A (en) * | 2019-04-08 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of image processing method, device and terminal |
-
2021
- 2021-05-17 CN CN202110536133.0A patent/CN113515246A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109951627A (en) * | 2017-12-20 | 2019-06-28 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN110149517A (en) * | 2018-05-14 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Method, apparatus, electronic equipment and the computer storage medium of video processing |
| CN108764370A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and computer equipment |
| CN109379625A (en) * | 2018-11-27 | 2019-02-22 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and computer-readable medium |
| CN109961747A (en) * | 2019-04-02 | 2019-07-02 | 上海墨案智能科技有限公司 | Electronic ink screen display methods, device and electronic equipment |
| CN110163810A (en) * | 2019-04-08 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of image processing method, device and terminal |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114398019A (en) * | 2022-01-24 | 2022-04-26 | 广州文石信息科技有限公司 | Screen updating request processing method and device and electronic ink screen equipment |
| CN114398019B (en) * | 2022-01-24 | 2024-02-23 | 广州文石信息科技有限公司 | Screen update request processing method and device and electronic ink screen equipment |
| CN114489545A (en) * | 2022-01-28 | 2022-05-13 | 广州文石信息科技有限公司 | Screen updating request scanning method and device, storage medium and related equipment |
| CN114489545B (en) * | 2022-01-28 | 2022-08-02 | 广州文石信息科技有限公司 | Screen updating request scanning method and device, storage medium and related equipment |
| CN115359761A (en) * | 2022-08-16 | 2022-11-18 | 广州文石信息科技有限公司 | Ink screen display control method and device based on key frame |
| CN116364023A (en) * | 2023-04-12 | 2023-06-30 | 广州文石信息科技有限公司 | Method, device, medium and equipment for driving electronic ink screen based on GPU |
| CN116364023B (en) * | 2023-04-12 | 2023-11-28 | 广州文石信息科技有限公司 | Method, device, medium and equipment for driving electronic ink screen based on GPU |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113515246A (en) | Electronic ink screen display control method, device, equipment and storage medium | |
| EP3736766A1 (en) | Method and device for blurring image background, storage medium, and electronic apparatus | |
| CN111160569A (en) | Application development method and device based on machine learning model and electronic equipment | |
| CN112308095A (en) | Picture preprocessing and model training method and device, server and storage medium | |
| US20010014173A1 (en) | Color Region Based Recognition of Unidentified Objects | |
| US10614347B2 (en) | Identifying parameter image adjustments using image variation and sequential processing | |
| CN112200062A (en) | Target detection method and device based on neural network, machine readable medium and equipment | |
| CN111951154B (en) | Picture generation method and device containing background and medium | |
| CN111489322B (en) | Method and device for adding sky filter to static picture | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN113505854A (en) | Method, device, equipment and medium for constructing facial image quality evaluation model | |
| CN113762303B (en) | Image classification method, device, electronic equipment and storage medium | |
| CN117095006B (en) | Image aesthetic evaluation method, device, electronic equipment and storage medium | |
| CN110990617B (en) | Picture marking method, device, equipment and storage medium | |
| WO2023109640A1 (en) | Interpretability method and system for deep reinforcement learning model in driverless scene | |
| CN111382647A (en) | Picture processing method, device, equipment and storage medium | |
| CN110475139B (en) | Video subtitle shielding method and device, storage medium and electronic equipment | |
| CN114035763B (en) | Jitter optimization method and device of electronic ink screen as computer display | |
| US20130182943A1 (en) | Systems and methods for depth map generation | |
| CN109034032B (en) | Image processing method, apparatus, device and medium | |
| CN115471439A (en) | Method and device for identifying defects of display panel, electronic equipment and storage medium | |
| CN116912187A (en) | Image generation model training and image generation method, device, equipment and medium | |
| CN115063800B (en) | Text recognition method and electronic equipment | |
| CN116778295A (en) | Model compression method, system and medium capable of adaptively adjusting knowledge distillation temperature | |
| CN116342973A (en) | Data labeling method and system based on semi-supervised learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211019 |
|
| RJ01 | Rejection of invention patent application after publication |