CN110569083B - Image segmentation processing method and device, computer equipment and storage medium - Google Patents
Image segmentation processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110569083B CN110569083B CN201910725288.1A CN201910725288A CN110569083B CN 110569083 B CN110569083 B CN 110569083B CN 201910725288 A CN201910725288 A CN 201910725288A CN 110569083 B CN110569083 B CN 110569083B
- Authority
- CN
- China
- Prior art keywords
- plug
- processing
- segmentation
- function
- post
- 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.)
- Active
Links
- 238000003709 image segmentation Methods 0.000 title claims abstract description 127
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 234
- 230000011218 segmentation Effects 0.000 claims abstract description 146
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000006870 function Effects 0.000 claims description 293
- 238000007781 pre-processing Methods 0.000 claims description 149
- 238000012805 post-processing Methods 0.000 claims description 131
- 238000004590 computer program Methods 0.000 claims description 27
- 230000000875 corresponding effect Effects 0.000 description 34
- 238000010586 diagram Methods 0.000 description 6
- 238000012546 transfer Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012285 ultrasound imaging Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
- G06F9/44526—Plug-ins; Add-ons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Stored Programmes (AREA)
Abstract
The application relates to an image segmentation processing method, an image segmentation processing device, computer equipment and a storage medium. The method comprises the following steps: reading image data and acquiring a target plug-in identification; acquiring a data processing plug-in corresponding to the target plug-in identification from a plug-in library; respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in a segmentation workflow; and inputting the image data into the segmentation workflow, and performing segmentation processing on the image data. By adopting the method, the redundancy of the image segmentation processing codes can be reduced.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image segmentation processing method and apparatus, a computer device, and a storage medium.
Background
The deep learning segmentation technology is more and more widely applied to the field of images, but one set of segmentation technology is difficult to meet the requirement of diversity of image products. Different types of products need to be added with personalized image segmentation functions according to the image characteristics of the products.
At present, in order to solve the problem of specificity of image segmentation processing in different types of products, processing codes for performing specificity processing in the process of segmenting a product image are usually added into codes of a general segmentation engine, so that a large number of different specificity codes are added into the general segmentation engine, redundancy of the codes in the engine is obviously increased, and maintenance cost and difficulty of the codes are increased.
Disclosure of Invention
In view of the above, it is necessary to provide an image segmentation processing method, an apparatus, a computer device, and a storage medium capable of reducing redundancy of image segmentation processing codes in view of the above technical problems.
An image segmentation processing method, the method comprising:
reading image data and acquiring a target plug-in identification;
acquiring a data processing plug-in corresponding to the target plug-in identification from a plug-in library;
respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in a segmentation workflow;
and inputting the image data into the segmentation workflow, and performing segmentation processing on the image data.
An image segmentation processing apparatus, the apparatus comprising:
the data reading module is used for reading image data and acquiring a target plug-in identification;
the plug-in acquisition module is used for acquiring the data processing plug-in corresponding to the target plug-in identification from a plug-in library;
the interface access module is used for respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in the segmentation workflow;
and the image segmentation module is used for inputting the image data into the segmentation workflow and carrying out segmentation processing on the image data.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the image segmentation processing method, the image segmentation processing device, the computer equipment and the storage medium, image segmentation functions belonging to image characteristics are integrated into one segmentation function plug-in, when an image needs to be segmented, the corresponding segmentation function plug-in is called on the basis of using a general segmentation workflow, and each segmentation function of the segmentation function plug-in is deployed at a corresponding position of the workflow, so that differentiated segmentation processing functions can be maintained through a lightweight plug-in and can be called at any time, and the code burden of the general segmentation workflow is reduced.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a method for image segmentation;
FIG. 2 is a flowchart illustrating a method of image segmentation processing according to an embodiment;
FIG. 3 is a flow diagram illustrating a flow of a process for segmenting image data according to one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating the add-on step of a plug-in one embodiment;
FIG. 5 is a flowchart illustrating the plug-in configuration steps in one embodiment;
FIG. 6 is a block diagram showing the structure of an image segmentation processing apparatus according to an embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image segmentation processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 sends the acquired image data to the server 104 for image segmentation processing, and the server 104 reads the image data after receiving the image data and acquires a target plug-in identifier; acquiring a data processing plug-in corresponding to the target plug-in identification from a plug-in library; respectively accessing each data processing function in the data processing plug-in into a corresponding data processing function interface in the segmentation workflow; and inputting the image data into the segmentation workflow through a data processing function interface, and performing segmentation processing on the image data.
The terminal 102 may be a terminal of various image capturing devices, but is not limited to various medical image capturing devices, such as a personal computer, a notebook computer, a smart phone, a camera, a tablet computer, and a portable wearable device, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, an image segmentation processing method is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
Image data is complex and needs to be segmented, such as medical image data, and organs and lesions need to be segmented. The image data may be acquired by an imaging device, for example, the medical image data may be acquired by a medical imaging device such as a CT device, an ultrasound imaging device, or a magnetic resonance imaging device. The image data can be sent to the server through the equipment terminal, and the server receives various image data and can store the various image data in a classified mode.
The target plug-in identification is used for uniquely identifying the data processing plug-in, the types of the data processing plug-ins can include multiple types, and different data processing plug-ins can be set for various types of image data. A user can set a data processing plug-in needed by an image needing to be segmented through a terminal, and the terminal carries a target plug-in identification of the set data processing plug-in when sending image data to a server.
The server can process the received image data in real time, or can associate the received image data with the target plug-in identification and add the image data to the segmentation task processing queue, and read and process the image data from the task processing queue in sequence. When the server needs to perform segmentation processing on the image data, reading the image data to be processed, and acquiring the associated target plug-in identification.
Because different types of image data have different image characteristics, different segmentation processing methods need to be adopted, different data processing plugins are set for various types of image data, data processing functions of specific processing steps during segmentation processing of the image data are integrated in the data processing plugins, and the specific processing steps can include multiple steps. Generally, an algorithm for image segmentation is common when an image is segmented, but steps such as image segmentation preprocessing and image post-processing after segmentation are greatly different among various images, and a data processing plug-in is used for processing the differential steps.
And the server searches the corresponding data processing plug-ins from the plug-in library according to the target plug-in identification.
And step 230, respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in the segmentation workflow.
The segmentation workflow is used for carrying out segmentation processing on the image data, the segmentation workflow comprises a main body segmentation algorithm function which is common to various images, and a corresponding data interface is provided at the workflow position of each specific processing step to be in butt joint with the data processing plug-in. And the server respectively accesses the data processing functions corresponding to the steps in the data processing plug-in into corresponding data processing function interfaces in the segmentation workflow so as to enable the segmentation workflow to carry out function call.
The server inputs image data into the segmentation workflow through the data processing function interface, segmentation processing is carried out on the image data according to the data processing flow in the segmentation workflow, a segmentation algorithm is set in the segmentation workflow to carry out segmentation processing on the image data, corresponding data processing functions in the data processing plug-in are called at the position of the workflow with the data processing function interface to carry out data processing, and finally an image segmentation result is output from the segmentation workflow. For example, the data processing function may be used to perform preprocessing of image data, post-processing of a segmentation processing result, and the like.
In the image segmentation processing method, the image segmentation functions belonging to the image characteristics are integrated in one segmentation function plug-in, when the image needs to be segmented, the corresponding segmentation function plug-in is called on the basis of using a general segmentation workflow, and each segmentation function of the segmentation function plug-in is deployed at the corresponding position of the workflow, so that the differentiated segmentation processing functions can be maintained through a lightweight plug-in and can be called at any time, and the code burden of the general segmentation workflow is reduced.
In one embodiment, the data processing function interface includes a first pre-processing function interface and a first post-processing function interface.
The step of performing segmentation processing on the image data may include: calling a first preprocessing function in the data processing plug-in through a first preprocessing function interface, and performing first preprocessing on the image data to obtain first preprocessed image data; inputting the first pre-processing image data into a first segmentation model of a segmentation workflow to obtain a first image segmentation result and transmitting the first image segmentation result to a first post-processing function interface; and calling a first post-processing function in the data processing plug-in through the first post-processing function interface, and performing post-processing on the first image segmentation result to obtain a first image segmentation post-processing result.
In this embodiment, the splitting workflow includes two data processing function interfaces, which are a first preprocessing function interface and a first post-processing function interface, respectively, where the first preprocessing function interface is accessed to the first preprocessing function in the data processing plugin, and the first post-processing function interface is accessed to the first post-processing function in the data processing plugin
After the image data is input into the segmentation workflow, the server calls a first preprocessing function in the data processing plug-in through a first preprocessing function interface in the segmentation workflow, and specifically, the image data can be transmitted into the first preprocessing function to be preprocessed, so that first preprocessed image data is obtained. The preprocessing can include data processing operations such as denoising, contrast enhancement, gray scale conversion and the like, the preprocessing of one type of image can include one or more processing operations, and when the preprocessing includes multiple processing operations, the processing sequence of each processing operation can also be determined according to the type of the image.
The data processing plug-in returns the obtained first preprocessed image data to the segmentation workflow through the first preprocessing function interface, inputs the first preprocessed image data into a first segmentation model in the segmentation workflow, and performs image segmentation, wherein the first segmentation model is used for performing image segmentation on the image data and obtaining a first image segmentation result.
The server calls a first post-processing function in the data processing plug-in through the first post-processing function interface, and specifically, the first image segmentation result can be transmitted into the first post-processing function to be subjected to post-processing operation, so that the first image segmentation post-processing result is obtained. The post-processing may include data processing operations such as smoothing, extracting a maximum connected region, and removing a small connected region, the post-processing of one type of image may include one or more processing operations, and when a plurality of processing operations are included, the order of processing of each processing operation may also be determined according to the type of the image.
In this embodiment, the data processing plug-in includes two processing functions, namely a first preprocessing function and a first post-processing function, and is respectively connected to the corresponding function interfaces of the segmentation workflow, so that the preprocessing function and the post-processing function can be set as required and integrated into one data processing plug-in, and thus, the preprocessing and post-processing requirements of various images can be met only by calling the corresponding plug-in.
In one embodiment, the data processing function interface further comprises a second pre-processing function interface and a second post-processing function interface.
After the step of obtaining the first image segmentation post-processing result, the method may further include: transmitting the first image segmentation post-processing result to a second preprocessing function interface through a first post-processing function interface; calling a second preprocessing function in the data processing plugin segmentation function plugins through a second preprocessing function interface, and performing second preprocessing on the processing result after the first image segmentation to obtain second preprocessed image data; inputting second pre-processing image data into a second segmentation model of the segmentation workflow through a second pre-processing function interface to obtain a second image segmentation result, and transmitting the second image segmentation result to a second post-processing function interface; and calling a second post-processing function in the data processing plug-in through a second post-processing function interface, and post-processing the second image segmentation result by the second post-processing function to obtain a second image segmentation post-processing result.
In the present embodiment, the division workflow includes two division processing sections of the first division processing and the second division processing. The first segmentation processing is used for carrying out rough segmentation processing on the image data, and the second segmentation processing is further carried out with fine segmentation processing based on the image rough segmentation processing result, so that a finer segmentation processing result is obtained.
In an embodiment, referring to fig. 3, in four data processing links of rough segmentation data preprocessing, rough segmentation result post-processing, fine segmentation data preprocessing, and fine segmentation result post-processing, a function interface is provided to interface with a corresponding data processing plug-in a plug-in factory.
Specifically, in the image data segmentation processing process, after the server inputs the image data into the segmentation workflow, the first preprocessing function interface calls a first preprocessing function in the data processing plug-in, the first preprocessing function is a rough segmentation preprocessing function, rough segmentation preprocessing is performed on the image data to obtain rough segmentation preprocessed image data, namely the first preprocessed image data, and the first preprocessed image data is input into a first segmentation model in the segmentation workflow to perform rough segmentation processing to obtain an image rough segmentation result, namely the first image segmentation result. The server further calls a first post-processing function in the data processing plug-in, wherein the first post-processing function is a rough segmentation post-processing function, and the rough segmentation post-processing operation is performed on the first image segmentation result to obtain an image rough segmentation post-processing result, namely the first image segmentation post-processing result.
The server further transmits the first image segmentation post-processing result to a second preprocessing function interface from the first post-processing function interface, calls a second preprocessing function in the data processing plug-in unit through the second preprocessing function interface, the second preprocessing function is a fine segmentation preprocessing function, and performs fine segmentation preprocessing on the first image segmentation result to obtain fine segmented preprocessed image data, namely the second preprocessed image data. And the server inputs the second preprocessed image data into a second segmentation model in the segmentation workflow, and performs segmentation operation processing to obtain an image segmentation result, namely a second image segmentation result. The server further calls a second post-processing function in the data processing plug-in, wherein the second post-processing function is a fine segmentation post-processing function, and performs fine segmentation post-processing operation on the second image segmentation result to obtain an image fine segmentation post-processing result, namely the second image segmentation post-processing result.
In this embodiment, the image segmentation process is refined into two parts, namely, coarse segmentation processing and fine segmentation processing, so that the image data can be more finely segmented, and a more accurate image segmentation result can be obtained.
In an embodiment, the step of calling, by the first preprocessing function interface, the first preprocessing function in the data processing plug-in and performing the first preprocessing on the image data to obtain the first preprocessed image data may include: storing the image data before being processed through the first preprocessing function; the step of performing the second preprocessing on the first image segmentation post-processing result may include: receiving the image data transferred by the first preprocessing function through the second preprocessing function, wherein the image data is image data before being processed; and performing second preprocessing on the first image segmentation post-processing result and the image data before the first image segmentation post-processing result.
In this embodiment, the first preprocessing function stores the original image data before the first preprocessing is not performed after the first preprocessing is performed on the image data, and the original image data is stored in the data processing plug-in. At this time, only the first preprocessed image data after the first preprocessing exists in the data flowing into the division workflow.
Because different types of image data are different in image preprocessing or post-processing method, the fine segmentation preprocessing of some types of image data is to process the first image segmentation post-processing result and the original image data at the same time, so that when the fine segmentation preprocessing, that is, the second preprocessing, is performed, and when the second preprocessing function is called to perform the fine segmentation preprocessing, the segmentation workflow transfers the first image segmentation post-processing result to the second preprocessing function through the second preprocessing function interface, and meanwhile, the first preprocessing function in the data processing plug-in also transfers the stored original image data to the second preprocessing function, so that the second preprocessing function performs the fine segmentation preprocessing based on the original image data and the first image segmentation post-processing result.
In other embodiments, some types of fine segmentation pre-processing of the image data are to perform the operation processing on the first pre-processing image data after the first image segmentation pre-processing and the coarse segmentation pre-processing at the same time. At this time, the first preprocessing function performs the first preprocessing on the image data, and then backups and stores the obtained first preprocessed image data, so that when the fine segmentation preprocessing is performed, the first preprocessed image data is transferred to the second preprocessing function for operation processing.
In other embodiments, some intermediate results generated in the previous processing procedure may also be stored according to the specific requirements of the image data segmentation processing, so as to be used by the following processing function to perform the call of the intermediate results.
In this embodiment, each processing function in the data processing plug-in may perform backup storage on intermediate data generated in the operation processing process, and the intermediate data may be transferred and called among the processing functions of the plug-in, thereby facilitating operation processing.
In one embodiment, as shown in fig. 4, the image segmentation processing method may further include the following plug-in addition step:
When a new image data segmentation processing requirement exists, a user can write a new data processing plug-in, and the terminal can send the newly added plug-in and a plug-in initial function to the server for centralized management and calling. Specifically, the terminal sends a plug-in addition request carrying the newly added plug-in and a plug-in initialization function to the server. And the server acquires the newly added plug-in and the plug-in initial function from the newly added plug-in request.
And 420, generating a newly added plug-in identifier according to the plug-in newly adding request.
The server can further read the plug-in information of the newly added plug-in from the plug-in addition request, and generate a newly added plug-in identifier according to the plug-in information, wherein the newly added plug-in identifier is used for uniquely identifying the newly added plug-in. The plug-in information may be information such as a name of the plug-in, a type of image processed by the plug-in, and the like.
And 430, storing the newly added plug-in identification, the newly added plug-in and the plug-in initialization function in the plug-in library in an associated manner.
And the server associates the newly added plug-in and the plug-in initialization function with the newly added plug-in identification respectively, and adds the newly added plug-in and the plug-in initialization function after the identification association to the plug-in library. The plug-in library is used for carrying out centralized management on all data processing plug-ins, and can further carry out classified storage on the data processing plug-ins according to the image processing types processed by the data processing plug-ins, so that the data processing plug-ins are convenient to search.
In one embodiment, after the step 220 in fig. 2 acquires the data processing plugin corresponding to the target plugin identifier from the plugin library, the following steps may be further included: searching a plug-in initialization function corresponding to the target plug-in identification from the plug-in library; and performing plug-in initialization on the data processing plug-in according to the plug-in initialization function.
And the server searches a plug-in initialization function corresponding to the target plug-in identification from the plug-in library, wherein the plug-in initialization function is used for initializing the data processing plug-in. The initialization processing includes parsing configuration information of the data processing plug-in, such as configuration information of a function interface to which each processing function in the plug-in needs to be docked.
In one embodiment, as shown in fig. 5, the image segmentation processing method may further include the following plug-in configuration steps:
The data processing plug-in can be written by a user, and can also be automatically configured and assembled by the server according to the requirements of the user. When a new plug-in configuration requirement exists, the terminal sends a plug-in configuration file to the server, the configuration plug-in identification of the data processing plug-in needing to be configured is set in the plug-in configuration file, and in addition, the split processing requirement function of each split processing flow is also configured in the plug-in configuration file. For example, the functional requirements of the post-processing process are to perform smoothing processing, the functional requirements of the fine segmentation pre-processing process are to process the input while being based on the original image and the coarse segmentation result image, and so on. And the server reads the configured plug-in identification and the plug-in requirement function from the received plug-in configuration file.
And step 520, searching a function code matched with the plug-in requirement function from the plug-in library.
In this embodiment, the plug-in library stores, in addition to the integrated plug-in including each processing step, a function code independent of each processing step, the server stores each function code in association with a function introduction, the function introduction may include information such as the processing step where the function is located, the processing method adopted, and the like, keywords of each information in the function introduction may be used, for example, the keywords of the processing step may be rough segmentation post-processing, fine segmentation pre-processing, and the like, and the keywords of the processing method may include smoothing, large connectivity extraction, small connectivity removal, and the like. The server extracts the function key words of each processing step from the plug-in demand function, semantically matches the function key words with the function introduction of each function code in the plug-in library, and finds out the function codes successfully matched.
And 530, assembling the function codes to generate a requirement configuration plug-in, and storing the configuration plug-in identification and the requirement configuration plug-in into the plug-in library in an associated manner.
And the server assembles the function codes searched in each processing step to generate a requirement configuration file, associates the read configuration plug-in identification with the requirement configuration plug-in, and adds the associated requirement configuration plug-in to a plug-in library for storage. Further, the server can obtain an initialization function writing logic, configure the plug-in according to the initialization function writing logic and configured requirements to generate a plug-in initialization function, and store the plug-in initialization function and the configuration plug-in identification in the plug-in library in a correlated manner.
In this embodiment, the function codes of each processing function are centrally managed in the plug-in library according to the function processing function, the function codes of the corresponding processing function can be automatically searched according to the configuration requirement of the plug-in, and the searched function codes are assembled and configured into the plug-in, so that the code compiling work can be reduced, and the plug-in can be suitable for the processing requirements of various images.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 6, there is provided an image segmentation processing apparatus including: a data reading module 610, a plug-in obtaining module 620, an interface access module 630 and an image segmentation module 640, wherein:
and the data reading module 610 is used for reading the image data and acquiring the target plug-in identification.
And the plug-in obtaining module 620 is configured to obtain the data processing plug-in corresponding to the target plug-in identifier from the plug-in library.
An interface access module 630, configured to access each data processing function in the data processing plug-in to a corresponding data processing function interface in the splitting workflow respectively.
And an image segmentation module 640, configured to input the image data into the segmentation workflow, and perform segmentation processing on the image data.
In one embodiment, the data processing function interface includes a first pre-processing function interface and a first post-processing function interface; the image segmentation module 640 may include:
and the first preprocessing unit is used for calling a first preprocessing function in the data processing plug-in unit through the first preprocessing function interface, and performing first preprocessing on the image data to obtain first preprocessed image data.
And the first segmentation unit is used for inputting the first pre-processing image data into a first segmentation model of the segmentation workflow to obtain a first image segmentation result and transmitting the first image segmentation result to the first post-processing function interface.
And the first post-processing unit is used for calling a first post-processing function in the data processing plug-in unit through the first post-processing function interface, and performing post-processing on the first image segmentation result to obtain a first image segmentation post-processing result.
In one embodiment, the data processing function interface further comprises a second pre-processing function interface and a second post-processing function interface; the image segmentation module 640 may further include:
and the data transfer unit is used for transferring the first image segmentation post-processing result to the second preprocessing function interface through the first post-processing function interface.
And the second preprocessing unit is used for calling a second preprocessing function in the data processing plug-in unit through the second preprocessing function interface, and performing second preprocessing on the processing result after the first image is segmented to obtain second preprocessed image data.
And the second segmentation unit is used for inputting the second pre-processed image data into a second segmentation model of the segmentation workflow through the second pre-processing function interface to obtain a second image segmentation result and transmitting the second image segmentation result to the second post-processing function interface.
And the second post-processing unit is used for calling a second post-processing function in the data processing plug-in unit through the second post-processing function interface, and the second post-processing function performs post-processing on the second image segmentation result to obtain a second image segmentation post-processing result.
In one embodiment, the image segmentation module 640 may further include:
and the data storage unit is used for storing the image data before the processing through the first preprocessing function.
The second preprocessing unit may include:
and the function transfer subunit is used for receiving the image data transferred by the first preprocessing function through the second preprocessing function, wherein the image data is image data before being processed.
And the preprocessing subunit is used for performing second preprocessing on the first image segmentation post-processing result and the image data before being processed.
In one embodiment, the image segmentation processing apparatus may further include:
and the request receiving module is used for receiving a plug-in newly-added request, and the plug-in newly-added request carries a newly-added plug-in and a plug-in initialization function.
And the identification generation module is used for generating a newly added plug-in identification according to the plug-in newly adding request.
And the plug-in storage module is used for storing the newly added plug-in identification, the newly added plug-in and the plug-in initialization function into the plug-in library in an associated manner.
In one embodiment, the image segmentation processing apparatus may further include:
and the function searching module is used for searching the plug-in initialization function corresponding to the target plug-in identification from the plug-in library.
And the initialization module is used for carrying out plug-in initialization on the data processing plug-in according to the plug-in initialization function.
In one embodiment, the image segmentation processing apparatus may further include:
and the file receiving module is used for receiving the plug-in configuration file and reading the configuration plug-in identification and the plug-in requirement function from the plug-in configuration file.
And the code searching module is used for searching the function codes matched with the plug-in requirement functions from the plug-in library.
And the plug-in generation module is used for assembling the function codes to generate a demand configuration plug-in and storing the configuration plug-in identification and the demand configuration plug-in into the plug-in library in an associated manner.
For specific limitations of the image segmentation processing device, reference may be made to the above limitations of the image segmentation processing method, which is not described herein again. The respective modules in the image segmentation processing device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing image segmentation processing related data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an image segmentation processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: reading image data and acquiring a target plug-in identification; acquiring a data processing plug-in corresponding to the target plug-in identification from a plug-in library; respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in a segmentation workflow; and inputting the image data into the segmentation workflow, and performing segmentation processing on the image data.
In one embodiment, the processing function interface includes a first pre-processing function interface and a first post-processing function interface; when the processor executes the computer program to perform the step of segmenting the image data, the processor is further configured to: calling a first preprocessing function in the data processing plug-in unit through the first preprocessing function interface, and performing first preprocessing on the image data to obtain first preprocessed image data; inputting the first pre-processing image data into a first segmentation model of the segmentation workflow to obtain a first image segmentation result and transmitting the first image segmentation result to the first post-processing function interface; and calling a first post-processing function in the data processing plug-in through the first post-processing function interface, and performing post-processing on the first image segmentation result to obtain a first image segmentation post-processing result.
In one embodiment, the data processing function interface further comprises a second pre-processing function interface and a second post-processing function interface; when the processor executes the computer program to perform the step of segmenting the image data, the processor is further configured to: transmitting the first image segmentation post-processing result to the second preprocessing function interface through the first post-processing function interface; calling a second preprocessing function in the data processing plug-in through the second preprocessing function interface, and performing second preprocessing on the processing result after the first image is segmented to obtain second preprocessed image data; inputting the second pre-processing image data into a second segmentation model of the segmentation workflow through the second pre-processing function interface to obtain a second image segmentation result, and transmitting the second image segmentation result to the second post-processing function interface; and calling a second post-processing function in the data processing plug-in through the second post-processing function interface, and post-processing the second image segmentation result by the second post-processing function to obtain a second image segmentation post-processing result.
In one embodiment, the processor, when executing the computer program, is further configured to: storing the image data before being processed through the first preprocessing function; when the processor executes the computer program to implement the step of performing the second preprocessing on the first image segmentation post-processing result, the processor is further configured to: receiving the image data transferred by the first preprocessing function through the second preprocessing function, wherein the image data is image data before being processed; and performing second preprocessing on the first image segmentation post-processing result and the image data before the first image segmentation post-processing result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving a newly added plug-in request, wherein the newly added plug-in request carries a newly added plug-in and a plug-in initialization function; generating a newly added plug-in identifier according to the plug-in newly adding request; and storing the newly added plug-in identification, the newly added plug-in and the plug-in initialization function in the plug-in library in an associated manner.
In one embodiment, the processor, when executing the computer program, further performs the steps of: searching a plug-in initialization function corresponding to the target plug-in identification from the plug-in library; and performing plug-in initialization on the data processing plug-in according to the plug-in initialization function.
In one embodiment, the processor when executing the computer program further performs the steps of: receiving a plug-in configuration file, and reading a configuration plug-in identifier and a plug-in requirement function from the plug-in configuration file; searching a function code matched with the plug-in requirement function from the plug-in library; and assembling the function codes to generate a demand configuration plug-in, and storing the configuration plug-in identification and the demand configuration plug-in into the plug-in library in an associated manner.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of: reading image data and acquiring a target plug-in identification; acquiring a data processing plug-in corresponding to the target plug-in identification from a plug-in library; respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in a segmentation workflow; and inputting the image data into the segmentation workflow, and performing segmentation processing on the image data.
In one embodiment, the processing function interface includes a first pre-processing function interface and a first post-processing function interface; the computer program, when executed by the processor, further causes the apparatus to perform the step of segmenting the image data by: calling a first preprocessing function in the data processing plug-in through the first preprocessing function interface, and performing first preprocessing on the image data to obtain first preprocessed image data; inputting the first pre-processing image data into a first segmentation model of the segmentation workflow to obtain a first image segmentation result and transmitting the first image segmentation result to the first post-processing function interface; and calling a first post-processing function in the data processing plug-in through the first post-processing function interface, and performing post-processing on the first image segmentation result to obtain a first image segmentation post-processing result.
In one embodiment, the data processing function interface further comprises a second pre-processing function interface and a second post-processing function interface; the computer program, when executed by the processor, further causes the apparatus to perform the step of segmenting the image data by: transmitting the first image segmentation post-processing result to the second preprocessing function interface through the first post-processing function interface; calling a second preprocessing function in the data processing plug-in through the second preprocessing function interface, and performing second preprocessing on the processing result after the first image is segmented to obtain second preprocessed image data; inputting the second pre-processing image data into a second segmentation model of the segmentation workflow through the second pre-processing function interface to obtain a second image segmentation result, and transmitting the second image segmentation result to the second post-processing function interface; and calling a second post-processing function in the data processing plug-in through the second post-processing function interface, and performing post-processing on the second image segmentation result by using the second post-processing function to obtain a second image segmentation post-processing result.
In one embodiment, the computer program, when executed by the processor, further performs the step of performing segmentation processing on the image data, further comprising: storing the image data before being processed through the first preprocessing function; when the computer program is executed by the processor, the step of performing the second preprocessing on the first image segmentation post-processing result is further configured to: receiving the image data transferred by the first preprocessing function through the second preprocessing function, wherein the image data is image data before being processed; and performing second preprocessing on the first image segmentation post-processing result and the image data before the first image segmentation post-processing result.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a newly added plug-in request, wherein the newly added plug-in request carries a newly added plug-in and a plug-in initialization function; generating a newly added plug-in identification according to the plug-in newly adding request; and storing the newly added plug-in identification, the newly added plug-in and the plug-in initialization function in the plug-in library in an associated manner.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching a plug-in initialization function corresponding to the target plug-in identification from the plug-in library; and performing plug-in initialization on the data processing plug-in according to the plug-in initialization function.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a plug-in configuration file, and reading a configuration plug-in identifier and a plug-in requirement function from the plug-in configuration file; searching a function code matched with the plug-in requirement function from the plug-in library; and assembling the function codes to generate a demand configuration plug-in, and storing the configuration plug-in identification and the demand configuration plug-in into the plug-in library in an associated manner.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An image segmentation processing method, the method comprising:
reading image data and acquiring a target plug-in identification;
acquiring a data processing plug-in corresponding to the target plug-in identification from a plug-in library;
respectively accessing each data processing function in the data processing plug-in into a corresponding data processing function interface in a segmentation workflow; the data processing function comprises a function for preprocessing image data and a function for post-processing a segmentation processing result;
and inputting the image data into the segmentation workflow, and performing segmentation processing on the image data.
2. The method of claim 1, wherein the data processing function interface comprises a first pre-processing function interface and a first post-processing function interface; the segmenting the image data includes:
calling a first preprocessing function in the data processing plug-in through the first preprocessing function interface, and performing first preprocessing on the image data to obtain first preprocessed image data;
inputting the first pre-processing image data into a first segmentation model of the segmentation workflow to obtain a first image segmentation result and transmitting the first image segmentation result to the first post-processing function interface;
and calling a first post-processing function in the data processing plug-in through the first post-processing function interface, and performing post-processing on the first image segmentation result to obtain a first image segmentation post-processing result.
3. The method of claim 2, wherein the data processing function interfaces further comprise a second pre-processing function interface and a second post-processing function interface; after the first image segmentation post-processing result is obtained, the method further includes:
transmitting the first image segmentation post-processing result to the second preprocessing function interface through the first post-processing function interface;
calling a second preprocessing function in the data processing plug-in through the second preprocessing function interface, and performing second preprocessing on the processing result after the first image is segmented to obtain second preprocessed image data;
inputting the second pre-processing image data into a second segmentation model of the segmentation workflow through the second pre-processing function interface to obtain a second image segmentation result, and transmitting the second image segmentation result to the second post-processing function interface;
and calling a second post-processing function in the data processing plug-in through the second post-processing function interface, and post-processing the second image segmentation result by the second post-processing function to obtain a second image segmentation post-processing result.
4. The method of claim 3, wherein the first pre-processing function interface calls a first pre-processing function in the data processing plug-in, and after performing the first pre-processing on the image data to obtain first pre-processed image data, the method comprises:
storing the image data before being processed through the first preprocessing function;
the second preprocessing is performed on the first image segmentation post-processing result, and includes:
receiving the image data transferred by the first preprocessing function through the second preprocessing function, wherein the image data is image data before being processed;
and performing second preprocessing on the first image segmentation post-processing result and the image data before the first image segmentation post-processing result.
5. The method of claim 1, further comprising:
receiving a newly added plug-in request, wherein the newly added plug-in request carries a newly added plug-in and a plug-in initialization function;
generating a newly added plug-in identifier according to the plug-in newly adding request;
and storing the newly added plug-in identification, the newly added plug-in and the plug-in initialization function in the plug-in library in an associated manner.
6. The method according to claim 5, wherein after the obtaining the data processing plug-in corresponding to the target plug-in identification from the plug-in library, further comprising:
searching a plug-in initialization function corresponding to the target plug-in identification from the plug-in library;
and performing plug-in initialization on the data processing plug-in according to the plug-in initialization function.
7. The method of claim 1, further comprising:
receiving a plug-in configuration file, and reading a configuration plug-in identifier and a plug-in requirement function from the plug-in configuration file;
searching a function code matched with the plug-in requirement function from the plug-in library;
and assembling the function codes to generate a demand configuration plug-in, and storing the configuration plug-in identification and the demand configuration plug-in into the plug-in library in an associated manner.
8. An image segmentation processing apparatus, characterized in that the apparatus comprises:
the data reading module is used for reading image data and acquiring a target plug-in identification;
the plug-in acquisition module is used for acquiring the data processing plug-in corresponding to the target plug-in identification from a plug-in library;
the interface access module is used for respectively accessing each data processing function in the data processing plug-in to a corresponding data processing function interface in the segmentation workflow; the data processing function comprises a function for preprocessing image data and a function for post-processing a segmentation processing result;
and the image segmentation module is used for inputting the image data into the segmentation workflow and carrying out segmentation processing on the image data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910725288.1A CN110569083B (en) | 2019-08-07 | 2019-08-07 | Image segmentation processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910725288.1A CN110569083B (en) | 2019-08-07 | 2019-08-07 | Image segmentation processing method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110569083A CN110569083A (en) | 2019-12-13 |
| CN110569083B true CN110569083B (en) | 2022-11-25 |
Family
ID=68774797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910725288.1A Active CN110569083B (en) | 2019-08-07 | 2019-08-07 | Image segmentation processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110569083B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111276219A (en) * | 2020-01-16 | 2020-06-12 | 上海联影医疗科技有限公司 | Medical imaging processing method, device, equipment and medium |
| CN112866814A (en) * | 2020-12-30 | 2021-05-28 | 广州虎牙科技有限公司 | Audio and video processing method and device |
| WO2023050418A1 (en) * | 2021-09-30 | 2023-04-06 | 深圳传音控股股份有限公司 | Data processing method, data processing system, electronic device, and storage medium |
| CN114357299A (en) * | 2021-12-31 | 2022-04-15 | 广州趣丸网络科技有限公司 | Data processing method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1154637A1 (en) * | 2000-05-13 | 2001-11-14 | Orell Füssli Sicherheitsdruck AG | Method for colour separation |
| JP2011048716A (en) * | 2009-08-28 | 2011-03-10 | Ricoh Co Ltd | Image processing system, management device, image processor, management method, program and recording medium |
| CN102419863A (en) * | 2011-08-22 | 2012-04-18 | 深圳市旭东数字医学影像技术有限公司 | Multi-stage medical image data processing method and system |
| JP2013138284A (en) * | 2011-12-28 | 2013-07-11 | Fuji Xerox Co Ltd | Image forming apparatus and program |
| CN104462174A (en) * | 2013-09-17 | 2015-03-25 | 株式会社理光 | Data processing apparatus, data processing method, and computer-readable recording medium |
| CN104461562A (en) * | 2014-12-22 | 2015-03-25 | 山东中创软件商用中间件股份有限公司 | Task creating method and system |
| CN105094818A (en) * | 2015-07-14 | 2015-11-25 | 国家信息中心 | Method and system for building comprehensive application of natural resources based on SOA |
| JP2016048583A (en) * | 2015-12-10 | 2016-04-07 | パイオニア株式会社 | Image processing apparatus and image processing method |
| CN109660684A (en) * | 2017-10-10 | 2019-04-19 | 佳能株式会社 | Image processing apparatus and its control method and storage medium |
| CN109949395A (en) * | 2019-03-15 | 2019-06-28 | 智慧足迹数据科技有限公司 | Thermodynamic chart rendering method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8139249B2 (en) * | 2007-06-29 | 2012-03-20 | Xerox Corporation | Event driven plugin architecture for importing scanned image data into a production workflow |
| US8122181B2 (en) * | 2008-11-13 | 2012-02-21 | Spansion Llc | Systems and methods for enhancing a data store for handling semantic information |
| JP5391889B2 (en) * | 2009-07-13 | 2014-01-15 | 株式会社リコー | Image forming apparatus, image processing apparatus, image processing system, image processing method, program, and recording medium |
| JP2011151492A (en) * | 2010-01-19 | 2011-08-04 | Ricoh Co Ltd | Image processing system, image processing apparatus, image segmentation program, and recording medium |
| JP6065031B2 (en) * | 2015-01-07 | 2017-01-25 | 株式会社リコー | Information processing apparatus, information processing system, display control method, and program |
| EP3286337A4 (en) * | 2015-04-23 | 2018-12-12 | Cedars-Sinai Medical Center | Automated delineation of nuclei for three dimensional (3-d) high content screening |
| US10599497B2 (en) * | 2017-04-26 | 2020-03-24 | International Business Machines Corporation | Invoking enhanced plug-ins and creating workflows having a series of enhanced plug-ins |
-
2019
- 2019-08-07 CN CN201910725288.1A patent/CN110569083B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1154637A1 (en) * | 2000-05-13 | 2001-11-14 | Orell Füssli Sicherheitsdruck AG | Method for colour separation |
| JP2011048716A (en) * | 2009-08-28 | 2011-03-10 | Ricoh Co Ltd | Image processing system, management device, image processor, management method, program and recording medium |
| CN102419863A (en) * | 2011-08-22 | 2012-04-18 | 深圳市旭东数字医学影像技术有限公司 | Multi-stage medical image data processing method and system |
| JP2013138284A (en) * | 2011-12-28 | 2013-07-11 | Fuji Xerox Co Ltd | Image forming apparatus and program |
| CN104462174A (en) * | 2013-09-17 | 2015-03-25 | 株式会社理光 | Data processing apparatus, data processing method, and computer-readable recording medium |
| CN104461562A (en) * | 2014-12-22 | 2015-03-25 | 山东中创软件商用中间件股份有限公司 | Task creating method and system |
| CN105094818A (en) * | 2015-07-14 | 2015-11-25 | 国家信息中心 | Method and system for building comprehensive application of natural resources based on SOA |
| JP2016048583A (en) * | 2015-12-10 | 2016-04-07 | パイオニア株式会社 | Image processing apparatus and image processing method |
| CN109660684A (en) * | 2017-10-10 | 2019-04-19 | 佳能株式会社 | Image processing apparatus and its control method and storage medium |
| CN109949395A (en) * | 2019-03-15 | 2019-06-28 | 智慧足迹数据科技有限公司 | Thermodynamic chart rendering method and device |
Non-Patent Citations (1)
| Title |
|---|
| "基于图像处理的车身漆膜缺陷识别与分类研究";骆亚微;《中国优秀硕士学位论文全文数据库 工程科技I辑》;20160915;B018-7 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110569083A (en) | 2019-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569083B (en) | Image segmentation processing method and device, computer equipment and storage medium | |
| CN109446302B (en) | Question-answer data processing method and device based on machine learning and computer equipment | |
| CN109032662B (en) | Code file generation method and device, computer equipment and storage medium | |
| CN110290212B (en) | Service call recording method, device, computer equipment and storage medium | |
| CN110489951A (en) | Method, apparatus, computer equipment and the storage medium of risk identification | |
| CN110750267A (en) | Service information updating method and device, computer equipment and storage medium | |
| CN111783506B (en) | Method, apparatus and computer readable storage medium for determining target characteristics | |
| CN110378230B (en) | Missing face recognition method, device, computer equipment and storage medium | |
| CN110866491A (en) | Target retrieval method, device, computer readable storage medium and computer equipment | |
| CN110990390A (en) | Data cooperative processing method and device, computer equipment and storage medium | |
| CN110532543B (en) | Method, device, computer equipment and storage medium for analyzing and processing evidence materials | |
| CN110659298A (en) | Financial data processing method and device, computer equipment and storage medium | |
| CN112231224A (en) | Business system testing method, device, equipment and medium based on artificial intelligence | |
| CN112241646B (en) | Lane line recognition method, device, computer equipment and storage medium | |
| CN108200087B (en) | Web intrusion detection method and device, computer equipment and storage medium | |
| CN114968612B (en) | Data processing method, system and related equipment | |
| CN112783866A (en) | Data reading method and device, computer equipment and storage medium | |
| CN111158959A (en) | Virtual machine backup method and device and virtual machine recovery method and device | |
| CN110795171A (en) | Service data processing method and device, computer equipment and storage medium | |
| CN113032621A (en) | Data sampling method and device, computer equipment and storage medium | |
| CN112784029A (en) | Service processing method and device based on natural language processing and computer equipment | |
| CN116383234A (en) | Search statement generation method and device, computer equipment and storage medium | |
| CN114387656B (en) | Face-changing method, device, equipment and storage medium based on artificial intelligence | |
| CN108897772B (en) | Data source supplementing method and device, computer equipment and storage medium | |
| CN112819687B (en) | Cross-domain image conversion method, device, computer equipment and storage medium based on unsupervised neural network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |