WO2022089196A1 - 一种图像处理方法、装置、电子设备及存储介质 - Google Patents

一种图像处理方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2022089196A1
WO2022089196A1 PCT/CN2021/123273 CN2021123273W WO2022089196A1 WO 2022089196 A1 WO2022089196 A1 WO 2022089196A1 CN 2021123273 W CN2021123273 W CN 2021123273W WO 2022089196 A1 WO2022089196 A1 WO 2022089196A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
interface
job
job image
response
Prior art date
Application number
PCT/CN2021/123273
Other languages
English (en)
French (fr)
Inventor
秦一锋
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2022089196A1 publication Critical patent/WO2022089196A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G06V10/235—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on user input or interaction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition

Definitions

  • the embodiments of the present disclosure relate to the field of computer technologies, for example, to an image processing method, an apparatus, an electronic device, and a storage medium.
  • Online education can be understood as a teaching method using the network as a medium.
  • many schools and families have begun to use online education platforms to carry out teaching activities. For example, students upload homework images to the platform using the student side, and the platform provides the homework images to the teacher side for teachers or parents to check and other activities.
  • the embodiments of the present disclosure provide an image processing method, device, electronic device, and storage medium, which can automatically screen job images, reduce manual time-consuming in the teaching process, and improve user experience.
  • an embodiment of the present disclosure provides an image processing method, including:
  • the job image is uploaded to a preset platform.
  • an embodiment of the present disclosure further provides an image processing apparatus, including:
  • a recognition module configured to perform text recognition on the selected job image in the first interface in response to a triggering operation of the sending control in the first interface
  • a classification module configured to determine the true and false type of the job image based on the text content obtained by the recognition
  • An uploading module configured to upload the job image to a preset platform in response to determining that the true-false type is true.
  • an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:
  • processors one or more processors
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the image processing method according to any one of the embodiments of the present disclosure.
  • an embodiment of the present disclosure further provides a storage medium containing computer-executable instructions, the computer-executable instructions, when executed by a computer processor, are configured to perform the image processing according to any one of the embodiments of the present disclosure method.
  • FIG. 1 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a first interface in an image processing method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of a first pop-up window interface in an image processing method provided by an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram of a second pop-up window interface in an image processing method provided by an embodiment of the present disclosure
  • FIG. 5 is a schematic flowchart of an image processing method provided by another embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • the term “including” and variations thereof are open-ended inclusions, ie, "including but not limited to”.
  • the term “based on” is “based at least in part on.”
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; the term “some embodiments” means “at least some embodiments”. Relevant definitions of other terms will be given in the description below.
  • FIG. 1 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure.
  • the embodiment of the present disclosure is applicable to the situation of screening job images, and is especially suitable for the client application to upload job images to a preset platform.
  • the method can be executed by an image processing device, and the device can be implemented in the form of software and/or hardware, the device can be integrated into a client application, and can be installed in an electronic device along with the application , such as installed in electronic devices such as mobile phones, tablets, laptops or desktop computers.
  • the image processing method provided by this embodiment includes:
  • the first interface may be an interface in a client application (Application, APP), and the client application may be a student-side learning application, such as a homework application for guiding students' homework.
  • client application Application, APP
  • the client application may be a student-side learning application, such as a homework application for guiding students' homework.
  • thumbnails of the job images in the editing state can be displayed.
  • the client application can first determine the job image to be sent in response to the selection operation on the thumbnail of the editing state in the first interface; then, in response to the trigger operation of the sending control in the first interface, text the job image. Identify actions.
  • the optical character recognition (Optical Character Recognition, OCR) method and/or the OpenCV character recognition and detection method can be used to perform text recognition on the job image, and other text recognition methods can also be applied to this.
  • FIG. 2 is a schematic diagram of a first interface in an image processing method provided by an embodiment of the present disclosure.
  • the first interface includes but is not limited to: an area 201 containing job image related information and a sending control 202 .
  • the area 201 may include but not limited to: prompt copy control and job image display control.
  • the prompt copy control can be used to display the prompt copy, and the prompt copy can include the easy-to-understand copy “Written Assignment” corresponding to the “job image”, and can also include the total quantity value and the selected quantity value of the job image, etc. .
  • "Written assignment 3/4" can indicate that there are 4 assignment images recorded in total, and 3 assignment images are currently selected.
  • the display control of the homework image can be used to display the thumbnail of the homework image, and the display control can be set with a corner label control corresponding to the learning content of the homework image, for example, set the corner label control of the subject corresponding to the homework image, as shown in Figure 2 In the "Chinese” and "Mathematics" and other corner control.
  • the display control of the job image can also be used for editing with or without selection. As shown in Figure 2, a corner label control with a solid circle and a checkmark can be marked on the upper left of the selected display control, and a corner label control with a hollow circle can be marked on the upper left of the unselected display control.
  • the sending control in the first interface may be triggered, for example, the sending control 202 in FIG. 2 .
  • the application may perform character recognition on the selected job image in response to the triggering operation of the sending control in the first interface.
  • the present disclosure can be based on traditional k-proximity, decision tree, multilayer perceptron, naive Bayes (including Bernoulli Bayes, Gaussian Bayes and polynomial Bayes), logistic regression and support vector Machines and other methods are used to classify the true and false content of the recognized text. It is also possible to classify the authenticity of the recognized text content based on the method of machine learning, and it is also possible to identify the authenticity based on other methods, which will not be exhaustive here.
  • determining the authenticity type of the job image based on the recognized text content includes: inputting the recognized text content into a pre-trained classification model, so as to output the authenticity type of the work image through the classification model.
  • the classification model used to classify the true and false of the job image may include a classification model based on ensemble learning and a classification model based on deep learning.
  • the classification model based on ensemble learning may include classification models implemented based on ensemble learning algorithms such as random forest, AdaBoost, and Light Gradient Boosting Machine (lightGBM).
  • the classification model based on deep learning may include classification models implemented based on deep learning algorithms such as Feed Forward Neural Network (FNN) and Long Short-Term Memory (LSTM).
  • FNN Feed Forward Neural Network
  • LSTM Long Short-Term Memory
  • the above classification model can be pre-trained, so that the classification model can learn the job features in the real job.
  • the trained classification model can classify whether the recognized text content is a real job based on the job characteristics, and output the true and false types.
  • the true and false type of the text content can be used as the true and false type of the job image.
  • the preset platform may be considered to be the platform server corresponding to the client application disclosed in this implementation.
  • the homework image uploaded by the client application can be distributed to the corresponding teacher client application through the preset platform, so that the user of the teacher client can perform homework correction and other processing.
  • the operation of the teacher client user to screen the false homework images can be avoided to a certain extent, thereby reducing the time and cost of the teaching process. Manual time-consuming, improve user experience.
  • the process of uploading the job image to the preset platform further includes: displaying the sending progress control in the first pop-up window interface; in response to the triggering of canceling the sending control in the first pop-up window interface operation to terminate the sending process; when the sending is successful, the first pop-up window interface is switched to the sending success prompting control.
  • FIG. 3 is a schematic diagram of a first pop-up window interface in an image processing method provided by an embodiment of the present disclosure.
  • a mask layer with preset transparency may be covered on the first interface, and a first pop-up window interface 2021 including a sending progress control may be set on the mask layer.
  • the pop-up window interface 2021 including the sending progress control may include, but is not limited to, the sending progress control, which is set to prompt the sending progress, and the sending progress control is, for example, a circular progress bar plus a progress percentage style control, or other styles.
  • Prompt copy control you can add prompt copy, for example, add the copy of "Sending job", set to prompt that the job image is currently being sent; cancel send control, set to cancel the sending of the job image when it is triggered.
  • the first pop-up window interface 2021 including the sending progress control can be switched to the sending success prompting control 2022, and the sending successful prompting control can be other styles besides the style of FIG. 3, here Don't be exhausted.
  • the image processing method further includes: when the true-false type is false, displaying a prompt copy control in the second pop-up window interface to prompt the user to re-upload the job image.
  • the job image selected in the first interface may not be uploaded to the preset platform, for example, all selected job images are not uploaded to the preset platform, or only not uploaded to the preset platform. Upload an image of a job with false type false.
  • a second pop-up window interface can be popped up, and a prompt copy control can be displayed on the second interface, and the prompt copy control can prompt the user to re-upload the job image, for example, the user can be prompted to re-upload the fax. Fake Job image with type FALSE.
  • FIG. 4 is a schematic diagram of a second pop-up window interface in an image processing method provided by an embodiment of the present disclosure.
  • a mask layer with preset transparency can be covered on the first interface, and a second pop-up window interface 2023 including a control for sending a prompt copy can be set on the mask layer.
  • the prompt copy control in the second pop-up window interface 2023 can add prompt copy, for example, add the copy of "XX upload failed, please upload the image of the assignment", which is set to prompt the user to upload the real image of the assignment.
  • the second pop-up window interface 2023 may also include an consent control, which is set to return to the first interface when triggered, so that the user can re-upload the job image, and the consent control may be added with a copy such as "OK" , to indicate that the user agrees to re-upload the job image;
  • the second pop-up window interface 2023 also includes an objection control, which is set to send a job image whose true and false type is false to the preset platform when triggered, and the objection control can be added with " Insist on sending” and other texts, so that the user can upload the job image smoothly if the true and false types are incorrectly identified.
  • the technical solution of the embodiment of the present disclosure in response to a trigger operation of sending a control in the first interface, text recognition is performed on the selected job image in the first interface; the recognized text content is input into a pre-trained classification model to pass the classification model Output the true and false type of the job image; when the true and false type is true, upload the job image to the preset platform.
  • the technical solutions of the embodiments of the present disclosure can automatically screen the homework images by performing character recognition and true and false classification on the homework images before uploading the homework images, reducing the manual time-consuming of the teaching process and improving the user experience.
  • the image processing method provided in this embodiment supplements the steps of generating the job image, evaluating the image quality of the job image, and identifying the handwriting of the job image.
  • the step of generating the job image the job image to be sent can be generated; by evaluating the image quality of the job image, the high-quality job image can be used for character recognition, and the accuracy of character recognition can be improved; Homework ghostwriting behavior recognition.
  • the screening effect of job images can be further improved, and user experience can be improved.
  • FIG. 5 is a schematic flowchart of an image processing method provided by another embodiment of the present disclosure. As shown in FIG. 5 , the image processing method provided by this embodiment includes:
  • the client application may establish a communication connection with an image capture device (eg, a camera) in advance, and may activate the image capture device when receiving a trigger operation of a start control of the image capture device, so as to use the image capture device to perform image capturing collection.
  • an image capture device eg, a camera
  • the image collection device may be deployed at a position where the desk top can be photographed from above, for example, it may be an overhead camera of a smart desk lamp.
  • the first area image may be an image of the acquisition area of the image acquisition device.
  • the image of the first area is collected according to preset rules, for example, the image of the first area may be collected every preset time period (for example, 1s, 3s, etc.); another example may be when the edge of the target (for example, a book) is detected.
  • images of the first area are collected at preset time intervals, and the collection is stopped after detecting that the edge of the target object leaves the collection area.
  • S512 in response to the photographing instruction, collect an image of the first area.
  • the client application may set a photographing control on at least one interface, and may generate a photographing instruction in response to a triggering operation of the photographing control, and control the image acquisition device to collect an image of the first area according to the photographing instruction.
  • the image acquisition device By collecting the image of the first area according to the photographing instruction, it is possible to assist the user to collect the homework image more targetedly. For example, when the homework of a certain department is completed, in response to the user triggering the operation of the photographing control, the completed homework of the department is photographed. , so as to further improve the user experience.
  • steps S511 and S512 are in an "and/or" relationship, that is, the client application can collect images of the first area according to preset rules, or collect images of the first area according to photographing instructions, or both according to preset rules.
  • the image of the first area, and the image of the first area is collected according to the photographing instruction.
  • the client not only collects the image of the first area according to the preset rule, but also collects the image of the first area according to the photographing instruction, and the relationship is "and", there is no strict sequence relationship between steps S511 and S512.
  • the first area image can be preprocessed to correct and/or highlight the homework part in the first area image, so as to facilitate character recognition and subsequent homework by the teacher end user Correction, etc.
  • preprocessing the first area image includes, but is not limited to: determining target corner points in the first area image, and cropping the first area image according to the target corner point; and/or, performing rectifying; and/or, performing image enhancement on the first region image.
  • the method of determining the target corners may be: corner detection based on grayscale features (such as gradient features, etc.) of the first region image, or corner detection based on binary features of the first region image, or based on the first region image.
  • the contour curve of the regional image is used for corner detection; the target corners are determined according to the detection results. For example, each corner detected can be used as the target corner, or some corners can be selected from the detected corners. as the target corner.
  • the process of screening some corner points may be, for example, determining the degree of matching between each corner point and the corner points in the preset corner point model, and screening the corner points with high matching degree as the target corner points.
  • the preset corner point model may be, for example, a model that includes six corner points and is in the shape of an open book page, or may be other models.
  • the positions of each corner point of the work part can be identified from the first area image;
  • the operation part in the area image is convenient for subsequent steps such as character recognition.
  • performing the correction on the image of the first area includes, but is not limited to, performing rectangle correction for removing distortion on the image in the first area, and/or rotation correction for adjusting the angle of the image, and the like.
  • performing image correction it is beneficial to improve the accuracy of character recognition.
  • performing enhancement processing on the image of the first region includes, but is not limited to, image sharpening processing based on methods such as gradient method, high-pass filtering method, or mask matching method.
  • image sharpening processing based on methods such as gradient method, high-pass filtering method, or mask matching method.
  • the first region image may be cropped according to the identified target corners, and then the cropped image may be corrected and image enhanced to obtain a job image, thereby greatly improving the success of character recognition. rate and accuracy.
  • Image Quality Assessment is currently one of the basic technologies in image processing. It mainly evaluates the quality of the image (image distortion degree) by analyzing and studying the characteristics of the image.
  • the image quality evaluation for the job image selected in the first interface may be performed by using the objective evaluation method in IQA to perform image quality assessment on the job image.
  • the objective evaluation methods may include, but are not limited to, traditional full reference (Full Reference-IQA, FR-IQA), semi-reference (Reduced Reference-IQA, RR-IQA) and no reference (No Reference-IQA, NR-IQA) ) evaluation method; evaluation method based on machine learning algorithm, for example, first use support vector machine (Support Vector Machine, SVM) to identify distortion types, and then establish support vector regression (SVR) regression analysis for specific distortion types
  • SVM Support Vector Machine
  • SVR support vector regression
  • the evaluation indicators include but are not included in Linear Correlation Coefficient (LCC) and Spearman's Rank Order Correlation Coefficient (SROCC), etc.
  • LCC Linear Correlation Coefficient
  • SROCC Spearman's Rank Order Correlation Coefficient
  • the handwriting features of the user of the client application may be pre-extracted before handwriting identification is performed, and the steps of extracting the handwriting features may include but are not limited to: when the client application is started for the first time, first enter the user's handwriting, for example, according to the received Historical job images, in order to recognize the handwriting in the historical job images as user handwriting, and for example, instruct the user to input specified characters or numbers; transformation) to extract handwriting features of different frequencies and/or different directions.
  • the same feature extraction method as when the user features are extracted in advance can be used to extract the handwriting features in the job image; then the k-proximity algorithm or the SVM method can be used. Classify whether it is user handwriting.
  • the identification result is the same handwriting, it can be considered that the identification is passed.
  • the job ghostwriting behavior can be identified, thereby facilitating the realization of the anti-cheating business function on the client application side, and further improving the user experience.
  • steps S531-S541 and steps S532-S542 are in an and/or relationship, that is, the client application can perform text recognition of the job image when the image quality assessment is passed, and can also perform text recognition of the job image when the handwriting identification is passed, It is also possible to perform character recognition of the work image when both the image quality evaluation and the handwriting identification are passed. Moreover, when the client performs both image quality evaluation and handwriting identification, the image quality evaluation can be performed first, which is beneficial to the success rate of handwriting identification.
  • the technical solutions of the embodiments of the present disclosure supplement the steps of generating a job image, evaluating the image quality of the job image, and identifying the handwriting of the job image.
  • the job image to be sent can be generated; by evaluating the image quality of the job image, the high-quality job image can be used for character recognition, and the accuracy of character recognition can be improved; Homework ghostwriting behavior recognition.
  • the image processing method provided in this embodiment the screening effect of job images can be further improved, and user experience can be improved.
  • the image processing methods provided by the embodiments of the present disclosure and the image processing methods provided by the above-mentioned embodiments belong to the same technical concept. For technical details not described in detail in this embodiment, please refer to the above-mentioned embodiments, and the same technical features are described in this embodiment. This example has the same beneficial effects as in the above-mentioned embodiment.
  • FIG. 6 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure.
  • the image processing apparatus provided in this embodiment is suitable for screening job images, especially for a situation where a client application automatically identifies true and false job images before uploading job images to a preset platform.
  • the image processing device includes:
  • the recognition module 610 is configured to perform text recognition on the selected job image in the first interface in response to the triggering operation of the sending control in the first interface;
  • the classification module 620 is configured to judge the true and false type of the job image based on the recognized text content
  • the uploading module 630 is configured to upload the job image to the preset platform when the true-false type is true.
  • the upload module also includes:
  • the progress display sub-module is set to display the sending progress control on the first pop-up window interface during the process of uploading the job image to the preset platform;
  • Cancel the uploading sub-module and is set to terminate the sending process in response to the triggering operation of canceling the sending control in the first pop-up window interface
  • the sending success prompt sub-module is set to switch the first pop-up window interface to the send success prompt control when the sending is successful.
  • the upload module also includes:
  • the re-upload prompt sub-module is set to display the prompt copy control in the second pop-up interface to prompt the user to re-upload the job image when the true and false type is false.
  • the image processing apparatus further includes:
  • the job image generation module is configured to, before responding to the triggering operation of sending the control in the first interface, collect the image of the first area according to a preset rule; and/or, collect the image of the first area in response to the photographing instruction ; Preprocess the image of the first area to obtain a job image.
  • the job image generation module includes:
  • a preprocessing submodule configured to determine a target corner point in the first area image, and crop the first area image according to the target corner point; and/or, correct the first area image; Area image for image enhancement.
  • the identification module further includes:
  • a quality assessment submodule configured to perform image quality assessment on the job image selected in the first interface before performing text recognition on the job image selected in the first interface;
  • the text recognition sub-module is configured to perform text recognition on the job image selected in the first interface when the evaluation is passed.
  • the identification module further includes:
  • a handwriting identification sub-module configured to perform handwriting identification on the selected job image in the first interface before character recognition is performed on the selected job image in the first interface;
  • the character recognition sub-module is configured to perform character recognition on the selected job image in the first interface when the authentication is passed.
  • the classification module is configured to: input the recognized text content into a pre-trained classification model, so as to output the true and false types of the job images through the classification model.
  • the image processing apparatus provided by the embodiment of the present disclosure can execute the image processing method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the execution method.
  • FIG. 7 it shows a schematic structural diagram of an electronic device (eg, a terminal device or a server in FIG. 7 ) 100 suitable for implementing an embodiment of the present disclosure.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (eg, mobile terminals such as in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 7 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 100 may include a processing device (such as a central processing unit, a graphics processor, etc.) 101, which may be stored in a read-only memory (Read-Only Memory, ROM) 102 according to a program or from a storage device 106 is loaded into a program in a random access memory (Random Access Memory, RAM) 103 to perform various appropriate actions and processes.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • various programs and data required for the operation of the electronic device 100 are also stored.
  • the processing device 101, the ROM 102, and the RAM 103 are connected to each other through a bus 104.
  • An input/output (I/O) interface 105 is also connected to the bus 104 .
  • the following devices may be connected to the I/O interface 105: input devices 106 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 107 such as a computer; a storage device 108 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 109 .
  • Communication means 109 may allow electronic device 100 to communicate wirelessly or by wire with other devices to exchange data.
  • FIG. 7 shows the electronic device 100 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 109 , or from the storage device 106 , or from the ROM 102 .
  • the processing apparatus 101 executes the above-mentioned functions defined in the methods of the embodiments of the present disclosure.
  • the electronic device provided by the embodiment of the present disclosure and the image processing method provided by the above-mentioned embodiment belong to the same disclosed concept.
  • the technical details not described in detail in this embodiment please refer to the above-mentioned embodiment, and this embodiment has the same characteristics as the above-mentioned embodiment. beneficial effect.
  • Embodiments of the present disclosure provide a computer storage medium on which a computer program is stored, and when the program is executed by a processor, implements the image processing method provided by the foregoing embodiments.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above.
  • Computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Erasable Programmable Read-Only Memory (EPROM) or flash memory (FLASH), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon.
  • Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol) to communicate, and can communicate with digital data in any form or medium.
  • Data communications eg, communication networks
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • LAN local area networks
  • WAN wide area networks
  • the Internet eg, the Internet
  • peer-to-peer networks eg, ad hoc peer-to-peer networks
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device:
  • character recognition is performed on the selected job image in the first interface; the true and false type of the job image is judged based on the recognized text content; when the true and false type is true, the job image is Upload to the default platform.
  • Computer program code for performing operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and This includes conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), and/or, may be connected to an external computer (eg, using an Internet service provider) to connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. Wherein, the names of units and modules do not constitute limitations on the units or modules themselves under certain circumstances.
  • the recognition module may also be described as a "character recognition module".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (Application Specific Standard Products) Standard Parts, ASSP), system on chip (System on Chip, SOC), complex programmable logic device (CPLD) and so on.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSP Application Specific Standard Products
  • ASOC System on Chip
  • CPLD complex programmable logic device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • Example 1 provides an image processing method, the method includes:
  • the job image is uploaded to a preset platform.
  • Example 2 provides an image processing method, further comprising:
  • the process of uploading the job image to the preset platform further includes:
  • the first pop-up window interface is switched to a sending success prompting control.
  • Example 3 provides an image processing method, further comprising:
  • the prompt copy control is displayed in the second pop-up window interface to prompt the user to re-upload the job image.
  • Example 4 provides an image processing method, further comprising:
  • the method before the responding to the triggering operation of sending the control in the first interface, the method further includes:
  • the image of the first region is collected; and/or,
  • the first area image is preprocessed to obtain a job image.
  • Example 5 provides an image processing method, further comprising:
  • the preprocessing of the first region image includes:
  • Image enhancement is performed on the first region image.
  • Example 6 provides an image processing method, further comprising:
  • the method before performing character recognition on the job image selected in the first interface, the method further includes:
  • the performing text recognition on the job image selected in the first interface includes:
  • character recognition is performed on the selected job image in the first interface.
  • Example 7 provides an image processing method, further comprising:
  • the method before performing character recognition on the job image selected in the first interface, the method further includes:
  • the performing text recognition on the job image selected in the first interface includes:
  • Example 8 provides an image processing method, further comprising:
  • the determining the authenticity type of the job image based on the recognized text content includes:

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Character Discrimination (AREA)
  • Character Input (AREA)

Abstract

本公开实施例公开了一种图像处理方法、装置、电子设备及存储介质，其中该方法，包括：响应于第一界面中发送控件的触发操作，对所述第一界面中选中的作业图像进行文字识别；基于识别得到的文字内容判断所述作业图像的真假类型；响应于确定所述真假类型为真，将所述作业图像上传至预设平台。

Description

一种图像处理方法、装置、电子设备及存储介质
本申请要求在2020年10月27日提交中国专利局、申请号为202011162866.4的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开实施例涉及计算机技术领域，例如涉及一种图像处理方法、装置、电子设备及存储介质。
背景技术
在线教育可以理解为，以网络为介质的教学方式。目前，许多学校和家庭都开始使用在线教育平台来开展教学活动，例如学生利用学生端将作业图像上传到平台，平台将作业图像提供给老师端以供老师或家长检查等活动。
任意拍摄的图像都可以上传到平台中，容易出现提供给老师端的图像为虚假作业图像的情况。不足之处至少包括：虚假作业图像增加了老师端用户进行图像筛选的人工耗时，导致教学过程效率低下，影响用户体验。
发明内容
本公开实施例提供了一种图像处理方法、装置、电子设备及存储介质，能够对作业图像进行自动筛选，减少教学过程的人工耗时，提高用户体验。
第一方面，本公开实施例提供了一种图像处理方法，包括：
响应于第一界面中发送控件的触发操作，对所述第一界面中选中的作业图像进行文字识别；
基于识别得到的文字内容确定所述作业图像的真假类型；
响应于确定所述真假类型为真，将所述作业图像上传至预设平台。
第二方面，本公开实施例还提供了一种图像处理装置，包括：
识别模块，设置为响应于第一界面中发送控件的触发操作，对所述第一界面中选中的作业图像进行文字识别；
分类模块，设置为基于识别得到的文字内容确定所述作业图像的真假类型；
上传模块，设置为响应于确定所述真假类型为真，将所述作业图像上传至 预设平台。
第三方面，本公开实施例还提供了一种电子设备，所述电子设备包括：
一个或多个处理器；
存储装置，设置为存储一个或多个程序，
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如本公开实施例任一所述的图像处理方法。
第四方面，本公开实施例还提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时设置为执行如本公开实施例任一所述的图像处理方法。
附图说明
贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1为本公开一实施例所提供的一种图像处理方法的流程示意图；
图2为本公开一实施例所提供的一种图像处理方法中第一界面的示意图；
图3为本公开一实施例所提供的一种图像处理方法中第一弹窗界面的示意图；
图4为本公开一实施例所提供的一种图像处理方法中第二弹窗界面的示意图；
图5为本公开另一实施例所提供的一种图像处理方法的流程示意图；
图6为本公开一实施例提供的一种图像处理装置结构示意图；
图7为本公开一实施例所提供的一种电子设备结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行 示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
图1为本公开一实施例所提供的一种图像处理方法的流程示意图，本公开实施例适用于对作业图像进行筛选的情形，尤其适用于客户端应用向预设平台上传作业图像前，对作业图像自动辨识真假的情形，该方法可以由图像处理装置来执行，该装置可以通过软件和/或硬件的形式实现，该装置可集成于客户端应用，并可随应用安装于电子设备中，例如安装于手机、平板电脑、笔记本电脑或台式计算机等电子设备中。
如图1所示，本实施例提供的图像处理方法，包括：
S110、响应于第一界面中发送控件的触发操作，对第一界面中选中的作业图像进行文字识别。
本公开实施例中，第一界面可以为客户端应用(Application，APP)中的界面，且客户端应用可以是学生侧的学习类应用，例如是指导学生作业的作业应用。
在第一界面中，可展示有处于编辑状态的作业图像的缩图。相应的，客户端应用可首先响应于对第一界面中编辑状态的缩图的选中操作，确定待发送的作业图像；然后响应于第一界面中的发送控件的触发操作，将作业图像进行文字识别操作。其中，可以利用光学字符识别(Optical Character Recognition，OCR)方法和/或OpenCV文字识别与检测方法，来对作业图像进行文字识别，且其他文字识别方法也可以应用于此。
示例性的，图2为本公开一实施例所提供的一种图像处理方法中第一界面 的示意图。参见图2，第一界面中包括但不限于：包含作业图像相关信息的区域201和发送控件202。
其中，区域201中可以包括但不限于：提示文案控件和作业图像的展示控件。其中，提示文案控件可以用于展示提示文案，且提示文案可包括，与“作业图像”对应的通俗易懂的文案“书面作业”，还可以包括作业图像的总数量值和被选中数量值等。如图2中，“书面作业3/4”可以表征共记录有4张作业图像，且有3张作业图像目前被选中。
其中，作业图像的展示控件可以用于展示作业图像的缩图，且该展示控件中可以设置与作业图像对应学习内容的角标控件，例如设置与作业图像对应学科的角标控件，如图2中“语文”和“数学”等角标控件。其中，作业图像的展示控件，还可以用于进行选中或不选中的编辑。如图2中，被选中的展示控件的左上方可以标注有实心圆加对号的角标控件，未被选中的展示控件左上方可标注有空心圆的角标控件。
当用户选中全部待发送的作业图像后，可以触发第一界面中的发送控件，例如图2中的发送控件202。应用可响应于第一界面中发送控件的触发操作，将选中的作业图像进行文字识别。
S120、基于识别得到的文字内容判断作业图像的真假类型。
本公开实施例中，可以基于传统的k邻近、决策树、多层感知器、朴素贝叶斯(包括伯努利贝叶斯、高斯贝叶斯和多项式贝叶斯)、逻辑回归和支持向量机等方式，对识别得到的文字内容进行真假分类。还可以基于机器学习的方法，对识别得到的文字内容进行真假分类，此外还可以基于其他方法识别进行真假判断，在此不做穷举。
在一些示例的实施方式中，基于识别得到的文字内容判断作业图像的真假类型，包括：将识别得到的文字内容输入预先训练的分类模型，以通过分类模型输出作业图像的真假类型。
其中，用于进行作业图像真假分类的分类模型，可以包括基于集成学习的分类模型和基于深度学习的分类模型。其中，基于集成学习的分类模型可以包括基于随机森林、AdaBoost和轻量级梯度提升机(Light Gradient Boosting Machine，lightGBM)等集成学习算法实现的分类模型。其中，基于深度学习的分类模型可以包括基于前馈神经网络(Feed Forward Neural Network，FNN)和长短期记忆网络(Long Short-Term Memory，LSTM)等深度学习算法实现的分 类模型。
基于真实作业的文字内容样本集和虚假作业的文字内容样本集，能够对上述分类模型进行预训练，以使分类模型学习真实作业中的作业特征。训练完成的分类模型，可以基于作业特征对识别得到的文字内容进行是否为真实作业的分类，并输出真假类型。相应的，文字内容的真假类型即可以作为作业图像的真假类型。
S130、于真假类型为真时，将作业图像上传至预设平台。
其中，预设平台可以认为是，本实施公开的客户端应用对应的平台服务器。通过预设平台可以将客户端应用上传的作业图像，分发至相对应的教师客户端应用中，以使教师客户端的用户进行作业批改等处理。通过在客户端应用侧进行作业图像的自动筛查，并将真实作业的作业图像上传至预设平台，能够在一定程度上避免教师客户端用户筛选虚假作业图像的操作，从而能够减少教学过程的人工耗时，提高用户体验。
在一些示例的实现方式中，在将作业图像上传至预设平台的过程中，还包括：将发送进度控件展示于第一弹窗界面中；响应于第一弹窗界面中取消发送控件的触发操作，终止发送过程；在发送成功时，将第一弹窗界面切换为发送成功提示控件。
在这些示例的实现方式中，通过在作业图像发送过程中，利用弹窗界面进行发送进度提示，并在发送成功后将弹窗控件切换为发送成功提示控件，可以使用户清楚了解到作业图像的发送进度，可进一步提高用户体验。
示例性的，图3为本公开一实施例所提供的一种图像处理方法中第一弹窗界面的示意图。
参见图3，可以在第一界面上覆盖一层预设透明度的蒙层，并可在蒙层上设置包含发送进度控件的第一弹窗界面2021。其中，包含发送进度控件的弹窗界面2021，可以包括但不限于：发送进度控件，设置为提示发送进度，且发送进度控件例如为圆形进度条加进度百分比样式的控件，也可以为其他样式的控件；提示文案控件，可以添加提示文案，例如添加“正在发送作业”的文案，设置为提示当前正在发送作业图像；取消发送控件，设置为被触发时，取消发送作业图像。
又参见图3，当数据发送完成时，包含发送进度控件的第一弹窗界面2021可以切换为发送成功提示控件2022，且发送成功提示控件除图3的样式外还可 以为其他样式，在此不做穷举。
在一些示例的实现方式中，图像处理方法，还包括：于真假类型为假时，将提示文案控件展示于第二弹窗界面中，以提示用户重新上传作业图像。
在这些示例的实现方式中，在作业图像为虚假作业时，可以不将第一界面中选中的作业图像上传至预设平台，例如全部选中的作业图像都不上传至预设平台，或者仅不上传真假类型为假的作业图像。并且，在作业图像为虚假作业时，还可以弹出第二弹窗界面，且第二界面中可展示有提示文案控件，提示文案控件中可以提示用户重新上传作业图像，例如可以提示用户重新上传真假类型为假的作业图像。
示例性的，图4为本公开一实施例所提供的一种图像处理方法中第二弹窗界面的示意图。
参见图4，可以在第一界面上覆盖一层预设透明度的蒙层，并可在蒙层上设置包含发送提示文案控件的第二弹窗界面2023。其中，第二弹窗界面2023中的提示文案控件，可以添加提示文案，例如添加“××上传失败，请上传作业图像哦”的文案，设置为提示用户上传真实的作业图像。
又参见图4，第二弹窗界面2023中还可以包括同意控件，设置为在被触发时返回第一界面，以供用户重新上传作业图像，且同意控件上可添加有“好的”等文案，以表征用户同意重新上传作业图像；第二弹窗界面2023中还包括反对控件，设置为在被触发时发送真假类型为假的作业图像至预设平台，且反对控件上可添加有“坚持发送”等文案，以使在真假类型识别错误的情况下，用户可顺利上传作业图像。
本公开实施例的技术方案，响应于第一界面中发送控件的触发操作，对第一界面中选中的作业图像进行文字识别；将识别得到的文字内容输入预先训练的分类模型，以通过分类模型输出作业图像的真假类型；于真假类型为真时，将作业图像上传至预设平台。本公开实施例的技术方案，通过在上传作业图像前，对作业图像进行文字识别和真假分类，能够对作业图像进行自动筛选，减少教学过程的人工耗时，提高用户体验。
本实施例与上述实施例中提供的图像处理方法中各个示例方案可以结合。本实施例提供的图像处理方法对作业图像的生成、作业图像的图像质量评估以及作业图像的笔迹鉴别等步骤进行补充。通过作业图像的生成步骤，能够生成 待发送的作业图像；通过对作业图像进行图像质量评估，能够利用高质量作业图像进行文字识别，提高文字识别准确率；通过对作业图像进行笔迹鉴别，能够对作业代写行为识别。通过本实施例提供的图像处理方法，能够进一步提高作业图像的筛选效果，提高用户体验。
图5为本公开另一实施例所提供的一种图像处理方法的流程示意图。如图5所示，本实施例提供的图像处理方法，包括：
S511、按预设规则，对第一区域图像进行采集。
本实施例中，客户端应用可以预先与图像采集设备(例如摄像头)建立通信连接，并且可以在接收到图像采集设备的启动控件的触发操作时，启动图像采集设备，以利用图像采集设备进行图像采集。其中，为了使采集的图像能够较好的呈现作业的页面情况，图像采集设备可以部署于可俯拍书桌桌面的位置处，例如可以是智能台灯的顶置摄像头。
其中，第一区域图像可以是图像采集设备的采集区域的图像。按预设规则对第一区域图像进行采集，例如可以是每隔预设时长(例如1s、3s等)，对第一区域图像进行采集；又如可以是在检测到目标物(例如书本)边缘进入采集区域后，每隔预设时长对第一区域图像进行采集，在检测到目标物边缘离开采集区域后，停止采集等。通过每隔预设时长进行采集，不仅能够实现作业图像的自动记录，而且相较于实时采集来说，也能够在一定程度上减少存储占用资源，提高应用运行流畅度。
S512、响应于拍照指令，对第一区域图像进行采集。
本实施例中，客户端应用可以在至少一个界面上设置拍照控件，并可响应于拍照控件的触发操作生成拍照指令，根据拍照指令控制图像采集设备采集第一区域图像。通过根据拍照指令对第一区域图像进行采集，能够协助用户更有针对性地进行作业图像采集，例如在某科作业完成时，响应于用户触发拍照控件的操作对该科已完成的作业进行拍照，从而进一步提升用户体验。
其中，S511步骤和S512步骤为“和/或”的关系，即客户端应用可以按预设规则采集第一区域图像，也可以根据拍照指令采集第一区域图像，还可以既按预设规则采集第一区域图像，又根据拍照指令采集第一区域图像。并且，当客户端既按预设规则采集第一区域图像，又根据拍照指令采集第一区域图像，为“和”关系时，S511步骤和S512步骤无严格的时序关系。
S520、对第一区域图像进行预处理，得到作业图像。
其中，采集到第一区域图像后，可以对第一区域图像进行预处理，以对第一区域图像中的作业部分进行矫正和/或突出，从而有利于文字识别，以及后续教师端用户进行作业批改等操作。
其中，对第一区域图像进行预处理，包括但不限于：确定第一区域图像中的目标角点，根据目标角点对第一区域图像进行裁切；和/或，对第一区域图像进行矫正；和/或，对第一区域图像进行图像增强。
其中，目标角点的确定方式可以是，基于第一区域图像的灰度特征(例如梯度特征等)进行角点检测，或者基于第一区域图像的二值特征进行角点检测，或者基于第一区域图像的轮廓曲线进行角点检测；根据检测结果确定目标角点，例如可以是将检测得到的各角点作为目标角点，或者可以是从检测得到的各角点中，筛选出部分角点作为目标角点。
其中，筛选部分角点的过程例如可以是，确定各角点与预设角点模型中角点的匹配度，将匹配度高的角点筛选为目标角点。其中，预设角点模型例如可以是包含六个角点的，呈打开的书页状的模型，也可以为其他模型。
通过确定第一区域图像中的目标角点，可以实现从第一区域图像中标识出作业部分的各角点位置；通过根据目标角点对第一区域图像进行裁切，旨在分割出第一区域图像中的作业部分，以利于进行后续文字识别等步骤。
其中，对第一区域图像进行矫正包括但不限于，对第一区域图像进行去除畸变的矩形矫正，和/或调整图像角度的旋转矫正处理等。通过进行图像矫正，有利于提高文字识别准确率。
其中，对第一区域图像进行增强处理包括但不限于，基于梯度法、高通滤波法或掩模匹配法等方法进行的图像锐化处理等。通过进行图像增强处理，能够使图像中文字的特征更为突出，能够提高文字识别成功率。
在一些示例的实现方式中，可以先根据识别的目标角点对第一区域图像进行裁切，再对裁切后的图像进行矫正和图像增强，以得到作业图像，从而可大大提高文字识别成功率和准确率。
S531、响应于第一界面中发送控件的触发操作，对第一界面中选中的作业图像进行图像质量评估。
其中，图像质量评估(Image Quality Assessment，IQA)目前是图像处理中的基本技术之一，主要通过对图像进行特性分析研究，评估出图像优劣(图像失真程度)。本实施例中，对第一界面中选中的作业图像进行图像质量评估，可 以是利用IQA中的客观评估方式对作业图像进行图像质量评估。
其中，客观评估方式可以包括但不限于，传统的全参考(Full Reference-IQA，FR-IQA)、半参考(Reduced Reference-IQA，RR-IQA)和无参考(No Reference-IQA，NR-IQA)的评估方式；基于机器学习算法的评估方式，例如先用支持向量机(Support Vector Machine，SVM)进行失真类型识别，进而对特定失真类型建立支持向量回归(support vector regression，SVR)的回归分析模型的评估方式；基于神经网络的评估方式，例如基于卷积神经网络(Convolutionalneural networks，CNN)的评估方式。
其中，衡量图像质量评估结果的指标有很多，可以基于上述客观评估方式，对不同评估指标进行评估。其中，评估指标包括但不现于线性相关系数(Linear Correlation Coefficient，LCC)和Spearman秩相关系数(Spearman's Rank Order Correlation Coefficient，SROCC)等。
S541、于评估通过时，对第一界面中选中的作业图像进行文字识别。
其中，当评估指标达标时，可以认为评估通过。通过对作业图像进行质量评估，能够对质量欠佳的图像(例如清晰度较差、光线较暗等质量欠佳的图像)进行筛选，从而有利于文字识别，以及后续教师端用户进行作业批改等操作。
S532、响应于第一界面中发送控件的触发操作，对第一界面中选中的作业图像进行笔迹鉴别。
其中，可以在进行笔迹鉴别前，预先提取客户端应用的用户的笔迹特征，且提取笔迹特征步骤可以包括但不限于：在客户端应用首次被启动时，首先录入用户的笔迹，例如根据接收的历史作业图像，以将识别历史作业图像中的手写笔迹作为用户笔迹，又如指示用户录入规定的文字或数字等；然后可根据录入笔迹，进行笔迹特征提取，例如利用加窗傅立叶变换(如Gabor变换)提取不同频率和/或不同方向的笔迹特征。
相应的，对第一界面选择的作业图像进行笔迹鉴别时，可以首先采用与预先提取用户特征时相同的特征提取方式，对作业图像中的笔迹特征进行提取；然后可使用k邻近算法或SVM方法进行是否为用户笔迹的分类。
S542、于鉴别通过时，对第一界面中选中的作业图像进行文字识别。
其中，当鉴别结果为相同笔迹时，可以认为鉴别通过。通过对作业图像进行笔迹鉴别，能够对作业代写行为进行识别，从而有利于实现在客户端应用侧即可实现反作弊的业务功能，进一步提高用户体验。
其中，S531-S541步骤和S532-S542步骤为和/或的关系，即客户端应用可以于图像质量评估通过时进行作业图像的文字识别，也可以于笔迹鉴别通过时进行作业图像的文字识别，还可以既于图像质量评估通过，且笔迹鉴别通过时，进行作业图像的文字识别。并且，当客户端既进行图像质量评估，又进行笔迹鉴别时，可以先进行图像质量评估，从而有利于笔迹鉴别的成功率。
S550、基于识别得到的文字内容判断作业图像的真假类型。
S561、于真假类型为真时，将作业图像上传至预设平台。
S562、于真假类型为假时，将提示文案控件展示于第二弹窗界面中，以提示用户重新上传作业图像。
本公开实施例的技术方案，对作业图像的生成、作业图像的图像质量评估以及作业图像的笔迹鉴别等步骤进行补充。通过作业图像的生成步骤，能够生成待发送的作业图像；通过对作业图像进行图像质量评估，能够利用高质量作业图像进行文字识别，提高文字识别准确率；通过对作业图像进行笔迹鉴别，能够对作业代写行为识别。通过本实施例提供的图像处理方法，能够进一步提高作业图像的筛选效果，提高用户体验。此外，本公开实施例提供的图像处理方法与上述实施例提供的图像处理方法属于同一技术构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且相同的技术特征在本实施例与上述实施例中具有相同的有益效果。
图6为本公开一实施例提供的一种图像处理装置结构示意图。本实施例提供的图像处理装置适用于对作业图像进行筛选的情形，尤其适用于客户端应用向预设平台上传作业图像前，对作业图像自动辨识真假的情形。
如图6所示，图像处理装置，包括：
识别模块610，设置为响应于第一界面中发送控件的触发操作，对第一界面中选中的作业图像进行文字识别；
分类模块620，设置为基于识别得到的文字内容判断作业图像的真假类型；
上传模块630，设置为于真假类型为真时，将作业图像上传至预设平台。
在一些示例的实现方式中，上传模块，还包括：
进度展示子模块，设置为在将作业图像上传至预设平台的过程中，将发送进度控件展示于第一弹窗界面中；
取消上传子模块，设置为响应于第一弹窗界面中取消发送控件的触发操作， 终止发送过程；
发送成功提示子模块，设置为在发送成功时，将第一弹窗界面切换为发送成功提示控件。
在一些示例的实现方式中，上传模块，还包括：
重新上传提示子模块，设置为于真假类型为假时，将提示文案控件展示于第二弹窗界面中，以提示用户重新上传作业图像。
在一些示例的实现方式中，图像处理装置，还包括：
作业图像生成模块，设置为在响应于第一界面中发送控件的触发操作之前，按预设规则，对第一区域图像进行采集；和/或，响应于拍照指令，对第一区域图像进行采集；对第一区域图像进行预处理，得到作业图像。
在一些示例的实现方式中，作业图像生成模块，包括：
预处理子模块，设置为确定第一区域图像中的目标角点，根据目标角点对第一区域图像进行裁切；和/或，对第一区域图像进行矫正；和/或，对第一区域图像进行图像增强。
在一些示例的实现方式中，识别模块，还包括：
质量评估子模块，设置为在对第一界面中选中的作业图像进行文字识别之前，对第一界面中选中的作业图像进行图像质量评估；
文字识别子模块，设置为于评估通过时，对第一界面中选中的作业图像进行文字识别。
在一些示例的实现方式中，识别模块，还包括：
笔迹鉴别子模块，设置为在对第一界面中选中的作业图像进行文字识别之前，对第一界面中选中的作业图像进行笔迹鉴别；
文字识别子模块，设置为于鉴别通过时，对第一界面中选中的作业图像进行文字识别。
在一些示例的实现方式中，分类模块，设置为：将识别得到的文字内容输入预先训练的分类模型，以通过分类模型输出作业图像的真假类型。
本公开实施例所提供的图像处理装置，可执行本公开任意实施例所提供的图像处理方法，具备执行方法相应的功能模块和有益效果。
值得注意的是，上述装置所包括的各个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的具体名称也只是为了便于相互区分，并不用于限制本公开实施例的 保护范围。
下面参考图7，其示出了适于用来实现本公开实施例的电子设备(例如图7中的终端设备或服务器)100的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图7示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图7所示，电子设备100可以包括处理装置(例如中央处理器、图形处理器等)101，其可以根据存储在只读存储器(Read-Only Memory，ROM)102中的程序或者从存储装置106加载到随机访问存储器(Random Access Memory，RAM)103中的程序而执行各种适当的动作和处理。在RAM 103中，还存储有电子设备100操作所需的各种程序和数据。处理装置101、ROM 102以及RAM 103通过总线104彼此相连。输入/输出(I/O)接口105也连接至总线104。
通常，以下装置可以连接至I/O接口105：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置106；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置107；包括例如磁带、硬盘等的存储装置108；以及通信装置109。通信装置109可以允许电子设备100与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备100，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置109从网络上被下载和安装，或者从存储装置106被安装，或者从ROM102被安装。在该计算机程序被处理装置101执行时，执行本公开实施例的方法中限定的上述功能。
本公开实施例提供的电子设备与上述实施例提供的图像处理方法属于同一公开构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且本实 施例与上述实施例具有相同的有益效果。
本公开实施例提供了一种计算机存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述实施例所提供的图像处理方法。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)或闪存(FLASH)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(Hyper Text Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序 被该电子设备执行时，使得该电子设备：
响应于第一界面中发送控件的触发操作，对第一界面中选中的作业图像进行文字识别；基于识别得到的文字内容判断作业图像的真假类型；于真假类型为真时，将作业图像上传至预设平台。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，和/或，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元、模块的名称在某种情况下并不构成对该单元、模块本身的限定，例如，识别模块还可以被描述为“文字识别模块”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、片上***(System on Chip，SOC)、复杂可编程逻辑设备(CPLD)等 等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行***、装置或设备使用或与指令执行***、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体***、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，【示例一】提供了一种图像处理方法，该方法包括：
响应于第一界面中发送控件的触发操作，对所述第一界面中选中的作业图像进行文字识别；
基于识别得到的文字内容判断所述作业图像的真假类型；
于所述真假类型为真时，将所述作业图像上传至预设平台。
根据本公开的一个或多个实施例，【示例二】提供了一种图像处理方法，还包括：
在一些示例的实现方式中，在所述将所述作业图像上传至预设平台的过程中，还包括：
将发送进度控件展示于第一弹窗界面中；
响应于所述第一弹窗界面中取消发送控件的触发操作，终止发送过程；
在发送成功时，将所述第一弹窗界面切换为发送成功提示控件。
根据本公开的一个或多个实施例，【示例三】提供了一种图像处理方法，还包括：
于所述真假类型为假时，将提示文案控件展示于第二弹窗界面中，以提示用户重新上传作业图像。
根据本公开的一个或多个实施例，【示例四】提供了一种图像处理方法，还包括：
在一些示例的实现方式中，在所述响应于第一界面中发送控件的触发操作之前，还包括：
按预设规则，对第一区域图像进行采集；和/或，
响应于拍照指令，对第一区域图像进行采集；
对所述第一区域图像进行预处理，得到作业图像。
根据本公开的一个或多个实施例，【示例五】提供了一种图像处理方法，还包括：
在一些示例的实现方式中，所述对所述第一区域图像进行预处理，包括：
确定所述第一区域图像中的目标角点，根据所述目标角点对所述第一区域图像进行裁切；和/或，
对所述第一区域图像进行矫正；和/或，
对所述第一区域图像进行图像增强。
根据本公开的一个或多个实施例，【示例六】提供了一种图像处理方法，还包括：
在一些示例的实现方式中，在所述对所述第一界面中选中的作业图像进行文字识别之前，还包括：
对所述第一界面中选中的作业图像进行图像质量评估；
相应的，所述对所述第一界面中选中的作业图像进行文字识别，包括：
于评估通过时，对所述第一界面中选中的作业图像进行文字识别。
根据本公开的一个或多个实施例，【示例七】提供了一种图像处理方法，还包括：
在一些示例的实现方式中，在所述对所述第一界面中选中的作业图像进行文字识别之前，还包括：
对所述第一界面中选中的作业图像进行笔迹鉴别；
相应的，所述对所述第一界面中选中的作业图像进行文字识别，包括：
于鉴别通过时，对所述第一界面中选中的作业图像进行文字识别。
根据本公开的一个或多个实施例，【示例八】提供了一种图像处理方法，还包括：
在一些示例的实现方式中，所述基于识别得到的文字内容判断所述作业图像的真假类型，包括：
将识别得到的文字内容输入预先训练的分类模型，以通过所述分类模型输出所述作业图像的真假类型。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操 作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (11)

  1. 一种图像处理方法，包括：
    响应于第一界面中发送控件的触发操作，对所述第一界面中选中的作业图像进行文字识别；
    基于识别得到的文字内容确定所述作业图像的真假类型；
    响应于确定所述真假类型为真，将所述作业图像上传至预设平台。
  2. 根据权利要求1所述的方法，在所述将所述作业图像上传至预设平台的过程中，还包括：
    将发送进度控件展示于第一弹窗界面中；
    响应于所述第一弹窗界面中取消发送控件的触发操作，终止发送过程；
    在发送成功时，将所述第一弹窗界面切换为发送成功提示控件。
  3. 根据权利要求1所述的方法，还包括：
    响应于确定所述真假类型为假，将提示文案控件展示于第二弹窗界面中，以提示用户重新上传作业图像。
  4. 根据权利要求1所述的方法，在所述响应于第一界面中发送控件的触发操作之前，还包括以下至少之一的操作：
    按预设规则，对第一区域图像进行采集，并对所述第一区域图像进行预处理，得到作业图像；
    响应于拍照指令，对第一区域图像进行采集，并对所述第一区域图像进行预处理，得到作业图像。
  5. 根据权利要求4所述的方法，其中，所述对所述第一区域图像进行预处理，包括以下至少之一的方式：
    确定所述第一区域图像中的目标角点，根据所述目标角点对所述第一区域图像进行裁切；
    对所述第一区域图像进行矫正；以及
    对所述第一区域图像进行图像增强。
  6. 根据权利要求1所述的方法，在所述对所述第一界面中选中的作业图像进行文字识别之前，还包括：
    对所述第一界面中选中的作业图像进行图像质量评估；
    所述对所述第一界面中选中的作业图像进行文字识别，包括：
    响应于确定所述图像质量评估通过，对所述第一界面中选中的作业图像进 行文字识别。
  7. 根据权利要求1所述的方法，在所述对所述第一界面中选中的作业图像进行文字识别之前，还包括：
    对所述第一界面中选中的作业图像进行笔迹鉴别；
    所述对所述第一界面中选中的作业图像进行文字识别，包括：
    响应于确定笔迹鉴别通过，对所述第一界面中选中的作业图像进行文字识别。
  8. 根据权利要求1所述的方法，其中，所述基于识别得到的文字内容确定所述作业图像的真假类型，包括：
    将识别得到的文字内容输入预先训练的分类模型，以通过所述分类模型输出所述作业图像的真假类型。
  9. 一种图像处理装置，包括：
    识别模块，设置为响应于第一界面中发送控件的触发操作，对所述第一界面中选中的作业图像进行文字识别；
    分类模块，设置为基于识别得到的文字内容确定所述作业图像的真假类型；
    上传模块，设置为响应于确定所述真假类型为真，将所述作业图像上传至预设平台。
  10. 一种电子设备，包括：
    至少一个处理器；
    存储装置，设置为存储至少一个程序，
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-8中任一所述的图像处理方法。
  11. 一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时设置为执行如权利要求1-8中任一所述的图像处理方法。
PCT/CN2021/123273 2020-10-27 2021-10-12 一种图像处理方法、装置、电子设备及存储介质 WO2022089196A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011162866.4 2020-10-27
CN202011162866.4A CN112308067A (zh) 2020-10-27 2020-10-27 一种图像处理方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022089196A1 true WO2022089196A1 (zh) 2022-05-05

Family

ID=74330950

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/123273 WO2022089196A1 (zh) 2020-10-27 2021-10-12 一种图像处理方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN112308067A (zh)
WO (1) WO2022089196A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112308067A (zh) * 2020-10-27 2021-02-02 北京字节跳动网络技术有限公司 一种图像处理方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109446900A (zh) * 2018-09-21 2019-03-08 平安科技（深圳）有限公司 证件真伪验证方法、装置、计算机设备及存储介质
JP2019113860A (ja) * 2019-03-15 2019-07-11 富士通株式会社 正誤判定ルール設定プログラム、正誤判定ルール設定方法および正誤判定ルール設定装置
CN110298454A (zh) * 2019-05-22 2019-10-01 深圳壹账通智能科技有限公司 作业图像的审核方法、装置、计算机设备及存储介质
CN111046760A (zh) * 2019-11-29 2020-04-21 山东浪潮人工智能研究院有限公司 一种基于域对抗网络的笔迹鉴定方法
CN111753830A (zh) * 2020-06-22 2020-10-09 作业不凡(北京)教育科技有限公司 一种作业图像校正方法和计算设备
CN112308067A (zh) * 2020-10-27 2021-02-02 北京字节跳动网络技术有限公司 一种图像处理方法、装置、电子设备及存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008204212A (ja) * 2007-02-21 2008-09-04 Promise Co Ltd 契約情報管理システム
CN106504599A (zh) * 2016-11-29 2017-03-15 华中师范大学 在线作业批改的方法、装置及***
CN109242856A (zh) * 2017-07-10 2019-01-18 杭州亿教亿学网络科技有限公司 一种纸质作业电子化批阅方法及装置
CN108364004A (zh) * 2018-01-16 2018-08-03 深圳市脑洞科技有限公司 基于移动终端的答题卡扫描方法、移动终端及存储介质
CN108735021A (zh) * 2018-05-23 2018-11-02 郭金荣 一种用于学生作业的智能辅导***
CN109227564A (zh) * 2018-10-19 2019-01-18 南京工业大学 一种纸质作业自动批改机器人
CN109741650A (zh) * 2019-03-22 2019-05-10 任磊 一种计算机教学分析改进***
CN110097052A (zh) * 2019-04-22 2019-08-06 苏州海赛人工智能有限公司 一种基于图像的真假车牌判别方法
CN110245591B (zh) * 2019-05-30 2022-09-13 宋西军 课堂监督***及与之关联的作业评判***
CN110942030A (zh) * 2019-11-27 2020-03-31 安徽师范大学 一种作业上传批改装置和控制方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109446900A (zh) * 2018-09-21 2019-03-08 平安科技（深圳）有限公司 证件真伪验证方法、装置、计算机设备及存储介质
JP2019113860A (ja) * 2019-03-15 2019-07-11 富士通株式会社 正誤判定ルール設定プログラム、正誤判定ルール設定方法および正誤判定ルール設定装置
CN110298454A (zh) * 2019-05-22 2019-10-01 深圳壹账通智能科技有限公司 作业图像的审核方法、装置、计算机设备及存储介质
CN111046760A (zh) * 2019-11-29 2020-04-21 山东浪潮人工智能研究院有限公司 一种基于域对抗网络的笔迹鉴定方法
CN111753830A (zh) * 2020-06-22 2020-10-09 作业不凡(北京)教育科技有限公司 一种作业图像校正方法和计算设备
CN112308067A (zh) * 2020-10-27 2021-02-02 北京字节跳动网络技术有限公司 一种图像处理方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN112308067A (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
US10902056B2 (en) Method and apparatus for processing image
US9721156B2 (en) Gift card recognition using a camera
US11270099B2 (en) Method and apparatus for generating facial feature
US9390340B2 (en) Image-based character recognition
CN109614934B (zh) 在线教学质量评估参数生成方法及装置
US9239961B1 (en) Text recognition near an edge
TWI712980B (zh) 理賠資訊提取方法和裝置、電子設備
CN111738041A (zh) 一种视频分割方法、装置、设备及介质
CN111885375A (zh) 双录视频的检验方法、装置、服务器及***
CN113515942A (zh) 文本处理方法、装置、计算机设备及存储介质
KR20180109499A (ko) 사용자의 음성 입력에 대한 답변을 제공하는 방법 및 장치
CN104442631A (zh) 一种汽车智能用户手册交互方法
CN110399934A (zh) 一种视频分类方法、装置及电子设备
WO2023197648A1 (zh) 截图处理方法及装置、电子设备和计算机可读介质
WO2022089196A1 (zh) 一种图像处理方法、装置、电子设备及存储介质
US11348254B2 (en) Visual search method, computer device, and storage medium
WO2024061311A1 (zh) 模型训练方法、图像分类方法和装置
WO2022206404A1 (zh) 练字格检测方法、装置、可读介质及电子设备
JP2018060374A (ja) 情報処理装置、評価システムおよびプログラム
WO2021036823A1 (zh) 文本处理方法、装置、设备及介质
CN113486171B (zh) 一种图像处理方法及装置、电子设备
CN114972893A (zh) 一种数据标注方法、装置、电子设备和存储介质
CN111797790B (zh) 图像处理方法和装置、存储介质和电子设备
US11210335B2 (en) System and method for judging situation of object
CN113191251A (zh) 一种笔顺检测方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21884925

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 10.08.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21884925

Country of ref document: EP

Kind code of ref document: A1