WO2023284464A1 - 一种图像处理方法、装置、设备及存储介质 - Google Patents

一种图像处理方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023284464A1
WO2023284464A1 PCT/CN2022/098362 CN2022098362W WO2023284464A1 WO 2023284464 A1 WO2023284464 A1 WO 2023284464A1 CN 2022098362 W CN2022098362 W CN 2022098362W WO 2023284464 A1 WO2023284464 A1 WO 2023284464A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
preset
recognition
shooting
target image
Prior art date
Application number
PCT/CN2022/098362
Other languages
English (en)
French (fr)
Inventor
邱顺明
郭晓彬
李刚
李�根
张树鹏
Original Assignee
北京字跳网络技术有限公司
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 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Priority to BR112023024318A priority Critical patent/BR112023024318A2/pt
Priority to EP22841104.7A priority patent/EP4325439A1/en
Publication of WO2023284464A1 publication Critical patent/WO2023284464A1/zh
Priority to US18/511,639 priority patent/US20240087309A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/993—Evaluation of the quality of the acquired pattern
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
    • H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet

Definitions

  • the present disclosure relates to the field of data processing, and in particular to an image processing method, device, equipment and storage medium.
  • an embodiment of the present disclosure provides an image processing method, which enables the image recognition server to perform recognition based on the target image whose image definition meets the preset definition condition, and improves the The accuracy of image recognition.
  • the present disclosure provides an image processing method, the method comprising:
  • the image recognition server before sending the target image to the image recognition server, it also includes:
  • the preset object corresponding to the successfully matched feature parameter is determined as the initial recognition result of the target image.
  • the sending the target image to the image recognition server includes:
  • the sending the target image to the image recognition server further includes:
  • the target image is sent to the image recognition server.
  • the preset recognition operation triggered for the shooting picture on the shooting page is received, based on the shooting picture on the shooting page, it is determined that the image definition meets the preset definition condition target image, including:
  • a recognition failure prompt message is displayed on the shooting page.
  • the preset recognition operation triggered for the shooting picture on the shooting page is received, based on the shooting picture on the shooting page, it is determined that the image definition meets the preset definition condition target image, including:
  • a set of images to be processed is acquired; wherein, the set of images to be processed includes a continuous multi-frame image whose end frame is the current image corresponding to the shooting picture ;
  • An image whose image definition meets a preset definition condition is determined from the set of images to be processed as a target image.
  • a recognition failure prompt message is displayed on the shooting page.
  • the present disclosure also provides an image processing device, the device comprising:
  • the determining module is configured to determine a target image whose image definition meets the preset definition condition based on the shooting image on the shooting page when a preset recognition operation triggered for the shooting image on the shooting page is received;
  • a sending module configured to send the target image to an image recognition server; wherein, the image recognition server is configured to recognize the target image.
  • the present disclosure provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is made to implement the above method.
  • the present disclosure provides a device, including: a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the computer program, Implement the above method.
  • the present disclosure provides a computer program product, where the computer program product includes a computer program/instruction, and when the computer program/instruction is executed by a processor, the above method is implemented.
  • An embodiment of the present disclosure provides an image processing method. First, when a preset recognition operation triggered for a shooting picture on the shooting page is received, based on the shooting picture on the shooting page, it is determined that the image definition meets the preset definition condition target image. Then, the target image is sent to the image recognition server for recognizing the target image. It can be seen that the image processing method provided by the embodiment of the present disclosure can first determine the target image whose image definition meets the preset definition condition before performing image recognition, and enables the image recognition server to perform identification based on the target image whose definition meets the condition , thereby improving the accuracy of image recognition.
  • FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure
  • FIG. 2 is a flowchart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 3 is a flow chart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 4 is a flow chart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 5 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure.
  • an embodiment of the present disclosure proposes an image processing method. First, when a preset recognition operation triggered for a shooting picture on the shooting page is received, the image is determined based on the shooting picture on the shooting page. The target image whose sharpness meets the preset sharpness conditions. Then, the target image is sent to the image recognition server for recognizing the target image. It can be seen that the image processing method provided by the embodiment of the present disclosure can first determine the target image whose image definition meets the preset definition condition before performing image recognition, and enables the image recognition server to perform identification based on the target image whose definition meets the condition , thereby improving the accuracy of image recognition.
  • an embodiment of the present disclosure provides an image processing method, as shown in FIG. 1 , which is a flow chart of an image processing method provided by an embodiment of the present disclosure.
  • the method includes:
  • the modes of the preset recognition operation triggered for the shooting picture on the shooting page may include multiple ways, for example, way 1, triggering the long press operation for the shooting picture on the shooting page, wherein, the shooting picture can be any position on the shooting page to trigger a long press operation; the second method is to trigger an operation for the recognition control set on the shooting page, wherein the recognition control can be set at any position on the shooting page (such as: the right side of the shooting page, the bottom, etc. );etc.
  • the shooting picture on the shooting page may include one frame or multiple consecutive frames of images captured by the current camera.
  • the manner of determining whether the image sharpness of the image meets the preset sharpness condition may include processing the image based on the image sharpness model, so as to obtain a target image that meets the preset sharpness condition.
  • an image sharpness model is configured in a client (such as a mobile phone, a tablet computer, a computer, etc.) that has a shooting function (such as a camera), where the image sharpness model can be trained based on image samples of different resolutions , after the target image is processed by the image sharpness model, the score of the target image can be output.
  • the threshold of the image sharpness score is set to 80 points
  • the image that meets the preset sharpness condition means that the image corresponding to the image is clear
  • the degree score is greater than or equal to 80 points.
  • the threshold of the preset image sharpness score is used to determine whether the image sharpness of the image meets the preset sharpness condition, and can be set to 80 points, 85 points, 90 points, etc. based on requirements.
  • the embodiments of the present disclosure are for The preset threshold of the image sharpness score is not limited.
  • S102 Send the target image to the image recognition server.
  • the image recognition server is used to recognize the target image.
  • the target image determined in S101 above is sent to the image recognition server, and then the image recognition server recognizes the target image.
  • the image recognition server is connected to the client through communication. Based on the communication connection between the image recognition server and the client, the client can send the target image to the image recognition server, and the image recognition server can return the recognition result to the client. And/or a template recommended based on the recognition result, etc.
  • the image recognition server can return the recognition result and/or templates recommended based on the recognition result to the client. For example, the image recognition server returns the target image corresponding to the client. The description information of the recognition result "sunflower”; or return the recommended template corresponding to the recognition result "sunflower” corresponding to the target image, etc. If the target image recognition fails, the image recognition server can return a recognition failure instruction to the client to remind the user that the image recognition failed this time. At the same time, the image recognition server can return to the client a general recommendation template based on general scene recognition Wait. For example, flashing text is displayed on the shooting page to prompt the user, or a Toast pop-up window is used to prompt the user. Specifically, the prompt text can be "No matching results were identified, recommend a general template for you, or try to re-identify!, and display the general template at the bottom of the shooting page.
  • the image processing method provided by the embodiments of the present disclosure first, when receiving the preset recognition operation triggered for the shooting picture on the shooting page, based on the shooting picture on the shooting page, it is determined that the image definition meets the preset definition condition target image. Then, the target image is sent to the image recognition server for recognizing the target image. It can be seen that the image processing method provided by the embodiment of the present disclosure can first determine the target image whose image definition meets the preset definition condition before performing image recognition, and enables the image recognition server to perform identification based on the target image whose definition meets the condition , thereby improving the accuracy of image recognition. In addition, since the target image for recognition meets the preset definition condition, the occurrence of invalid input and invalid recognition is reduced, thus improving the efficiency of image recognition as a whole.
  • the method for determining whether the image sharpness meets the preset sharpness condition may include multiple implementation manners, and two specific implementation manners are listed below.
  • FIG. 2 it is a flowchart of another image processing method provided by an embodiment of the present disclosure, wherein the above S101 specifically includes:
  • the set of images to be processed includes consecutive multiple frames of images with the current image corresponding to the shooting frame as the end frame.
  • a set of images to be processed is acquired, wherein the set of images to be processed includes multiple consecutive images with the current image corresponding to the shooting picture as the end frame. frame image.
  • the preview image in the camera preview interface is stored in the form of a preview preview stream.
  • the preview image in the form of the stored preview stream can be selected. , to obtain the latest N frames of preview images, which together with the current image constitute an image set to be processed.
  • the continuous multi-frame images included in the image set to be processed and whose end frame is the current image corresponding to the shooting screen may be consecutive 5-frame images, continuous 7-frame images, etc.
  • the number of frames is not limited.
  • S202 Determine whether there is an image whose image definition meets the preset definition condition from the image set to be processed, if yes, use the image meeting the preset definition condition as the target image, and execute S102; if not determined, execute S203 .
  • each image in the image set to be processed may be processed separately based on the image recognition model, so as to determine whether there is an image whose image definition meets a preset definition condition in the image set to be processed.
  • an image that meets the preset definition condition means that the corresponding image resolution score of the image is greater than or equal to 80 points.
  • the image sets to be processed (assumed to include images 1 to 5) acquired in S201 are respectively input into the image sharpness model, based on the processing of the image sharpness model, the image sharpness score of each image is obtained, and Each image sharpness score is compared with a preset threshold (such as 80 points) to determine whether there is an image meeting the preset sharpness condition in the image set to be processed.
  • the image sharpness score of image 1 to image 5 is 70, 74, 76, 79, and 82 respectively, the image sharpness score of image 5 is greater than the preset threshold (such as 80 points), that is, image 5 is in line with the preset threshold. Image of sharpness condition. After the image 5 is determined as the target image, continue to execute S102 in the above embodiment.
  • the higher image sharpness score can be selected.
  • the corresponding image is taken as the target image.
  • the image sharpness scores of image 1 to image 5 are 70, 74, 78, 82, and 90 respectively, then the image sharpness scores of image 4 and image 5 are both greater than the preset threshold (such as 80 points), that is, image 4 1.
  • Image 5 is an image that meets the preset sharpness condition, and the image sharpness score of image 5 is relatively high, then image 5 can be selected as the target image. After the image 5 is determined as the target image, continue to execute S102 in the above embodiment.
  • a recognition failure prompt message is displayed on the shooting page.
  • the prompt message "recognition failed, please re-trigger the recognition function” is displayed on the shooting page, and flashes at a preset interval; or, a Toast pop-up window pops up on the shooting page to prompt the user that the recognition fails.
  • the client when it does not determine the target image whose resolution meets the preset image resolution conditions, it will not send the target image to the image recognition server, reducing the number of invalid recognitions of the image recognition server and reducing the number of invalid recognitions of the client. A waste of network resources between the server and the image recognition server.
  • the image set to be processed including multiple consecutive frames of images is acquired for the determination of the target image, and due to The image sets are all stored in the client, which may cause problems such as excessive memory usage and slowdown of the client system. Therefore, in order to reduce the pressure on the client memory, you can trigger During the preset recognition operation, only one frame of the current image corresponding to the shooting screen is acquired each time.
  • the embodiment of the present disclosure provides a flowchart of another image processing method, referring to FIG. 3 , including:
  • S301 Acquire a current image corresponding to the shooting screen when a preset recognition operation triggered for the shooting screen on the shooting page is received.
  • a current image corresponding to the shooting screen is acquired, and the current image corresponding to the shooting screen includes a frame of images, such as image 1 .
  • S302 Determine whether the image sharpness of the current image meets the preset sharpness condition, if so, determine the current image as the target image, and execute S102; if not, execute S303.
  • the acquired current image may be processed based on the image recognition model to determine whether the image definition of the current image meets the preset definition condition.
  • an image that meets the preset definition condition means that the corresponding image resolution score of the image is greater than or equal to 80 points.
  • the image definition score of the frame of the current image is obtained, and compared with a preset threshold (such as 80 points) A comparison is made to determine whether the image definition of the current image of the frame meets the preset definition condition.
  • the acquisition times of the current image after determining that the image definition of the current image does not meet the preset definition condition, it is determined whether the acquisition times of the current image have reached the preset number of image acquisitions, that is, the acquisition times of the current image and the preset image Fetch counts for comparison.
  • the preset image acquisition times may be 3 times, 5 times, 7 times, etc., and the embodiment of the present disclosure does not limit the preset image acquisition times.
  • the current image (such as image 1) corresponding to the shooting screen is acquired for the first time, based on the clarity of the image
  • the sharpness score of the image 1 is less than the preset threshold (eg, 80 points), it is determined that the sharpness of the image 1 does not meet the preset sharpness condition.
  • the number of acquisitions of the current image (accumulated twice) does not reach the preset number of acquisitions of images (such as 3 times), then continue to execute S301, and acquire the current image corresponding to the shooting picture (such as image 3) for the third time, based on the clearness of the image
  • the image sharpness score of image 3 is less than the preset threshold (eg, 80 points), it is determined that the image sharpness of image 2 does not meet the preset sharpness condition.
  • a prompt message of recognition failure is displayed on the shooting page.
  • the specific prompting method is as in the example of S203 above, which will not be repeated here.
  • the image processing method when the preset recognition operation triggered for the shooting picture on the shooting page is received, the current image corresponding to the shooting picture is acquired, and it is determined whether the image definition of the current image meets the preset clarity If the condition is met, the current image is determined to be the target image; if not, continue to acquire the current image corresponding to the shooting screen until the image definition of the acquired current image meets the preset definition condition, or the acquisition of the current image is obtained The number of times reaches the preset number of image acquisitions, and then, the target image is sent to the image recognition server or a recognition failure prompt message is displayed on the shooting page. It can be seen that the image processing method provided by the embodiment of the present disclosure can alleviate the problem that the running speed of the client system decreases due to excessive memory usage when determining the definition of the image.
  • the client before sending the target image to the image recognition server for image recognition, the client first performs initial recognition on the target image, and then sends the initial recognition result together with the target image to The image recognition server performs image recognition by combining the target image and the initial recognition result by the image recognition server, thereby improving the recognition efficiency of the target image.
  • the method for initially identifying a target image may include, first, extracting image features of the target image, and then matching the image features with pre-stored feature parameters of preset objects, and if it is determined that the matching If successful, the preset object corresponding to the successfully matched feature parameter is determined as the initial recognition result of the target image. Furthermore, the target image and the initial recognition result of the target image are sent to the image recognition server, and the target image is recognized based on the initial recognition result.
  • the characteristic parameter of the preset object may include the corresponding relationship between the preset object and the characteristic parameter.
  • the characteristic parameter of the preset object may include The corresponding relationship between " and the characteristic parameters of "flower”, the corresponding relationship between the characteristic parameters of "grass” and “grass”, the corresponding relationship between the characteristic parameters of "cat” and “cat”, etc.
  • the preset object corresponding to the successfully matched feature parameters is determined as the initial recognition result of the target image. It can be understood that the more pre-stored feature parameters corresponding to the preset object, the higher the accuracy of the initial recognition result for the preset object.
  • the initial recognition of the image may be implemented based on an image recognition model.
  • an image recognition model is configured on the client side, wherein the image recognition model is trained based on image samples with preset objects.
  • the image recognition model configured on the client side uses the image recognition model configured on the client side to initially recognize the target image, and after processing the image recognition model, the extracted image features of the target image indicate that the target image has the characteristics of "flowers”, and then determine the image features If it is successfully matched with the pre-stored feature parameter of "flower", the preset object "flower” is determined as the initial recognition result of the target image.
  • the target image and the initial recognition result corresponding to the target image are sent to the image recognition server, and the image recognition server recognizes the target image based on the initial recognition result.
  • the initial recognition result corresponding to the target image is "flower”
  • the type identification of "flower” is sent to the image recognition server together with the target image, wherein the image recognition server may include Image recognition models (such as: “recognition of flowers” model, “recognition of grass” model, "recognition of cats” model, etc.).
  • the "flower recognition” model in the image recognition server is called to recognize the target image and obtain the final recognition result.
  • the recognition result corresponding to the target image is "Sunflower "Wait.
  • the client before the target image is sent to the image recognition server for image recognition, the client performs initial recognition based on the image features of the target image to obtain the initial recognition result, and then sends the initial result and the target image to Image recognition server. Since the initial recognition result is obtained based on the image features of the target image and can directly represent the features of the target image, the image recognition server can identify the target image based on the initial recognition result to improve the accuracy of image recognition. In addition, the image recognition server can call the corresponding recognition model based on the initial recognition result, and then recognize the target image in a targeted manner, thus improving the image recognition efficiency as a whole.
  • the target image can be sent to the image recognition system separately.
  • the image recognition server only performs recognition based on the target image.
  • the image recognition server may further include a general recognition model for recognizing objects that fail to match the characteristic parameters of the preset objects. Specifically, if it is determined that the matching result of the image feature and the pre-stored feature parameters of the preset object is a matching failure, the target image is sent to the image recognition server separately, and the target image is processed by the image recognition server based on the general recognition model. Recognize, and after the recognition is successful, return the recognition result or a template recommended based on the recognition result to the client.
  • the embodiment of the present disclosure also provides an image processing method, as shown in FIG. 4 , which is provided by the embodiment of the present disclosure.
  • a flow chart of another image processing method, the method comprising:
  • S401 Acquire a current image corresponding to the shooting screen when a preset recognition operation triggered for the shooting screen on the shooting page is received.
  • S402 Determine whether the image sharpness of the current image meets the preset sharpness condition, if so, determine the current image as the target image, and execute S405; if not, execute S403.
  • S403 Determine whether the number of acquisitions of the current image reaches the preset number of acquisitions of images, if not, execute S401; if yes, execute S404.
  • S405 Extract image features of the target image.
  • S406 Match the image features with the pre-stored feature parameters of the preset object, and determine whether the matching result is successful, if yes, perform S407; if not, perform S408.
  • the characteristic parameters of the preset object include a correspondence between "flower” and characteristic parameters of "flower”; a correspondence between "grass” and characteristic parameters of "grass”; and so on.
  • the image features are matched with the feature parameters of the pre-stored preset objects. If it is determined that the matching result of the image features of image 1 and the feature parameters of the pre-stored preset objects is successful , execute S407. If it is determined that the matching result of the image features of the image 2 and the pre-stored feature parameters of the preset object is a failure, execute S408.
  • S407 Determine the preset object corresponding to the successfully matched characteristic parameters as the initial recognition result of the target image, and send the target image and the initial recognition result of the target image to the image recognition server, and recognize the target image based on the initial recognition result.
  • the image recognition server recognizes the image 1 based on the type identifier of "flower”, and obtains the final recognition result as "sunflower”.
  • the image recognition server returns the description information of "Sunflower” or the recommended template associated with the recognition result "Sunflower” to the client.
  • S408 Send the target image to the image recognition server for image recognition.
  • the image 2 is sent to the image recognition server.
  • the image recognition server recognizes the image 2 based on the general recognition model, it returns an instruction of recognition failure to the client, and returns an instruction based on the recognition result or based on the recognition Results recommended templates, etc.
  • a Toast pop-up window will display "No matching results have been identified, a general template is recommended for you, or please try to identify again!”, and the general template is displayed at the bottom of the shooting page.
  • the current image corresponding to the shooting picture is acquired, and it is determined whether the image definition of the current image meets the preset clarity If the condition is met, the current image is determined to be the target image; if not, continue to acquire the current image corresponding to the shooting screen until the image definition of the acquired current image meets the preset definition condition, or the acquisition of the current image is obtained The number of times reaches the preset number of image acquisitions.
  • the image features of the target image are extracted, the image features are matched with the feature parameters of the pre-stored preset objects, and the preset objects corresponding to the successfully matched feature parameters are determined as the initial recognition of the target image
  • the target image and the initial recognition result of the target image are sent to the image recognition server, and the target image is recognized based on the initial recognition result.
  • the embodiment of the present disclosure first determines the target image whose image definition meets the preset definition condition, and can initially identify the target image based on the image features of the target image, thereby enabling the image recognition server to be based on The initial recognition result performs image recognition on the target image, thereby improving the accuracy of image recognition.
  • the target image for recognition meets the preset definition condition, the occurrence of invalid input and invalid recognition is reduced, and the efficiency of image recognition is improved as a whole.
  • the number of times that the user fails to prompt recognition during the operation of the image recognition operation is reduced, thereby improving the user experience.
  • FIG. 5 it is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure, and the device includes:
  • the first determining module 501 is configured to, when receiving a preset recognition operation triggered for a shooting picture on the shooting page, determine a target image whose image definition meets a preset definition condition based on the shooting picture on the shooting page;
  • the sending module 502 is configured to send the target image to an image recognition server; wherein the image recognition server is configured to recognize the target image.
  • the device further includes:
  • An extraction module configured to extract image features of the target image
  • a matching module configured to match the image features with the feature parameters of pre-stored preset objects
  • the second determining module is configured to determine the preset object corresponding to the successfully matched feature parameter as the initial recognition result of the target image if it is determined that the matching is successful.
  • the sending module 502 includes:
  • the first sending sub-module is configured to send the target image and the initial recognition result of the target image to an image recognition server; wherein, the image recognition server is used to identify the target image based on the initial recognition result to identify.
  • the sending module 502 further includes:
  • the second sending submodule is configured to send the target image to the image recognition server if it is determined that the image feature fails to match the pre-stored preset object feature parameters.
  • the first determination module 501 includes:
  • the first acquiring submodule is configured to acquire the current image corresponding to the shooting picture when receiving the preset recognition operation triggered for the shooting picture on the shooting page, and determine whether the image definition of the current image meets the preset Clarity condition;
  • the second determination sub-module is used to determine the current image as the target image if it is determined that the image definition of the current image meets the preset definition condition, otherwise, re-execute the acquisition of the image corresponding to the shooting picture. the current image, and determine whether the image sharpness of the current image meets the preset sharpness condition until it is determined that the preset number of image acquisitions is reached.
  • the device further includes:
  • the first prompting module is used to display recognition failure prompt information on the shooting page when it is determined that the preset number of times of image acquisition has been reached and no image meeting the preset sharpness condition has been determined.
  • the first determining module 501 includes:
  • the second acquisition sub-module is configured to acquire a set of images to be processed when a preset recognition operation triggered for a shooting picture on the shooting page is received; wherein, the set of images to be processed includes a current image corresponding to the shooting picture Continuous multi-frame images for the end frame;
  • the second determination sub-module is configured to determine, from the set of images to be processed, an image whose image definition meets a preset definition condition as a target image.
  • the device further includes:
  • the second prompt module is configured to display a recognition failure prompt message on the shooting page if no image conforming to the preset sharpness condition is determined from the image set to be processed.
  • the image processing device provided by the embodiments of the present disclosure, firstly, upon receiving the preset recognition operation triggered for the shooting picture on the shooting page, based on the shooting picture on the shooting page, it is determined that the image definition conforms to the preset definition condition target image. Then, the target image is sent to the image recognition server for recognizing the target image. It can be seen that the image processing device provided by the embodiment of the present disclosure can first determine the target image whose image definition meets the preset definition condition before performing image recognition, and enables the image recognition server to perform identification based on the target image whose definition meets the condition , thereby improving the accuracy of image recognition. In addition, since the target image for recognition meets the preset definition condition, the occurrence of invalid input and invalid recognition is reduced, thus improving the efficiency of image recognition as a whole.
  • an embodiment of the present disclosure also provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device realizes this The image processing method described in the embodiment is disclosed.
  • the embodiment of the present disclosure also provides a computer program product, the computer program product includes a computer program/instruction, and when the computer program/instruction is executed by a processor, the image processing method described in the embodiment of the present disclosure is implemented.
  • an embodiment of the present disclosure also provides an image processing device, as shown in FIG. 6 , which may include:
  • Processor 601 , memory 602 , input device 603 and output device 604 The number of processors 601 in the image processing device may be one or more, and one processor is taken as an example in FIG. 6 .
  • the processor 601 , the memory 602 , the input device 603 and the output device 604 may be connected through a bus or in other ways, wherein connection through a bus is taken as an example in FIG. 6 .
  • the memory 602 can be used to store software programs and modules, and the processor 601 executes various functional applications and data processing of the image processing device by running the software programs and modules stored in the memory 602 .
  • the memory 602 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function, and the like.
  • the memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.
  • the input device 603 can be used to receive input digital or character information, and generate signal input related to user settings and function control of the image processing device.
  • the processor 601 will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the executable files stored in the memory 602. application programs to realize various functions of the above-mentioned image processing device.

Abstract

本公开提供了一种图像处理方法、装置、设备及存储介质，所述方法包括：在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像。然后，将目标图像发送至图像识别服务端，用于对该目标图像进行识别。可见，本公开实施例提供的图像处理方法能够在进行图像识别之前，首先确定图像清晰度符合预设清晰度条件的目标图像，并使得图像识别服务端能够基于清晰度符合条件的目标图像进行识别，从而提高了图像识别的准确率。

Description

一种图像处理方法、装置、设备及存储介质
本申请要求于2021年7月12日提交的申请号为202110783343.X、申请名称为“一种图像处理方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及数据处理领域，尤其涉及一种图像处理方法、装置、设备及存储介质。
背景技术
随着多媒体短视频的风靡，人们对图像或视频的拍摄兴趣高涨，拍摄页面的功能也越来越多，例如针对拍摄页面上的拍摄画面的识别功能，如何提高图像识别的准确率，是目前亟需解决的技术问题。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开实施例提供了一种图像处理方法，能够使得图像识别服务端基于图像清晰度符合预设清晰度条件的目标图像进行识别，提高了图像识别的准确率。
第一方面，本公开提供了一种图像处理方法，所述方法包括：
在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像；
将所述目标图像发送至图像识别服务端；其中，所述图像识别服务端用于对所述目标图像进行识别。
一种可选的实施方式中，所述将所述目标图像发送至图像识别服务端之前，还包括：
提取所述目标图像的图像特征；
将所述图像特征与预先存储的预设对象的特征参数进行匹配；
如果确定匹配成功，则将匹配成功的特征参数对应的预设对象确定为所述目标图像的初始识别结果。
相应的，所述将所述目标图像发送至图像识别服务端，包括：
将所述目标图像和所述目标图像的初始识别结果发送至图像识别服务端；其中，所述图像识别服务端用于基于所述初始识别结果对所述目标图像进行识别。
一种可选的实施方式中，所述将所述目标图像发送至图像识别服务端，还包括：
如果确定所述图像特征与预先存储的预设对象的特征参数匹配失败，则将所述目标图像发送至所述图像识别服务端。
一种可选的实施方式中，所述在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像，包括：
在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取所述拍摄画面对应的当前图像，并确定所述当前图像的图像清晰度是否符合预设清晰度条件；
如果确定所述当前图像的图像清晰度符合所述预设清晰度条件，则将所述当前图像确定为目标图像；，否则重新执行所述获取所述拍摄画面对应的当前图像，并确定所述当前图 像的图像清晰度是否符合预设清晰度条件的步骤，直到确定当前达到预设图像获取次数。
一种可选的实施方式中，在确定当前达到所述预设图像获取次数，且未确定出符合所述预设清晰度条件的图像时，在所述拍摄页面上显示识别失败提示信息。
一种可选的实施方式中，所述在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像，包括：
在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取待处理图像集；其中，所述待处理图像集中包括以所述拍摄画面对应的当前图像为结束帧的连续多帧图像；
从所述待处理图像集中确定图像清晰度符合预设清晰度条件的图像，作为目标图像。
一种可选的实施方式中，如果从所述待处理图像集中未确定出符合所述预设清晰度条件的图像，则在所述拍摄页面上显示识别失败提示信息。
第二方面，本公开还提供了一种图像处理装置，所述装置包括：
确定模块，用于在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像；
发送模块，用于将所述目标图像发送至图像识别服务端；其中，所述图像识别服务端用于对所述目标图像进行识别。
第三方面，本公开提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备实现上述的方法。
第四方面，本公开提供了一种设备，包括：存储器，处理器，及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时，实现上述的方法。
第五方面，本公开提供了一种计算机程序产品，所述计算机程序产品包括计算机程序/指令，所述计算机程序/指令被处理器执行时实现上述的方法。
本公开实施例提供的技术方案与现有技术相比具有如下优点：
本公开实施例提供了一种图像处理方法，首先，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像。然后，将目标图像发送至图像识别服务端，用于对该目标图像进行识别。可见，本公开实施例提供的图像处理方法能够在进行图像识别之前，首先确定图像清晰度符合预设清晰度条件的目标图像，并使得图像识别服务端能够基于清晰度符合条件的目标图像进行识别，从而提高了图像识别的准确率。
另外，由于进行识别的目标图像符合预设的清晰度条件，因此减少了出现无效输入与无效识别的情况，因此整体上提升了图像识别效率。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言， 在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种图像处理方法的流程图；
图2为本公开实施例提供的另一种图像处理方法的流程图；
图3为本公开实施例提供的另一种图像处理方法的流程图；
图4为本公开实施例提供的另一种图像处理方法的流程图；
图5为本公开实施例提供的一种图像处理装置的结构示意图；
图6为本公开实施例提供的一种图像处理设备的结构示意图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面将对本公开的方案进行进一步描述。需要说明的是，在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本公开，但本公开还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本公开的一部分实施例，而不是全部的实施例。
为了提高图像识别的准确率，本公开实施例提出了一种图像处理方法，首先，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像。然后，将目标图像发送至图像识别服务端，用于对该目标图像进行识别。可见，本公开实施例提供的图像处理方法能够在进行图像识别之前，首先确定图像清晰度符合预设清晰度条件的目标图像，并使得图像识别服务端能够基于清晰度符合条件的目标图像进行识别，从而提高了图像识别的准确率。
另外，由于进行识别的目标图像符合预设的清晰度条件，因此减少了出现无效输入与无效识别的情况，因此整体上提升了图像识别效率。
基于此，本公开实施例提供了一种图像处理方法，如图1所示，为本公开实施例提供的一种图像处理方法的流程图，该方法包括：
S101：在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像。
本公开实施例中，针对拍摄页面上的拍摄画面触发的预设识别操作的方式可以包括多种方式，例如，方式一、针对拍摄页面上的拍摄画面触发长按操作，其中，可以针对拍摄画面上的任意一个位置触发长按操作；方式二、针对拍摄页面上设置的识别控件的触发操作，其中，识别控件可以设置在拍摄页面上的任意位置(如：拍摄页面的右侧、下方等位置)；等等。
本公开实施例中，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的图像，作为目标图像。具体的实现方式在后续实施例中进行介绍，在此不再赘述。
其中，拍摄页面上的拍摄画面可以包括当前摄像头拍摄到的一帧或连续多帧图像。
本公开实施例中，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件 的图像，作为目标图像。在后续的识别过程中，基于符合预设清晰度条件的目标图像进行识别，有利于减少出现无效输入的情况。其中，确定图像的图像清晰度是否符合预设清晰度条件的方式可以包括基于图像清晰度模型对图像进行处理，从而得到符合预设清晰度条件的目标图像。
举例说明，假设在具有拍摄功能(如摄像头)的客户端(如手机、平板电脑、电脑等)中配置图像清晰度模型，其中，图像清晰度模型可以是基于不同清晰度的图像样本训练得到的，目标图像经过图像清晰度模型的处理后，可以输出目标图像的分值，假设设置图像清晰度分值的阈值为80分，则符合预设清晰度条件的图像是指该图像对应的图像清晰度分值大于或者等于80分。
需要说明的是，预设图像清晰度分值的阈值用来确定图像的图像清晰度是否符合预设清晰度条件，可以基于需求设置为80分、85分、90分等，本公开实施例对于预设图像清晰度分值的阈值不做限定。
S102：将目标图像发送至图像识别服务端。
其中，图像识别服务端用于对目标图像进行识别。
本公开实施例中，将上述S101中确定的目标图像发送至图像识别服务端，进而由图像识别服务端对目标图像进行识别。其中，图像识别服务端与客户端通信连接，基于图像识别服务端与客户端之间的通信连接，客户端能够将目标图像发送至图像识别服务端，图像识别服务端能够向客户端返回识别结果和/或基于识别结果推荐的模板等。
本公开实施例中，如果对目标图像识别成功，则图像识别服务端能够向客户端返回识别结果和/或基于识别结果推荐的模板等，例如，图像识别服务端向客户端返回目标图像对应的识别结果“向阳花”的描述信息；或者返回目标图像对应的识别结果“向阳花”对应的推荐模板等。如果对目标图像识别失败，则图像识别服务端能够向客户端返回识别失败的指令，以提示用户本次图像识别失败，同时，图像识别服务端可以向客户端返回基于通用场景识别的通用推荐模板等。例如，在拍摄页面上以闪烁的方式显示文字提示用户或者以Toast弹窗的形式提示用户等。具体的，提示性文字可以为“没有识别到匹配的结果，为您推荐通用模板，或请尝试重新识别！”，同时在拍摄页面下方展示通用模板。
本公开实施例提供的图像处理方法中，首先，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像。然后，将目标图像发送至图像识别服务端，用于对该目标图像进行识别。可见，本公开实施例提供的图像处理方法能够在进行图像识别之前，首先确定图像清晰度符合预设清晰度条件的目标图像，并使得图像识别服务端能够基于清晰度符合条件的目标图像进行识别，从而提高了图像识别的准确率。另外，由于进行识别的目标图像符合预设的清晰度条件，因此减少了出现无效输入与无效识别的情况，因此整体上提升了图像识别效率。
在上述实施例的基础上，用于确定图像清晰度是否符合预设清晰度条件的方法可以包括多种实现方式，以下列举两种具体的实现方式。
一种可选的实施方式中，如图2所示，为本公开实施例提供的另一种图像处理方法的流程图，其中，上述S101具体包括：
S201：在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取待处理图像集。
其中，待处理图像集中包括以拍摄画面对应的当前图像为结束帧的连续多帧图像。
本公开实施例中，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取待处理图像集，其中，待处理图像集中包括以拍摄画面对应的当前图像为结束帧的连续多帧图像。通常，相机预览界面中的预览图像是以preview预览流的形式进行存储的，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，可以从已存储的preview流形式的预览图片中，获取最新的N帧预览图像，与当前图像共同构成待处理图像集。
需要说明的是，待处理图像集中包括的以拍摄画面对应的当前图像为结束帧的连续多帧图像可以为连续5帧图像、连续7帧图像等，本公开实施例对于连续多帧图像的具体帧数不做限定。
S202：从待处理图像集中确定是否存在图像清晰度符合预设清晰度条件的图像，如果确定，则将符合预设清晰度条件的图像作为目标图像，并执行S102；如果未确定，则执行S203。
本公开实施例中，可以基于图像识别模型对待处理图像集中的各个图像分别进行处理，以确定待处理图像集中是否存在图像清晰度符合预设清晰度条件的图像。
以客户端中配置有图像清晰度模型，并且设置图像清晰度分值的阈值为80分为例，符合预设清晰度条件的图像为该图像对应的图像清晰度分值大于或者等于80分。具体的，将S201中获取的待处理图像集(假设包括图像1～图像5)分别输入至图像清晰度模型中，基于图像清晰度模型的处理，得到每张图像的图像清晰度分值，并将各个图像清晰度分值与预设阈值(如80分)进行比较，以确定待处理图像集中是否有符合预设清晰度条件的图像。
举例说明，如果待处理图像集中仅有一帧图像的图像清晰度分值大于或等于图像清晰度阈值，即仅有一帧图像符合预设清晰度条件，则该图像直接被确定为目标图像。假设图像1～图像5的图像清晰度分值分别为70、74、76、79、82，则图像5的图像清晰度分值大于预设阈值(如80分)，即图像5为符合预设清晰度条件的图像。将图像5确定为目标图像后，继续执行上述实施例中的S102。
如果待处理图像集中存在多帧图像的图像清晰度分值大于或等于图像清晰度阈值，即待处理图像集中存在多帧图像符合预设清晰度条件，则可以将其中图像清晰度分值较高对应的图像作为目标图像。假设图像1～图像5的图像清晰度分值分别为70、74、78、82、90，则图像4、图像5的图像清晰度分值均大于预设阈值(如80分)，即图像4、图像5为符合预设清晰度条件的图像，并且图像5的图像清晰度分值较高，则可以选取图像5作为目标图像。将图像5确定为目标图像后，继续执行上述实施例中的S102。
另外，也可以从待处理图像集中符合预设清晰度条件的多张图像中随机确定一张图像，作为目标图像。
如果待处理图像集中的图像对应的图像清晰度分值均小于图像清晰度阈值，即在待处 理图像集中未确定出符合预设清晰度条件的图像，则执行S203。
S203：在拍摄页面上显示识别失败提示信息。
本公开实施例中，如果从待处理图像集中未确定出符合预设清晰度条件的图像，则在拍摄页面上显示识别失败提示信息。例如，在拍摄页面上显示“识别失败，请重新触发识别功能”的提示信息，并以预设间隔时间闪烁；或者，在拍摄页面上跳出Toast弹窗，以提示用户识别失败。
可见，本公开实施例中客户端未确定出清晰度符合预设图像清晰度条件的目标图像时，不会向图像识别服务端发送目标图像，降低图像识别服务端的无效识别次数，同时减少客户端和图像识别服务端之间的网络资源的浪费。
在上述可选的实施方式中，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取包括连续多帧图像的待处理图像集，用于目标图像的确定，而由于待处理图像集均存储于客户端中，可能导致占用内存过多、客户端系统的运行速度下降的问题，因此，为了降低对于客户端内存造成的压力，可以在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，每次仅获取拍摄画面对应的一帧当前图像。
为此，本公开实施方式提供了另一种图像处理方法的流程图，参考图3，包括：
S301：在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取拍摄画面对应的当前图像。
本公开实施例中，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取拍摄画面对应的当前图像，拍摄画面对应的当前图像包括一帧图像，例如图像1。
S302：确定当前图像的图像清晰度是否符合预设清晰度条件，如果符合，则将当前图像确定为目标图像，并执行S102；如果不符合，则执行S303。
本公开实施例中，可以基于图像识别模型对获取的当前图像进行处理，以确定当前图像的图像清晰度是否符合预设清晰度条件。以客户端中配置有图像清晰度模型，并且设置图像清晰度分值的阈值为80分为例，符合预设清晰度条件的图像为该图像对应的图像清晰度分值大于或者等于80分。具体的，当S301中获取的一帧当前图像输入至图像清晰度模型中，基于图像清晰度模型的处理，得到该帧当前图像的图像清晰度分值，并与预设阈值(如80分)进行比较，以确定该帧当前图像的图像清晰度是否符合预设清晰度条件。
在当前图像的图像清晰度分值大于或等于图像清晰度阈值时，将该当前图像确定为目标图像，之后继续执行上述实施例中的S102；否则，确定该当前图像不符合预设清晰度条件，并执行S303。
S303：确定当前图像的获取次数是否达到预设图像获取次数，如果否，则执行S301；如果是，则执行S304。
本公开实施例中，在确定当前图像的图像清晰度不符合预设清晰度条件之后，确定当前图像的获取次数是否已经达到预设图像获取次数，即将获取到当前图像的获取次数与预设图像获取次数进行比较。其中，预设图像获取次数可以为3次、5次、7次等，本公开实施例对于预设图像获取次数不做限定。
举例说明，假设预设图像获取次数为3次，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，第一次获取拍摄画面对应的当前图像(如图像1)，基于图像清晰度模型的处理，得到图像1的图像清晰度分值小于预设阈值(如80分)，则确定图像1的图像清晰度不符合预设清晰度条件。进而，确定当前图像的获取次数(累计一次)没有达到预设图像获取次数(如3次)，则继续执行S301，即第二次获取拍摄画面对应的当前图像(如图像2)，基于图像清晰度模型的处理，得到图像2的图像清晰度分值小于预设阈值(如80分)，则确定图像2的图像清晰度不符合预设清晰度条件。进而，确定当前图像的获取次数(累计二次)没有达到预设图像获取次数(如3次)，则继续执行S301，第三次获取拍摄画面对应的当前图像(如图像3)，基于图像清晰度模型的处理，得到图像3的图像清晰度分值小于预设阈值(如80分)，则确定图像2的图像清晰度不符合预设清晰度条件。进而，确定当前图像的获取次数(累计三次)已经达到预设图像获取次数(如3次)，此时不需要再次获取拍摄画面对应的当前图像，而是执行S304，提示用户本次识别失败。
S304：在拍摄页面上显示识别失败提示信息。
本公开实施例中，在确定当前图像的获取次数已经达到预设图像获取次数，且未确定出符合预设清晰度条件的图像时，则在拍摄页面上显示识别失败提示信息。具体的提示方式如上述S203的举例，此处不再赘述。
本公开实施例提供的图像处理方法中，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取拍摄画面对应的当前图像，并确定当前图像的图像清晰度是否符合预设清晰度条件，如果符合，则当前图像确定为目标图像，如果不符合，则继续获取拍摄画面对应的当前图像，直到获取的当前图像的图像清晰度符合预设清晰度条件，或者获取当前图像的获取次数达到预设图像获取次数，进而，将目标图像发送至图像识别服务端或者拍摄页面上显示识别失败提示信息。可见，本公开实施例提供的图像处理方法在确定图像的清晰度时能够缓解内存占用过多，导致客户端系统运行速度下降的问题。
为了进一步提高图像识别服务端的识别效率，可以在将目标图像发送至图像识别服务端，进行图像识别之前，首先在客户端对目标图像进行初始识别，然后将初始识别结果与目标图像一并发送至图像识别服务端，由图像识别服务端结合目标图像和初始识别结果进行图像识别，从而提高对目标图像的识别效率。
一种可选的实施方式中，对目标图像进行初始识别的方法可以包括，首先，提取目标图像的图像特征，然后，将图像特征与预先存储的预设对象的特征参数进行匹配，如果确定匹配成功，则将匹配成功的特征参数对应的预设对象确定为该目标图像的初始识别结果。进而，将目标图像和该目标图像的初始识别结果发送至图像识别服务端，并基于初始识别结果对目标图像进行识别。
本公开实施例中，在提取到目标图像的图像特征后，用于与预先存储的预设对象的特征参数进行匹配，以对目标图像进行初始识别。其中，预设对象的特征参数可以包括预设对象与特征参数的对应关系，例如，预设对象包括“花”、“草”、“猫”等，则预设对象的特征参数可以包括“花”与“花”的特征参数的对应关系、“草”与“草”的特征参数的对 应关系、“猫”与“猫”的特征参数的对应关系等等。
本公开实施例中，如果确定目标图像的图像特征与预先存储的预设对象的特征参数匹配成功，则将匹配成功的特征参数对应的预设对象确定为该目标图像的初始识别结果。可以理解的是，预设对象对应的预先存储的特征参数越多，则针对该预设对象的初始识别结果的准确性越高。
一种可选的实施方式中，对图像进行初始识别可以基于图像识别模型实现。例如，在客户端配置图像识别模型，其中，图像识别模型是基于具有预设对象的图像样本训练得到的。
举例说明，利用客户端配置的图像识别模型对目标图像进行初始识别，经过图像识别模型的处理，提取到的目标图像的图像特征表征出该目标图像具有“花”的特征后，确定该图像特征与预先存储的“花”的特征参数匹配成功，则预设对象“花”被确定为该目标图像的初始识别结果。
本公开实施例中，确定目标图像对应的初始识别结果之后，将目标图像和该目标图像对应的初始识别结果发送至图像识别服务端，由图像识别服务端基于初始识别结果对目标图像进行识别。例如，确定目标图像对应的初始识别结果为“花”，将“花”的类型标识与目标图像一并发送至图像识别服务端，其中，图像识别服务端可以包括用于对不同对象进行识别的图像识别模型(如：“识花”模型、“识草”模型、“识猫”模型等等)。进而，基于接收到的“花”的类型标识调取图像识别服务端中的“识花”模型，对目标图像进行识别，得到最终的识别结果，例如，目标图像对应的识别结果为“向阳花”等。
本公开实施例中，在将目标图像发送至图像识别服务端进行图像识别之前，首先基于目标图像的图像特征在客户端进行初始识别，得到初始识别结果，再将该初始结果与目标图像发送至图像识别服务端。由于初始识别结果是基于目标图像的图像特征得到的，能够直接表征目标图像的特征，因此，图像识别服务端基于初始识别结果对目标图像进行识别能够提高图像识别的准确率。另外，图像识别服务端能够基于初始识别结果调取对应的识别模型，进而针对性地对目标图像进行识别，因此整体上提升了图像识别效率。
另一种可选的实施方式中，在对目标图像的初始识别过程中，如果确定目标图像的图像特征与预先存储的预设对象的特征参数匹配失败，则可以单独将目标图像发送至图像识别服务端，由图像识别服务端仅基于目标图像进行识别。
本公开实施例中，图像识别服务端还可以包括用于对与预设对象的特征参数匹配失败的对象进行识别的通用识别模型。具体的，如果确定图像特征与预先存储的预设对象的特征参数进行匹配的结果为匹配失败，则单独将目标图像发送至图像识别服务端，由图像识别服务端基于通用识别模型对目标图像进行识别，并在识别成功后，向客户端返回识别结果或者基于识别结果推荐的模板等。
在上述实施例的基础上，以客户端同时配置图像清晰度模型以及图像识别模型为例，本公开实施例还提供了一种图像处理方法，如图4所示，为本公开实施例提供的另一种图 像处理方法的流程图，该方法包括：
S401：在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取拍摄画面对应的当前图像。
S402：确定当前图像的图像清晰度是否符合预设清晰度条件，如果符合，则将当前图像确定为目标图像，并执行S405；如果不符合，则执行S403。
S403：确定当前图像的获取次数是否达到预设图像获取次数，如果否，则执行S401；如果是，则执行S404。
S404：在拍摄页面上显示识别失败提示信息。
上述S401-S404的具体过程在上述实施例S301-S304中已进行详细说明，此处不再赘述。
S405：提取目标图像的图像特征。
S406：将图像特征与预先存储的预设对象的特征参数进行匹配，并确定匹配结果是否成功，如果是，则执行S407；如果否，则执行S408。
本公开实施例中，例如，预设对象的特征参数包括“花”与“花”的特征参数的对应关系；“草”与“草”的特征参数的对应关系；等等。经过客户端中配置的图像识别模型的处理，将图像特征与预先存储的预设对象的特征参数进行匹配，如果确定图像1的图像特征与预先存储的预设对象的特征参数的匹配结果为成功，则执行S407。如果确定图像2的图像特征与预先存储的预设对象的特征参数的匹配结果为失败，则执行S408。
S407：将匹配成功的特征参数对应的预设对象确定为目标图像的初始识别结果，并将目标图像和目标图像的初始识别结果发送至图像识别服务端，基于初始识别结果对目标图像进行识别。
本公开实施例中，例如，“花”的特征参数对应的预设对象为“花”，则图像1的初始识别结果为“花”，将“花”的类型标识与图像1一并发送至图像识别服务端，基于“花”的类型标识对图像1进行识别，得到最终识别结果为“向阳花”。图像识别服务端向客户端返回“向阳花”的描述信息或者与识别结果“向阳花”相关联的推荐模板等。
S408：将目标图像发送至图像识别服务端，进行图像识别。
本公开实施例中，例如，将图像2发送至图像识别服务端，图像识别服务端基于通用识别模型对图像2进行识别后，向客户端返回识别失败的指令，并返回基于识别结果或者基于识别结果推荐的模板等。具体的，在拍摄页面上以Toast弹窗的形式显示“没有识别到匹配的结果，为您推荐通用模板，或请尝试重新识别！”，同时在拍摄页面下方展示通用模板。
本公开实施例提供的图像处理方法中，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取拍摄画面对应的当前图像，并确定当前图像的图像清晰度是否符合预设清晰度条件，如果符合，则当前图像确定为目标图像，如果不符合，则继续获取拍摄画面对应的当前图像，直到获取的当前图像的图像清晰度符合预设清晰度条件，或者获取当前图像的获取次数达到预设图像获取次数。此外，在确定目标图像之后，提取目标图像的图像特征，将图像特征与预先存储的预设对象的特征参数进行匹配，并将匹配成功的特征 参数对应的预设对象确定为目标图像的初始识别结果，进而，将目标图像和目标图像的初始识别结果发送至图像识别服务端，基于初始识别结果对目标图像进行识别。
可见，本公开实施例在进行图像识别之前，首先确定图像清晰度符合预设清晰度条件的目标图像，并能够基于目标图像的图像特征对目标图像进行初始识别，进而使得图像识别服务端能够基于初始识别结果对目标图像进行图像识别，从而提高了图像识别的准确率。
另外，由于进行识别的目标图像符合预设的清晰度条件，因此减少了出现无效输入与无效识别的情况，整体上提升了图像识别效率。另外，在提高了图像识别准确率的基础上，用户在操作图像识别的过程中减少了出现提示识别失败的次数，从而提升了用户体验。
基于上述方法实施例，本公开还提供了一种图像处理装置，参考图5，为本公开实施例提供的一种图像处理装置的结构示意图，所述装置包括：
第一确定模块501，用于在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像；
发送模块502，用于将所述目标图像发送至图像识别服务端；其中，所述图像识别服务端用于对所述目标图像进行识别。
一种可选的实施方式中，所述装置还包括：
提取模块，用于提取所述目标图像的图像特征；
匹配模块，用于将所述图像特征与预先存储的预设对象的特征参数进行匹配；
第二确定模块，用于如果确定匹配成功，则将匹配成功的特征参数对应的预设对象确定为所述目标图像的初始识别结果。
相应的，所述发送模块502，包括：
第一发送子模块，用于将所述目标图像和所述目标图像的初始识别结果发送至图像识别服务端；其中，所述图像识别服务端用于基于所述初始识别结果对所述目标图像进行识别。
一种可选的实施方式中，所述发送模块502，还包括：
第二发送子模块，用于如果确定所述图像特征与预先存储的预设对象的特征参数匹配失败，则将所述目标图像发送至所述图像识别服务端。
一种可选的实施方式中，第一确定模块501，包括：
第一获取子模块，用于在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取所述拍摄画面对应的当前图像，并确定所述当前图像的图像清晰度是否符合预设清晰度条件；
第二确定子模块，用于如果确定所述当前图像的图像清晰度符合所述预设清晰度条件，则将所述当前图像确定为目标图像，否则重新执行所述获取所述拍摄画面对应的当前图像，并确定所述当前图像的图像清晰度是否符合预设清晰度条件的步骤，直到确定当前达到预设图像获取次数。
一种可选的实施方式中，所述装置还包括：
第一提示模块，用于在确定当前达到所述预设图像获取次数，且未确定出符合所述预 设清晰度条件的图像时，在所述拍摄页面上显示识别失败提示信息。
一种可选的实施方式中，第一确定模块501，包括：
第二获取子模块，用于在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取待处理图像集；其中，所述待处理图像集中包括以所述拍摄画面对应的当前图像为结束帧的连续多帧图像；
第二确定子模块，用于从所述待处理图像集中确定图像清晰度符合预设清晰度条件的图像，作为目标图像。
一种可选的实施方式中，所述装置还包括：
第二提示模块，用于如果从所述待处理图像集中未确定出符合所述预设清晰度条件的图像，则在所述拍摄页面上显示识别失败提示信息。
本公开实施例提供的图像处理装置中，首先，在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像。然后，将目标图像发送至图像识别服务端，用于对该目标图像进行识别。可见，本公开实施例提供的图像处理装置能够在进行图像识别之前，首先确定图像清晰度符合预设清晰度条件的目标图像，并使得图像识别服务端能够基于清晰度符合条件的目标图像进行识别，从而提高了图像识别的准确率。另外，由于进行识别的目标图像符合预设的清晰度条件，因此减少了出现无效输入与无效识别的情况，因此整体上提升了图像识别效率。
除了上述方法和装置以外，本公开实施例还提供了一种计算机可读存储介质，计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备实现本公开实施例所述的图像处理方法。
本公开实施例还提供了一种计算机程序产品，所述计算机程序产品包括计算机程序/指令，所述计算机程序/指令被处理器执行时实现本公开实施例所述的图像处理方法。
另外，本公开实施例还提供了一种图像处理设备，参见图6所示，可以包括：
处理器601、存储器602、输入装置603和输出装置604。图像处理设备中的处理器601的数量可以一个或多个，图6中以一个处理器为例。在本公开的一些实施例中，处理器601、存储器602、输入装置603和输出装置604可通过总线或其它方式连接，其中，图6中以通过总线连接为例。
存储器602可用于存储软件程序以及模块，处理器601通过运行存储在存储器602的软件程序以及模块，从而执行图像处理设备的各种功能应用以及数据处理。存储器602可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序等。此外，存储器602可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。输入装置603可用于接收输入的数字或字符信息，以及产生与图像处理设备的用户设置以及功能控制有关的信号输入。
具体在本实施例中，处理器601会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器602中，并由处理器601来运行存储在存储器602中的应用程序，从而实现上述图像处理设备的各种功能。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所述的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (12)

  1. 一种图像处理方法，其特征在于，所述方法包括：
    在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像；
    将所述目标图像发送至图像识别服务端；其中，所述图像识别服务端用于对所述目标图像进行识别。
  2. 根据权利要求1所述的方法，其特征在于，所述将所述目标图像发送至图像识别服务端之前，还包括：
    提取所述目标图像的图像特征；
    将所述图像特征与预先存储的预设对象的特征参数进行匹配；
    如果确定匹配成功，则将匹配成功的特征参数对应的预设对象确定为所述目标图像的初始识别结果。
    相应的，所述将所述目标图像发送至图像识别服务端，包括：
    将所述目标图像和所述目标图像的初始识别结果发送至图像识别服务端；其中，所述图像识别服务端用于基于所述初始识别结果对所述目标图像进行识别。
  3. 根据权利要求2所述的方法，其特征在于，所述将所述目标图像发送至图像识别服务端，还包括：
    如果确定所述图像特征与预先存储的预设对象的特征参数匹配失败，则将所述目标图像发送至所述图像识别服务端。
  4. 根据权利要求1所述的方法，其特征在于，所述在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像，包括：
    在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取所述拍摄画面对应的当前图像，并确定所述当前图像的图像清晰度是否符合预设清晰度条件；
    如果确定所述当前图像的图像清晰度符合所述预设清晰度条件，则将所述当前图像确定为目标图像，否则重新执行所述获取所述拍摄画面对应的当前图像，并确定所述当前图像的图像清晰度是否符合预设清晰度条件的步骤，直到确定当前达到预设图像获取次数。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    在确定当前达到所述预设图像获取次数，且未确定出符合所述预设清晰度条件的图像时，在所述拍摄页面上显示识别失败提示信息。
  6. 根据权利要求1所述的方法，其特征在于，所述在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像，包括：
    在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，获取待处理图像集；其中，所述待处理图像集中包括以所述拍摄画面对应的当前图像为结束帧的连续多帧图像；
    从所述待处理图像集中确定图像清晰度符合预设清晰度条件的图像，作为目标图像。
  7. 根据权利要求6所述的方法，其特征在于，所述方法还包括：
    如果从所述待处理图像集中未确定出符合所述预设清晰度条件的图像，则在所述拍摄页面上显示识别失败提示信息。
  8. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    接收所述图像识别服务端发送的识别结果和/或基于所述识别结果推荐的模板。
  9. 一种图像处理装置，其特征在于，所述装置包括：
    第一确定模块，用于在接收到针对拍摄页面上的拍摄画面触发的预设识别操作时，基于所述拍摄页面上的拍摄画面，确定图像清晰度符合预设清晰度条件的目标图像；
    发送模块，用于将所述目标图像发送至图像识别服务端；其中，所述图像识别服务端用于对所述目标图像进行识别。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备实现如权利要求1-8任一项所述的方法。
  11. 一种设备，其特征在于，包括：存储器，处理器，及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时，实现如权利要求1-8任一项所述的方法。
  12. 一种计算机程序产品，其特征在于，所述计算机程序产品包括计算机程序/指令，所述计算机程序/指令被处理器执行时实现如权利要求1-8任一项所述的方法。
PCT/CN2022/098362 2021-07-12 2022-06-13 一种图像处理方法、装置、设备及存储介质 WO2023284464A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
BR112023024318A BR112023024318A2 (pt) 2021-07-12 2022-06-13 Método e aparelho de processamento de imagem e dispositivo e meio de armazenamento
EP22841104.7A EP4325439A1 (en) 2021-07-12 2022-06-13 Image processing method and apparatus, and device and storage medium
US18/511,639 US20240087309A1 (en) 2021-07-12 2023-11-16 Image processing method, apparatus, and device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110783343.X 2021-07-12
CN202110783343.XA CN113505700A (zh) 2021-07-12 2021-07-12 一种图像处理方法、装置、设备及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/511,639 Continuation US20240087309A1 (en) 2021-07-12 2023-11-16 Image processing method, apparatus, and device, and storage medium

Publications (1)

Publication Number Publication Date
WO2023284464A1 true WO2023284464A1 (zh) 2023-01-19

Family

ID=78012443

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/098362 WO2023284464A1 (zh) 2021-07-12 2022-06-13 一种图像处理方法、装置、设备及存储介质

Country Status (5)

Country Link
US (1) US20240087309A1 (zh)
EP (1) EP4325439A1 (zh)
CN (1) CN113505700A (zh)
BR (1) BR112023024318A2 (zh)
WO (1) WO2023284464A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113505700A (zh) * 2021-07-12 2021-10-15 北京字跳网络技术有限公司 一种图像处理方法、装置、设备及存储介质
CN113992851A (zh) * 2021-10-22 2022-01-28 北京字跳网络技术有限公司 一种视频生成方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496010A (zh) * 2011-12-09 2012-06-13 上海合合信息科技发展有限公司 一种结合预览图像和拍摄图像的名片识别方法
CN108399349A (zh) * 2018-03-22 2018-08-14 腾讯科技（深圳）有限公司 图像识别方法及装置
CN109145903A (zh) * 2018-08-22 2019-01-04 阿里巴巴集团控股有限公司 一种图像处理方法和装置
US20200310637A1 (en) * 2019-03-25 2020-10-01 Samsung Electronics Co., Ltd. Electronic device performing function according to gesture input and operation method thereof
CN113505700A (zh) * 2021-07-12 2021-10-15 北京字跳网络技术有限公司 一种图像处理方法、装置、设备及存储介质

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140055819A (ko) * 2012-11-01 2014-05-09 삼성전자주식회사 얼굴인식장치 및 그 제어방법
EP3352131A4 (en) * 2015-09-18 2019-05-08 Nec Corporation FINGERPRINT IMAGING SYSTEM, FINGERPRINT IMAGING APPARATUS, IMAGE PROCESSING DEVICE, FINGERPRINT IMAGING METHOD AND RECORDING MEDIUM
CN107656665A (zh) * 2016-07-25 2018-02-02 印象认知（北京）科技有限公司 基于显示屏的指纹采集控制方法、装置及电子设备
JP2019008456A (ja) * 2017-06-22 2019-01-17 キヤノン株式会社 情報処理装置、その制御方法及びプログラム
CN110858286B (zh) * 2018-08-23 2023-08-11 杭州海康威视数字技术股份有限公司 一种用于目标识别的图像处理方法及装置
CN111080493B (zh) * 2018-10-18 2023-09-05 杭州海康威视数字技术股份有限公司 一种菜品信息识别方法、装置及菜品自助结算系统
CN110020581B (zh) * 2018-12-03 2020-06-09 阿里巴巴集团控股有限公司 一种基于多帧脸部图像的比对方法、装置和电子设备
JP2020103579A (ja) * 2018-12-27 2020-07-09 キヤノン株式会社 画像処理装置、画像処理方法及びプログラム
CN110807491A (zh) * 2019-11-05 2020-02-18 上海眼控科技股份有限公司 车牌图像清晰度模型训练方法、清晰度检测方法及装置
CN111046365B (zh) * 2019-12-16 2023-05-05 腾讯科技（深圳）有限公司 人脸图像传输方法、数值转移方法、装置及电子设备
CN111104988B (zh) * 2019-12-28 2023-09-29 Oppo广东移动通信有限公司 图像识别方法及相关装置
CN112949423A (zh) * 2021-02-07 2021-06-11 深圳市优必选科技股份有限公司 物体识别方法、物体识别装置及机器人
CN112767392B (zh) * 2021-03-02 2024-04-09 百果园技术(新加坡)有限公司 图像清晰度确定方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496010A (zh) * 2011-12-09 2012-06-13 上海合合信息科技发展有限公司 一种结合预览图像和拍摄图像的名片识别方法
CN108399349A (zh) * 2018-03-22 2018-08-14 腾讯科技（深圳）有限公司 图像识别方法及装置
CN109145903A (zh) * 2018-08-22 2019-01-04 阿里巴巴集团控股有限公司 一种图像处理方法和装置
US20200310637A1 (en) * 2019-03-25 2020-10-01 Samsung Electronics Co., Ltd. Electronic device performing function according to gesture input and operation method thereof
CN113505700A (zh) * 2021-07-12 2021-10-15 北京字跳网络技术有限公司 一种图像处理方法、装置、设备及存储介质

Also Published As

Publication number Publication date
BR112023024318A2 (pt) 2024-02-06
US20240087309A1 (en) 2024-03-14
CN113505700A (zh) 2021-10-15
EP4325439A1 (en) 2024-02-21

Similar Documents

Publication Publication Date Title
WO2023284464A1 (zh) 一种图像处理方法、装置、设备及存储介质
CN111491102B (zh) 拍照场景的检测方法、系统、移动终端及存储介质
CN109495689B (zh) 一种拍摄方法、装置、电子设备及存储介质
WO2016127478A1 (zh) 一种图像处理方法、装置和终端
US8947453B2 (en) Methods and systems for mobile document acquisition and enhancement
US20170125060A1 (en) Video playing method and device
US20180077359A1 (en) Image processing method and apparatus and terminal device
WO2021169686A1 (zh) 一种拍摄控制方法、装置及计算机可读存储介质
CN108234880B (zh) 一种图像增强方法和装置
CN109151318B (zh) 一种图像处理方法、装置及计算机存储介质
CN108419009B (zh) 图像清晰度增强方法和装置
CN110705356B (zh) 功能控制方法及相关设备
EP4329283A1 (en) Image processing method and apparatus, and device and storage medium
US20200005689A1 (en) Generating three-dimensional user experience based on two-dimensional media content
WO2023093438A1 (zh) 图像显示方法、装置、电子设备及计算机可读存储介质
WO2018028253A1 (zh) 一种信息处理方法、装置及存储介质
CN109167939B (zh) 一种自动配文方法、装置及计算机存储介质
CA3102425C (en) Video processing method, device, terminal and storage medium
CN114424157A (zh) 一种视频录制方法、装置及计算机可读存储介质
CN110727810A (zh) 图像处理方法、装置、电子设备及存储介质
JP2024502117A (ja) 画像処理方法、画像生成方法、装置、機器及び媒体
WO2023065934A1 (zh) 视频生成方法、装置、设备及存储介质
US10373329B2 (en) Information processing apparatus, information processing method and storage medium for determining an image to be subjected to a character recognition processing
CN111567034A (zh) 曝光补偿的方法、装置及计算机可读存储介质
CN112087569B (zh) 一种摄像机及摄像机启动方法、装置

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: 22841104

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022841104

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2023571813

Country of ref document: JP

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112023024318

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 2022841104

Country of ref document: EP

Effective date: 20231116

ENP Entry into the national phase

Ref document number: 112023024318

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20231121

NENP Non-entry into the national phase

Ref country code: DE