Image processing method and device, computer equipment and computer readable storage medium

Abstract

The invention relates to an image processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of determining a to-be-recognized image in response to an image recognition trigger event; when the to-be-recognized image comprises a text image, a same-screen display image area and a text editing area; the to-be-recognized image is displayed in the image area; displaying an editing guide prompt for the text editing area; the editing guide prompt is used for indicating to edit a text included in the text image in the text editing area; in response to a text editing event triggered for the text editing area, displaying a text obtained by editing in the text editing area; and in response to a text editing completion event, obtaining an identification text of the to-be-identified image, the identification text including the text obtained by editing. By adopting the method, the flexibility of image recognition can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an image processing method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of computer technology, optical character recognition (OCR) technology has emerged. Optical character recognition technology is a process in which electronic devices detect characters in images, determine their shapes by detecting dark and light patterns, and then use character recognition methods to translate the shapes into computer text. Optical character recognition technology is widely used in various scenarios, such as information entry for bills and certificates, etc.

[0003] In traditional technology, after an electronic device recognizes text in an image through optical character recognition technology, the user usually needs to switch to the image display page to verify whether the text in the image and the recognized text are consistent to avoid recognition errors.

[0004] However, the text in the image may be difficult to remember, and the user needs to switch the display page of the image and the display page of the recognized text many times, which is cumbersome. Summary of the invention

[0005] Based on this, it is necessary to provide an image processing method, apparatus, computer device, computer-readable storage medium and computer program product that can flexibly compare text in an image and recognize text in order to address the above technical problems.

[0006] In a first aspect, the present application provides an image processing method. The method comprises:

[0007] In response to an image recognition triggering event, determining an image to be recognized;

[0008] When the image to be identified includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be identified;

[0009] Displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct editing the text included in the text image in the text editing area;

[0010] In response to a text editing event triggered for the text editing area, displaying the edited text in the text editing area;

[0011] In response to a text editing completion event, a recognized text of the image to be recognized is obtained, wherein the recognized text includes the text obtained by the editing.

[0012] In a second aspect, the present application also provides an image processing device. The device comprises:

[0013] An image determination module, configured to determine an image to be identified in response to an image recognition triggering event;

[0014] A same-screen display module, used for displaying an image area and a text editing area on the same screen when the image to be identified includes a text image; the image area displays the image to be identified;

[0015] A prompt module, used for displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct to edit the text included in the text image in the text editing area;

[0016] An editing module, configured to display the edited text in the text editing area in response to a text editing event triggered for the text editing area;

[0017] The text obtaining module is used to obtain the recognized text of the image to be recognized in response to a text editing completion event, wherein the recognized text includes the text obtained by the editing.

[0018] In one embodiment, the same-screen display module is also used to display an editing area trigger control when the image to be identified includes a text image and the text image recognition fails; in response to a trigger event of the editing area trigger control, the image area and the text editing area are displayed on the same screen.

[0019] In one embodiment, the same-screen display module is also used to display a text display area when the image to be identified includes a text image of a preset text category; the text display area displays text items of a preset text category, and the text items are used to display the recognized text of the text image; when the text format of the recognized text of the text image does not match the text format corresponding to the preset text category, the text item of the preset text category is marked; in response to a trigger event of recognizing text in the marked text item, the image area and the text editing area are displayed on the same screen.

[0020] In one embodiment, the same-screen display module is also used to respond to a text editing completion event, replace the recognized text in the marked text item in the text display area with the edited text and display it; when the text format of the edited text matches the text format corresponding to the preset text category, the recognized text of the image to be recognized is obtained.

[0021] In one embodiment, the same-screen display module is further used to display a picture-text comparison page when the image to be identified includes a text image; on the picture-text comparison page, an image area and a text editing area are displayed.

[0022] In one embodiment, the device further comprises a moving module; the moving module is used to move the image to be identified in the image area in response to an image movement event of the image to be identified according to the image movement direction indicated by the image movement event.

[0023] In one embodiment, the size of the text editing area is smaller than the size of the image area, and the text editing area covers a portion of the image to be recognized in the image area;

[0024] The moving module is further used to respond to an area moving event of the text editing area and move the text editing area on the image area according to the area moving direction indicated by the area moving event.

[0025] In one embodiment, the device also includes a zoom module; the zoom module is used to respond to a zoom event of the image to be identified, scale the image to be identified in the image area according to the zoom category indicated by the zoom event; and display at least a portion of the image to be identified after scaling in the image area.

[0026] In one embodiment, the zoom module is also used to, in response to a text editing event triggered for the text editing area, enlarge the image to be identified and focus on the position of the text image for display; in the text editing area, display the text obtained by editing the focused text image.

[0027] In one embodiment, the zoom module is further used to mark the text image in the image to be identified in response to a text editing event triggered for the text editing area; and to enlarge the image to be identified and focus on the position of the marked text image for display.

[0028] In one embodiment, the image determination module is also used to display an image recognition interface, display an image import control on the image recognition interface; in response to a trigger event of the image import control, display multiple candidate images in a local image set; in response to an image selection event among the multiple candidate images, display the image to be identified selected by the image selection event on the image recognition interface.

[0029] In one embodiment, the image determination module is also used to display an image recognition interface, displaying an image shooting control on the image recognition interface; in response to a triggering operation on the image shooting control, displaying a picture presented by a camera; in response to a shooting event triggered on the camera, displaying an image to be identified shot by the camera on the image recognition interface.

[0030] In one embodiment, the image determination module is further used to display a scene interaction interface of a preset interaction scene, and to display an image recognition control on the scene interaction interface; and to determine an image to be recognized in response to a triggering event of the image recognition control;

[0031] The device also includes an interaction module; the interaction module is used to display a scene interaction result obtained by performing a scene interaction operation based on the recognized text in the preset scene.

[0032] In one embodiment, the image determination module is further used to obtain an image storage path corresponding to the image to be identified in response to a triggering event of the image recognition control, and obtain the image to be identified from the image storage path;

[0033] The same-screen display module is further used to, when the image to be identified includes a text image, obtain the control display text corresponding to the preset interaction scene, and generate a text confirmation control corresponding to the control display text; determine an image area displaying the image to be identified, and determine a text editing area including the text confirmation control, and display the image area and the text editing area on the same screen;

[0034] The interaction module is also used to, when there is an associated scene interaction operation with the text confirmation control, perform the scene interaction operation based on the recognized text to obtain a scene interaction result in the preset interaction scene.

[0035] In one embodiment, the scene interaction interface of the preset interaction scene includes a session interface of a first session, and the scene interaction result represents joining a second session; the interaction module is further used to display a session description interface searched based on the recognition text; and in response to a session joining event in the session description interface, join the second session indicated by the session description interface.

[0036] In one embodiment, the scene interaction interface of the preset interaction scene includes a text entry interface of a text entry scene, and the scene interaction result includes the entry result of the recognized text; the interaction module is also used to display the recognized text of the image to be recognized on the text entry interface; and in response to a text entry event of the recognized text, prompt the entry result of the recognized text.

[0037] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0038] In response to an image recognition triggering event, determining an image to be recognized;

[0039] When the image to be identified includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be identified;

[0040] Displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct editing the text included in the text image in the text editing area;

[0041] In response to a text editing event triggered for the text editing area, displaying the edited text in the text editing area;

[0042] In response to a text editing completion event, a recognized text of the image to be recognized is obtained, wherein the recognized text includes the text obtained by the editing.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] In response to an image recognition triggering event, determining an image to be recognized;

[0045] When the image to be identified includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be identified;

[0046] Displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct editing the text included in the text image in the text editing area;

[0047] In response to a text editing event triggered for the text editing area, displaying the edited text in the text editing area;

[0048] In response to a text editing completion event, a recognized text of the image to be recognized is obtained, wherein the recognized text includes the text obtained by the editing.

[0049] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0050] In response to an image recognition triggering event, determining an image to be recognized;

[0051] When the image to be identified includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be identified;

[0052] Displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct editing the text included in the text image in the text editing area;

[0053] In response to a text editing event triggered for the text editing area, displaying the edited text in the text editing area;

[0054] In response to a text editing completion event, a recognized text of the image to be recognized is obtained, wherein the recognized text includes the text obtained by the editing.

[0055] The above-mentioned image processing method, device, computer equipment, storage medium and computer program product, in response to an image recognition triggering event, determine the image to be recognized, when the image to be recognized includes a text image, display the image area and the text editing area on the same screen, the image area displays the image to be recognized, so that the image to be recognized and the area for editing text are presented on the same screen, so that the user can edit the text by comparing the image, avoiding the inconvenience caused by the image display and text editing on different pages. Display the editing guide prompt for the text editing area, so as to instruct the user which text to edit in the text image in the text editing area through the editing guide prompt to obtain the correct text. In response to the text editing event triggered for the text editing area, the edited text is displayed in the text editing area, and in response to the text editing completion event, the recognized text of the image to be recognized is obtained, and the obtained recognized text includes the edited text, and provides an interactive method for obtaining the text in the image by combining machine recognition and manual editing, and can assist in the case of inaccurate machine recognition by manual editing, so that the text recognition of the image is more flexible and the recognized text of the image obtained is also more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A diagram showing an application environment of an image processing method in an embodiment;

[0057] Figure 2 is a schematic flow chart of an image processing method in one embodiment;

[0058] Figure 3 A schematic diagram of an interface in which an image area and a text editing area are displayed on the same screen in one embodiment;

[0059] Figure 4 This is a schematic diagram of an interface for displaying an image area and a text editing area on the same screen in another embodiment;

[0060] Figure 5 This is a schematic diagram of an interface for displaying an image area and a text editing area on the same screen in another embodiment;

[0061] Figure 6It is a schematic diagram of an interface for enlarging an image to be displayed in an image area in an embodiment;

[0062] Figure 7 A schematic diagram of an interface for displaying an image import control on an image recognition interface in an embodiment;

[0063] Figure 8 A schematic diagram of an interface for displaying image capture controls on an image recognition interface in an embodiment;

[0064] Fig. 9 A schematic diagram of a flow chart of obtaining a scene interaction result in a preset interaction scene in one embodiment;

[0065] Fig.10 is a timing diagram of an image processing method in one embodiment;

[0066] Fig.11 is a schematic diagram of the architecture of an image processing method in one embodiment;

[0067] Fig.12 A schematic diagram of an interface for searching a group number in an embodiment;

[0068] Fig.13 A schematic diagram of an interface for inputting vehicle information in an embodiment;

[0069] Fig.14 is a structural block diagram of an image processing device in one embodiment;

[0070] Fig.15 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0072] The image processing method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, can be integrated on the server 104, or can be placed on the cloud or other servers. The terminal 102 determines the image to be recognized in response to the image recognition trigger event. When the image to be recognized includes a text image, the terminal 102 displays the image area and the text editing area on the same screen; the image area displays the image to be recognized. The terminal 102 obtains and displays the editing guide prompt for the text editing area from the server 104; the editing guide prompt is used to indicate the text included in the text image to be edited in the text editing area. The terminal 102 responds to the text editing event triggered for the text editing area, and displays the edited text in the text editing area. The terminal 102 obtains the recognized text of the image to be recognized in response to the text editing completion event, and the recognized text includes the edited text. Among them, the terminal 102 can be, but is not limited to, various display devices, such as desktop computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Applications can be run on the terminal 102, and the applications can be communication applications, email applications, information flow applications, browser applications, etc. with image recognition functions. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0073] In one embodiment, Figure 2 As shown, an image processing method is provided, which is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0074] Step S202: In response to an image recognition triggering event, determining an image to be recognized.

[0075] The image to be recognized refers to an image for which text recognition is required. The image to be recognized may be a locally stored image or an image captured in real time by a camera.

[0076] The image recognition trigger event is used to trigger the image recognition operation. The image recognition trigger event can be a touch operation, a cursor operation, a key operation or a voice operation. The touch operation can be a touch click operation, a touch press operation or a touch slide operation. The touch operation can be a single-point touch operation or a multi-point touch operation. The cursor operation can be an operation of controlling the cursor to click or an operation of controlling the cursor to press. The key operation can be a virtual key operation or a physical key operation.

[0077] Specifically, the user may trigger image recognition to select an image to be recognized. The terminal determines the image to be recognized in response to the image recognition triggering event.

[0078] In this embodiment, the terminal displays an image recognition interface, and in response to an image recognition trigger event on the image recognition interface, determines an image to be recognized. Further, in response to an image recognition trigger event on the image recognition interface, displays an image to be recognized on the image recognition interface.

[0079] In this embodiment, at least one of an image import control and an image capture control is displayed on the image recognition interface. When the image recognition interface displays the image import control, the user can trigger the image import control to select an image to be recognized from the local image set. When the image recognition interface displays the image capture control, the user can trigger the image capture control to capture the image to be recognized.

[0080] Step S204, when the image to be recognized includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be recognized.

[0081] The text image refers to the text existing in the image to be recognized.

[0082] In other embodiments, the image to be recognized includes a text image which may be a text image of a preset category, such as a communication category, an identity verification category, a bill category, a book category, etc., but is not limited thereto.

[0083] Specifically, the terminal performs image recognition on the image to be recognized. When the image to be recognized includes a text image, an image area and a text editing area are displayed on the screen of the terminal at the same time. The image area is used to display the image to be recognized, and the image area can display at least a part of the image to be recognized. The text editing area is used for the user to edit and input the text included in the text image.

[0084] Both the image area and the text editing area can be displayed through independent interfaces, floating windows, pop-ups, floating layers, etc. Floating layers are a general term for content layers that float above the basic content of the page. For example, various bubbles, prompt boxes, and drop-down menus are all forms of floating layers. Pop-ups are also content layers that float above the basic content. The difference between pop-ups and floating layers is that pop-ups are usually centered and fixed display areas, and are associated with the position of the control that triggers them.

[0085] For example, two pop-up windows are displayed on the same screen, one pop-up window displays an image area, and the other pop-up window displays a text editing area.

[0086] In this embodiment, the image area can float next to the text editing area in the form of a floating window, so that the user can view the image to be recognized and compare the text included in the edited text image on the same screen.

[0087] The image area and the text editing area may also be two areas belonging to one page, that is, the image area and the text editing area are displayed in a picture-text comparison page.

[0088] In other embodiments, the text editing area can also partially cover the image area, covering a portion of the image to be identified displayed in the image area. The text editing area can also move on the image area, and the moving range of the text editing area is the range defined by the image area.

[0089] In this embodiment, when the image to be recognized includes a text image of a preset category, the image area and the text editing area are displayed on the same screen.

[0090] In this embodiment, when the image to be recognized includes a text image, the image area and the text editing area can be displayed on the same screen regardless of whether the recognition of the text image fails.

[0091] In one embodiment, when the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including: when the image to be recognized includes a text image and the text image recognition fails, the image area and the text editing area are displayed on the same screen.

[0092] In one embodiment, when the image to be recognized includes a text image, an image area and a text editing area are displayed on the same screen, including: when the image to be recognized includes a text image, and the text format of the text obtained by recognizing the text image does not match the preset text format, the image area and the text editing area are displayed on the same screen.

[0093] Step S206, displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct the text included in the text image to be edited in the text editing area.

[0094] The editing guide prompt is used to instruct to edit the text included in the text image in the text editing area. The editing guide prompt can be displayed in a pop-up window, a floating layer, etc., or in the text editing area.

[0095] Specifically, the terminal obtains an editing guide prompt for the text editing area, and displays the editing guide prompt through a pop-up window or a floating layer. Further, the text editing area is pointed to from the pop-up window or the floating layer in a visual manner.

[0096] In this embodiment, when the image to be recognized includes a text image, the image area, the text editing area and the editing guidance prompt for the text editing area are displayed on the same screen.

[0097] In this embodiment, the terminal may also display the editing guidance prompt in the text editing area.

[0098] Step S208: in response to a text editing event triggered on the text editing area, displaying the edited text in the text editing area.

[0099] The text editing event refers to the operation of a user editing text in a text editing area.

[0100] Specifically, the user can trigger a text editing event in the editing area to edit the text included in the text image in the text editing area. In response to the text editing event triggered for the text editing area, the terminal displays the text edited by the user in the text editing area.

[0101] In this embodiment, in response to a text editing event triggered for the text editing area, the display of the editing guide prompt is cancelled. Further, when the editing guide prompt is displayed in the text editing area, in response to a text editing event triggered for the text editing area, the display of the editing guide prompt is cancelled.

[0102] like Figure 3 As shown, when the image to be recognized includes a text image, an image area 302 and a text editing area 304 are displayed on the screen 300 of the terminal. The image area 302 displays the image 306 to be recognized. In addition, an editing guide prompt 308 for the text editing area 304 is also displayed on the screen 300. The editing guide prompt 308 is "Enter group number", which is used to instruct the user to enter the group number of the image 306 to be recognized in the text editing area 304.

[0103] Step S210, in response to a text editing completion event, obtaining recognized text of the image to be recognized, where the recognized text includes the text obtained by editing.

[0104] Specifically, after the user completes editing the text included in the text image in the editing area, the editing can be completed through a preset operation. The preset operation is, for example, a single click or double click on the text editing area, but is not limited thereto. In response to the text editing completion event, the terminal obtains the text edited by the user in the text editing area, and obtains the recognized text of the image to be recognized based on the text obtained through the editing.

[0105] In this embodiment, the text editing area includes a text confirmation control, and the text editing completion event includes a triggering event for the text confirmation control.

[0106] In this embodiment, the recognized text includes text obtained by editing, and may also include text obtained by image recognition of text in an image to be recognized.

[0107] When the image to be recognized includes multiple text images, optical character recognition can be performed on each text image to obtain the recognized text corresponding to the successfully recognized text image. When there is a text image that fails to be recognized, or the text format of the recognized text of the text image does not match the preset text format, the terminal can display the image area and the text editing area on the same screen, and the user edits the text included in the text image in the text editing box to obtain the recognized text corresponding to the text image, and the recognized text obtained by editing and the recognized text corresponding to the successfully recognized text image are used as the recognized text of the image to be recognized.

[0108] In one embodiment, in response to an image recognition triggering event, determining an image to be recognized includes:

[0109] In response to an image recognition triggering event, obtaining and determining an image storage path;

[0110] Get the image to be recognized from the image storage path;

[0111] When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including:

[0112] Performing image recognition on the image to be recognized, and when the image to be recognized includes a text image, determining an image area corresponding to the image to be recognized, and a text editing area corresponding to the image area;

[0113] An editing guide prompt corresponding to the image to be recognized is obtained, the image area and the text editing area are displayed on the same screen, and the editing guide prompt is displayed for the text editing area.

[0114] In the above-mentioned image processing method, in response to an image recognition triggering event, an image to be recognized is determined. When the image to be recognized includes a text image, an image area and a text editing area are displayed on the same screen, and the image area displays the image to be recognized, so that the image to be recognized and the area for editing text are presented on the same screen, so that the user can edit the text by comparing the image, avoiding the inconvenience caused by image display and text editing on different pages. An editing guide prompt is displayed for the text editing area, so as to instruct the user which text included in the text image to edit in the text editing area through the editing guide prompt to obtain the correct text. In response to a text editing event triggered for the text editing area, the edited text is displayed in the text editing area. In response to a text editing completion event, the recognized text of the image to be recognized is obtained, and the obtained recognized text includes the edited text. An interactive method is provided for obtaining the text in the image by combining machine recognition and manual editing, and can be assisted by manual editing when the machine recognition is inaccurate, so that the text recognition of the image is more flexible and the recognized text of the image obtained is also more accurate.

[0115] In one embodiment, an image recognition application with an image recognition function may be run on the terminal to enter an image recognition interface of the image recognition application. The user may trigger an image recognition event on the image recognition interface to determine an image to be recognized.

[0116] The image recognition application can be presented to the user in the form of an application, and the user can play the video through the application. The application may refer to a client installed in the terminal. The application may also refer to an installation-free application, that is, an application that can be used without downloading and installing. This type of application can also be called a mini-program, which is usually run as a subprogram in the client. The client is called the parent application, and the subprogram running in the client is called the sub-application. The application can also refer to a web application opened through a browser, etc. The image recognition application can specifically be a communication application, email application, information flow application, browser application, media playback application, etc. with image recognition function, but is not limited to this. Information flow applications include various information entry applications such as vehicle information entry, certificate information entry, ticket information entry, etc., and media playback applications include audio playback applications, video playback applications, etc.

[0117] The image recognition application can also be a cloud application, which refers to an application running in the cloud. A cloud application refers to an application that interacts between a terminal and the cloud. The operation mode of a cloud application is to use the powerful computing power of a cloud simulator to encode the operation process into an audio and video stream, and transmit it to the terminal through the network to realize interaction with the user.

[0118] In one embodiment, when the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including:

[0119] When the image to be recognized includes a text image and the text image recognition fails, the editing area trigger control is displayed; in response to a trigger event of the editing area trigger control, the image area and the text editing area are displayed on the same screen.

[0120] The text image recognition failure refers to the failure to recognize the text in the text image.

[0121] Specifically, the terminal performs image recognition on the image to be recognized, recognizes that the image to be recognized includes a text image, and the terminal fails to recognize the text image, then the editing area trigger control can be displayed. The user triggers the editing area trigger control, and the terminal responds to the trigger event of the editing area trigger control and displays the image area and the text editing area on the same screen.

[0122] In this embodiment, when the image to be recognized includes a text image and the text image recognition fails, a recognition result prompt area is displayed; the recognition result prompt area displays an editing area trigger control. Further, a prompt message indicating the failure of text image recognition is displayed in the recognition result extraction area. For example, the prompt message is "The session account is not recognized", and the prompt message may also include content prompting the user to trigger the entry into the text editing area, such as "No valid information is currently found in the image, you can try to manually enter the search session account."

[0123] In other embodiments, when the image to be recognized includes a text image, and the text format of the recognized text corresponding to the text image does not match the preset text format, an edit area trigger control is displayed.

[0124] In other embodiments, when the image to be recognized includes a text image, and the text format of the recognized text corresponding to the text image does not match the preset text format, a recognition result prompt area is displayed; the recognition result prompt area displays an editing area trigger control.

[0125] like Figure 4 As shown, the user triggers the image recognition trigger event in the image recognition interface 400 to determine the image to be recognized. When the image to be recognized includes a text image and the recognition of the text image fails, the recognition result prompt area 402 is displayed. The recognition result prompt area 402 displays an edit area trigger control 404, which is a control shown as "manual input search". The user clicks the edit area trigger control 404, and the following is displayed: Figure 3 screen.

[0126] In addition, the recognition result prompt area 402 may also display a prompt message 406 indicating recognition failure, that is, the prompt message is "Conversation account not recognized". The prompt message 406 may also include content prompting the user to trigger entry into the text editing area, such as "No valid information is currently found in the image. You can try to manually enter the search group number."

[0127] The recognition result prompt area 402 may also display a cancel control, and the user may click the cancel control to return to the image recognition interface 400 to redefine the image to be recognized.

[0128] In this embodiment, when the image to be identified includes a text image and the text image recognition fails, an editing area trigger control automatically pops up, allowing the user to trigger the control to automatically display the image area and the text editing area on the same screen, making it convenient for the user to manually enter the text in the text image.

[0129] In one embodiment, when the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including:

[0130] When the image to be recognized includes a text image of a preset text category, a text display area is displayed; the text display area displays a text item of a preset text category, and the text item is used to display the recognized text of the text image; when the text format of the recognized text of the text image does not match the preset text format corresponding to the preset text category, a text item of the preset text category marked by a text tag is displayed; in response to a trigger event of recognizing text in the marked text item, an image area and a text editing area are displayed on the same screen.

[0131] Among them, the preset text category refers to a preset configured text category, such as "name", "evidence number", "date", "ticket number", etc., but is not limited to these.

[0132] The preset text category can be specifically distinguished according to the preset interaction scenario. Different preset text categories can be set in different preset interaction scenarios. For example, in the session adding scenario, the preset text category can be the session category to which the session account belongs. Session categories include single-person session, multi-person session, and sessions of different session applications.

[0133] Specifically, the terminal performs image recognition on the image to be recognized, recognizes that the image to be recognized includes a text image, and recognizes that the included text image includes a text image of a preset text category, and then displays a text display area.

[0134] The terminal displays a text item of a preset text category in the text display area, and the text item is used to display the recognized text of the text image. Further, when the terminal recognizes at least a portion of the text included in the text image of the preset text category, the at least a portion of the text is displayed in the text item, and the at least a portion of the text is the recognized text of the text image.

[0135] The terminal can obtain a preset text format corresponding to a preset text category, and the terminal matches the text format of the recognized text of the text image with the preset text format. When the text format of the recognized text of the text image does not match the preset text format, the terminal marks the text item of the preset text category with a text tag, and displays the text item marked by the text tag in the text display area.

[0136] For example, the preset text format corresponding to "date" is "XX-XX-XX", and the recognized text of the text image is "2015-03", then the text format is "XX-XX", which means the format does not match.

[0137] The user may trigger the recognition of text in the marked text item, and in response to the triggering event of the recognition of text in the marked text item, the image area and the text editing area are displayed on the same screen.

[0138] In this embodiment, the user can trigger the text mark, or trigger the text item marked by the text mark, or trigger the recognition text displayed in the marked text item, so that the image area and the text editing area can be displayed on the same screen.

[0139] In this embodiment, regardless of whether the text included in the text image can be identified, the text display area and the text item of the preset text category can be displayed. When the text included in the text image is not identified, the text item does not display the identified text; when at least a portion of the text of the text image is identified, regardless of whether the text format of the at least a portion of the text matches the preset text format, the identified text corresponding to the identified text image can be displayed in the text item.

[0140] Further, when the text format of the at least a portion of the recognized text matches the preset text format, the text item is not marked, that is, the text mark is not displayed. If the text format of the at least a portion of the recognized text does not match the preset text format, the text item is marked to prompt the user that the recognition is inaccurate.

[0141] In other embodiments, when the image to be recognized includes a text image, a text display area is displayed; the text display area displays a text item, which is used to display the recognized text of the text image; when the text format of the recognized text of the text image does not match the preset text format, a text item marked by a text tag is displayed; in response to a trigger event of the marked text item, the image area and the text editing area are displayed on the same screen.

[0142] In other embodiments, when the image to be recognized includes a text image and the recognition of the text image fails, the text display area is displayed.

[0143] like Figure 5 As shown, the user triggers an image recognition trigger event on the image recognition interface 500 to determine the image 502 to be recognized and display it on the image recognition interface 500. After the user clicks the confirmation control, the terminal recognizes the image 502 to be recognized. When the image 502 to be recognized includes a text image 504 of a preset text category, a text display area 506 is displayed. A text item 508 of a preset text category is displayed in the text display area 506, and a recognized text 510 of the corresponding text image 504 is displayed in the text item 508.

[0144] When the recognized text 510 of the text image 504 is not accurately recognized, that is, the text format of the recognized text 510 does not match the preset text format corresponding to the preset text category, the text item 508 is marked by a text mark 512. The user clicks the text mark 512, or clicks the text item 508 marked by the text mark 512, or clicks the recognized text 510 displayed by the marked text item 508, and the image area and the text editing area can be displayed on the same screen.

[0145] In this embodiment, when the image to be recognized includes a text image of a preset text category, a text display area is displayed. Regardless of whether the text in the text image can be recognized, a text item of the preset text category is displayed in the text display area, so that the user can understand what content needs to be recognized. When at least a portion of the content of the text image is recognized, the recognized text can be displayed in the text item, so that the user can view the recognized text and the unrecognized text, and can also understand whether the recognition is accurate. When the text format of the recognized text of the text image does not match the preset text format, indicating that the recognition is inaccurate, a text item of the preset text category marked by a text mark is displayed to prompt the user that the part is inaccurately recognized through the text mark, so that the user can trigger the same-screen display of the image area and the text editing area for the inaccurately recognized part, so as to manually edit the part that the machine recognizes inaccurately in the text editing area, thereby obtaining an accurate recognition result.

[0146] In one embodiment, in response to a text editing completion event, obtaining the recognized text of the image to be recognized includes:

[0147] In response to a text editing completion event, the recognized text in the text item marked in the text display area is replaced with the edited text and displayed; when the text format of the edited text matches the preset text format, the recognized text of the image to be recognized is obtained.

[0148] Specifically, the terminal can perform manual editing in the text editing area to obtain the edited text. In response to the text editing completion event, the terminal obtains the text in the text editing area, replaces the recognized text displayed by the text item marked in the text display area with the edited text, and displays it.

[0149] The terminal determines the text format of the edited text, matches the text format with the preset text format, and obtains the recognized text of the image to be recognized when the text format of the edited text matches the preset text format. If not, the text item marked by the text mark is displayed.

[0150] In this embodiment, the recognized text in the text item is displayed in the text editing area. The user can edit the recognized text displayed in the text editing area with reference to the text image in the image to be recognized. After the editing is completed, the recognized text displayed in the text item marked in the text display area is replaced with the edited text.

[0151] In this embodiment, in response to the text editing completion event, the recognized text in the marked text item in the text display area is replaced with the edited text and displayed, so that the user can judge whether the obtained text is accurate by whether the text item is marked. When the text format of the edited text matches the preset text format, the complete recognized text of the image to be recognized can be accurately obtained from the text display area. In addition, the user can check all the recognition information again in the text display area, which helps to improve the accuracy of the obtained text.

[0152] In one embodiment, when the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including:

[0153] When the image to be recognized includes a text image, a picture-text comparison page is displayed; on the picture-text comparison page, an image area and a text editing area are displayed.

[0154] Specifically, the terminal performs image recognition on the image to be recognized, and when the image to be recognized includes a text image, a picture-text comparison page is displayed. The picture-text comparison page includes an image display area and a text editing area, and the image to be recognized is displayed in the image area.

[0155] In this embodiment, when the image to be identified includes a text image, a picture-text comparison page is displayed. On the picture-text comparison page, an image area and a text editing area are displayed, so that the image area for displaying the image and the text editing area for editing the text can be displayed on the same page. This allows the user to edit the text in the text editing area without switching pages to view the text in the image, thereby improving the flexibility of manual input.

[0156] In one embodiment, the method further comprises:

[0157] In response to an image movement event of the image to be recognized, the image to be recognized is moved in the image area according to the image movement direction indicated by the image movement event.

[0158] The image moving event refers to the moving operation on the image area, and the image moving direction refers to the direction in which the image area moves.

[0159] Specifically, the image to be identified is displayed in the image area, and the user can move the image to be identified in the image area. In response to the image movement event of the image to be identified, the terminal determines the image movement direction indicated by the image movement event, and moves the image to be identified in the image area according to the image movement direction. In response to the image movement stop event, the movement of the image to be identified is stopped, and the image to be identified after the movement stops is displayed.

[0160] In this embodiment, at least a portion of the image to be recognized is displayed in the image recognition area, and the user can move the image to be recognized in the image area to display the text image in the image to be recognized in the image recognition area.

[0161] In this embodiment, the user can move the image to be identified in the image area, so that the user can move the text image in the image to be identified to a position that is easy to observe, so as to perform manual editing in the text editing area by comparing the text image.

[0162] In one embodiment, the size of the text editing area is smaller than the size of the image area, and the text editing area covers a portion of the image to be recognized in the image area;

[0163] In response to an image movement event of the image to be recognized, moving the image to be recognized in the image area according to the image movement direction indicated by the image movement event, comprising:

[0164] In response to an area moving event for the text editing area, the text editing area is moved on the image area according to the area moving direction indicated by the area moving event.

[0165] The area moving event refers to the moving operation on the text editing area. The area moving direction refers to the direction in which the text editing area moves.

[0166] Specifically, the size of the text editing area is smaller than the size of the image area, and the text editing area can partially cover the image area, covering a portion of the image to be recognized displayed in the image area. The text editing area can also move on the image area, and the moving range of the text editing area is the range defined by the image area.

[0167] The user can move the text editing area on the image area. In response to an area moving event for the text editing area, the terminal determines the area moving direction indicated by the area moving event and moves the text editing area on the image area according to the area moving direction.

[0168] In this embodiment, in response to an image movement event of the image to be recognized, the image to be recognized is moved in the image area according to the image movement direction indicated by the image movement event. That is, the image to be recognized displayed in the image area can be moved, and the text editing area covered on the image area can also be moved. The user can adjust the position of the image or text editing area as needed to facilitate manual editing.

[0169] In this embodiment, the size of the text editing area is smaller than that of the image area, and the text editing area covers a portion of the image to be identified in the image area, so that the text editing area can be moved within the range limited by the image area, so that the text editing area and the image to be identified can be displayed on the same screen no matter how they are moved, so that the user can move the image or text editing area as needed, so as to perform manual editing in the text editing area by comparing the image.

[0170] In one embodiment, the method further comprises:

[0171] In response to a zoom event on the image to be recognized, the image to be recognized is zoomed in the image area according to the zoom category indicated by the zoom event; and at least a portion of the zoomed image to be recognized is displayed in the image area.

[0172] The zoom event refers to a size adjustment event for the image to be identified, including a size increase event or a size reduction event for the image to be identified. The zoom category is size increase or size reduction.

[0173] Specifically, the user can scale the image to be identified in the image area to adjust the size of the image to be identified. In response to the scaling event of the image to be identified, the terminal determines the scaling category indicated by the scaling event, scales the image to be identified in the image area according to the scaling category, obtains the scaled image to be identified, and displays at least a portion of the scaled image to be identified in the image area.

[0174] In this embodiment, the range defined by the image area remains unchanged. When the size of the image to be identified increases, the image area may not be able to display the entire image, so a portion of the image to be identified after enlargement is displayed. The user can move the enlarged image to be identified so that the text image is displayed, so that the user can edit the text included in the text image in the text editing area.

[0175] In this embodiment, the image to be identified displayed in the image area can be enlarged or reduced by the user, so that the user can adjust the image to be identified to a suitable size, so as to perform manual editing in the text editing area by comparing the image.

[0176] like Figure 6 As shown, an image area 602 and a text editing area 604 are displayed in the same screen 600 , an image 606 to be identified is displayed in the image area 602 , and a user zooms in on the image 606 to be identified so that a portion of the zoomed image 606 to be identified is displayed in the image area 602 .

[0177] In one embodiment, in response to a text editing event triggered for a text editing area, displaying the edited text in the text editing area includes:

[0178] In response to a text editing event triggered on a text editing area, the image to be recognized is enlarged and focused on the position of the text image for display; in the text editing area, the text edited on the focused text image is displayed.

[0179] Specifically, the user triggers the text editing area to edit the text, and the terminal responds to the text editing event triggered for the text editing area, determines the text image in the image to be identified, and enlarges the image to be identified and focuses on the position of the text image for display, so as to ensure that the text image can still be displayed in the image area after the image is enlarged. The user edits the text image displayed after enlargement in the text editing area, and the terminal responds to the text editing event and displays the text obtained by the user editing the text image in real time in the text editing area.

[0180] For example, when a user clicks on a text editing area, the image to be identified displayed in the image area is automatically enlarged, and the focus is placed on the position of the text image in the enlarged image to be identified, so that the enlarged text image is fully displayed in the image area for easy viewing by the user.

[0181] In this embodiment, in response to a text editing event triggered for a text editing area, the image to be identified is enlarged and automatically focused to the position of the text image for display, so that the position in the image where the text needs to be obtained through manual editing can be automatically located, which is convenient for users to view. In addition, enlarging the image to be identified also enlarges the text image, so that users can more clearly identify the text included in the text image, which is convenient for users to manually edit the text included in the text image in the text editing area.

[0182] In one embodiment, in response to a text editing event triggered for a text editing area, the image to be recognized is enlarged and focused to the position of the text image for display, including:

[0183] In response to a text editing event triggered for a text editing area, an image to be identified marked by an image tag on a text image is displayed; the image to be identified is enlarged and focused on the position of the text image marked by the image tag for display.

[0184] The image marker is a marker for marking a text image in the image to be recognized, such as a rectangular frame, a rectangular frame of different colors, a highlight mark, etc.

[0185] Specifically, the user triggers the text editing area to edit the text, and the terminal responds to the text editing event triggered for the text editing area, marks the text image in the image to be recognized by the image mark, and displays the marked image to be recognized in the image area. In addition, the terminal automatically enlarges the size of the image to be recognized, and focuses on the position of the text image marked by the image mark to ensure that the text image can still be displayed in the image area after the image is enlarged.

[0186] In this embodiment, in response to a text editing event triggered for a text editing area, the text image in the image to be identified can be automatically marked and displayed through the image mark, so that the user can be prompted which text in the image needs to be manually edited through the mark in the image. The image to be identified is enlarged and focused on the position of the text image marked by the image mark for display, so that the text included in the text image is clearer, avoiding editing errors caused by the text font being too small for the user to browse clearly, which is conducive to improving the accuracy of manual editing.

[0187] In one embodiment, in response to an image recognition triggering event, determining an image to be recognized includes:

[0188] An image recognition interface is displayed, and an image import control is displayed on the image recognition interface; in response to a trigger event of the image import control, multiple candidate images in a local image set are displayed; in response to an image selection event among the multiple candidate images, an image to be recognized selected by the image selection event is displayed on the image recognition interface.

[0189] Among them, the image import control can provide the function of jumping from the image recognition interface to the local image set.

[0190] Specifically, the terminal displays an image recognition interface, and displays an image import control on the image recognition interface. The user can trigger the image import control. In response to the triggering event of the image import control, the terminal jumps from the image recognition interface to the local image set and displays multiple candidate images in the local image set.

[0191] The user may select one from a plurality of candidate images in the local image collection, and in response to an image selection event in the plurality of candidate images, the candidate image selected by the image selection event is used as the image to be recognized.

[0192] Furthermore, in response to an image selection event among the plurality of candidate images, the terminal imports the candidate image selected by the image selection event into the image recognition interface and displays it on the image recognition interface.

[0193] In this embodiment, an image import control is displayed on the image recognition interface to provide an image import function on the image recognition interface, so that the user can independently select an image to be recognized from the local. In response to a trigger event of the image import control, multiple candidate images in the local image set are displayed, and in response to an image selection event from the multiple candidate images, the image to be recognized selected by the image selection event is displayed on the image recognition interface, so that the user can select an image for recognition from the local existing images.

[0194] In one embodiment, in response to an image recognition triggering event, determining an image to be recognized includes:

[0195] An image recognition interface is displayed, and an image shooting control is displayed on the image recognition interface; in response to a triggering operation on the image shooting control, a picture presented by the camera is displayed; in response to a shooting event triggered on the camera, an image to be identified shot by the camera is displayed on the image recognition interface.

[0196] Among them, the image shooting control can provide the function of calling the terminal's camera to shoot.

[0197] Specifically, the terminal displays an image capture control on the image recognition interface, and the user can trigger the image capture control. In response to the triggering operation of the image capture control, the terminal calls the camera and displays the picture presented by the camera. Further, the terminal can display the picture presented by the camera on the image recognition interface.

[0198] In this embodiment, the user can trigger the image shooting control, and the terminal responds to the triggering operation of the image shooting control by calling the terminal's own camera, or calling the camera authorized for use by the terminal, and displays the picture presented by the camera.

[0199] The user can use the camera to shoot a scene with text. In response to the shooting event triggered by the camera, the terminal imports the image to be identified obtained by the camera into the image recognition interface for display on the image recognition interface.

[0200] When it is necessary to take multiple images to be identified, the image recognition interface can be imported after the shooting is completed, and the image shooting control can be re-triggered to shoot again, so that the multiple images to be identified that are taken can be displayed on the image recognition interface.

[0201] In this embodiment, the terminal may shoot an existing image through a camera to obtain an image to be recognized, and import the shot image to be recognized into an image recognition interface.

[0202] In this embodiment, an image shooting control is displayed on the image recognition interface to provide a real-time shooting function on the image recognition interface. In response to the triggering operation of the image shooting control, the picture presented by the camera is displayed, and in response to the shooting event triggered by the camera, the image to be identified shot by the camera is displayed on the image recognition interface, so that the user can obtain the image to be identified by shooting in real time with the camera, and multiple ways of obtaining images can be provided for the user.

[0203] like Figure 7 As shown, an image recognition interface 700 is displayed, and an image import control 702 and an image shooting control 704 are displayed on the image recognition interface 700. The image import control 702 is displayed as "Upload photo", and the image shooting control 704 is displayed as "Click to shoot".

[0204] The user clicks the image import control 702 to jump to the local image set 706 , and after selecting an image 708 to be identified in the local image set 706 , the image 708 to be identified is displayed on the image recognition interface 700 .

[0205] like Figure 8 As shown, the user clicks the image capture control 704 to call the camera and display a picture 710 presented by the camera. The user captures the picture 710 through the camera to form an image 712 to be recognized. The image 712 to be recognized is displayed in the image recognition interface 700.

[0206] In addition, a "retake" control and a "confirm photo" control may also be displayed in the image recognition interface 700. Clicking the "retake" control allows retaking the photo. After clicking the "confirm photo" control, the image 712 to be recognized is displayed in the image recognition interface 700.

[0207] In one embodiment, in response to an image recognition triggering event, determining an image to be recognized includes:

[0208] Displaying a scene interaction interface of a preset interaction scene, and displaying an image recognition control on the scene interaction interface; and determining an image to be recognized in response to a triggering event of the image recognition control;

[0209] The method also includes: in a preset interaction scene, displaying a scene interaction result obtained by performing a scene interaction operation based on the recognized text.

[0210] Among them, the preset interaction scenarios include, but are not limited to, conversation scenarios, item search scenarios, text entry scenarios, etc. Conversation scenarios include, but are not limited to, conversation search scenarios, conversation addition scenarios, etc. Item search scenarios include, for example, book placement search scenarios, commodity placement search scenarios, commodity sales information search scenarios, etc. Text entry scenarios include, for example, bill information entry, certificate information entry, etc.

[0211] A scenario interaction operation refers to an interaction operation performed using the recognized text in a preset interaction scenario. The scenario interaction operations performed in different preset interaction scenarios are different. For example, in a conversation search scenario, a search operation is performed based on the recognized text; in a certificate information entry scenario, an entry operation is performed based on the recognized text.

[0212] Specifically, the terminal displays a scene interaction interface of a preset interaction scene, and displays an image recognition control on the scene interaction interface. The user can trigger the image recognition control, and the terminal responds to the triggering event of the image recognition control, determines the image to be recognized from the local image set or starts the camera to capture the image to be recognized.

[0213] When the image to be recognized includes a text image, the terminal displays an image area and a text editing area on the same screen; the image area displays the image to be recognized. In addition, an editing guide prompt for the text editing area is displayed, and the editing guide prompt is used to instruct to edit the text included in the text image in the text editing area. In response to a text editing event triggered for the text editing area, the edited text is displayed in the text editing area.

[0214] After obtaining the recognition text of the image to be recognized, the terminal performs a scene interaction operation in the preset interaction scene based on the recognition text, obtains a scene interaction result, and displays the scene interaction result.

[0215] In this embodiment, the image processing method is applied in a preset interaction scene to perform image recognition in the preset interaction scene. The scene interaction interface of the preset interaction scene can be used as an image recognition interface, and the image recognition control may include at least one of an image import control or an image shooting control.

[0216] In this embodiment, a scene interaction interface of a preset interaction scene is displayed, an image recognition control is displayed in the scene interaction interface, and an image recognition function can be called in the preset interaction scene, so that the image to be recognized and the text editing area can be displayed on the same screen in each interaction scene, so that image recognition can be applied to each interaction scene. After obtaining the recognized text through machine recognition and manual editing, in the preset interaction scene, the recognized text obtained by image recognition is subjected to the corresponding scene interaction operation in the preset interaction scene to obtain the interaction result in the corresponding scene, so that more interaction scenes can be adapted.

[0217] In one embodiment, Fig. 9 As shown, the text editing completion event includes a trigger event for a text confirmation control; in response to the trigger event for an image recognition control, determining an image to be recognized includes:

[0218] Step S902, in response to a triggering event of the image recognition control, obtaining an image storage path corresponding to the image to be recognized, and obtaining the image to be recognized from the image storage path.

[0219] Specifically, the terminal displays a scene interaction interface of a preset interaction scene, and displays an image recognition control on the scene interaction interface. The terminal obtains an image storage path corresponding to the image to be recognized in response to a trigger event of the image recognition control. The terminal obtains the image to be recognized from the image storage path. The image storage path may be a local image set, a storage path of an image stored on another device, or a uniform resource locator (URL) of the image.

[0220] In this embodiment, in response to a trigger event of the image recognition control, an image to be recognized captured by a camera is acquired.

[0221] When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including:

[0222] Step S904: when the image to be recognized includes a text image, a control display text corresponding to a preset interactive scenario is obtained, and a text confirmation control corresponding to the control display text is generated.

[0223] Step S906, determining an image area for displaying the image to be recognized, and determining a text editing area including a text confirmation control, and displaying the image area and the text editing area on the same screen.

[0224] The control display text refers to the display text of the text confirmation control included in the text editing area. For example, if the control display text is "Search", the text confirmation control included in the text editing area will display "Search"; if the control display text is "Confirm", the text confirmation control will display "Confirm".

[0225] Specifically, the terminal identifies the image to be identified. When the image to be identified includes a text image, the terminal can obtain the corresponding control display text in the preset interaction scenario, determine the text confirmation control corresponding to the control display text, and thus generate a text editing area.

[0226] In this embodiment, an editing guide prompt in a preset interaction scenario is obtained, and a text editing area is generated according to the control display text, the text confirmation control corresponding to the control display text, and the editing guide prompt.

[0227] The terminal determines an image area for displaying the image to be recognized, and displays the image area and the text editing area on the same screen.

[0228] In the preset interaction scene, the scene interaction results obtained by performing scene interaction operations based on the recognized text are displayed, including:

[0229] Step S908, when the text confirmation control has an associated scene interaction operation, the scene interaction operation is performed based on the recognized text to obtain a scene interaction result in a preset interaction scene.

[0230] Specifically, after obtaining the recognized text of the image to be recognized, the terminal detects whether the text confirmation control has an associated scene interaction operation. If so, the scene interaction operation is performed based on the recognized text to obtain the scene interaction result under the preset interaction scene.

[0231] In this embodiment, in response to a trigger event of an image recognition control, an image storage path corresponding to the image to be recognized is obtained to obtain the image to be recognized from the image storage path. When the image to be recognized includes a text image, the control display text corresponding to the preset interaction scene is obtained to generate a text confirmation control corresponding to the control display text, thereby customizing the text editing area in the preset interaction scene. Determine the image area for displaying the image to be recognized, and determine the text editing area including the text confirmation control, and display the image area and the text editing area on the same screen to facilitate the user to enter the corresponding text in the text editing area in accordance with the image to be recognized. When there is an associated scene interaction operation with the text confirmation control, the scene interaction operation is performed based on the recognized text, and the scene interaction result in the preset interaction scene is obtained, so that image recognition can be applied to more interaction scenes, so as to solve the inaccurate image recognition in each interaction scene through machine recognition and manual editing, and the situation where frequent page switching is required when manually inputting text.

[0232] In one embodiment, the image processing method can be formed into an independent component and integrated into a client with OCR recognition. After an OCR recognition error occurs, the component can be called to help users perform efficient information correction and information input. Fig.10 As shown, a timing diagram of an image processing method is provided, including:

[0233] (1) Startup steps

[0234] Prepare parameters: prepare the image URL or local path of the image; prepare the control display copy; encapsulate the customized behavior of the text confirmation control according to the interface defined by the component. The interface refers to the standardized way of data transmission and mutual calling between different components in the software system, such as the startup interface in this component. The image URL is an identifier used to identify and locate resource images on the Internet.

[0235] Startup interface: The component will provide a startup interface to the caller, and the caller will pass in the corresponding parameters based on the interface.

[0236] (2) Internal processing flow of this component

[0237] Interface display: According to the preset interaction scenario corresponding to the image to be recognized, customize the editing prompt information, control display text and keyboard in the preset interaction scenario.

[0238] The user adjusts the position of the image to be recognized in the image area.

[0239] The user edits text in the text editing area and obtains the edited text.

[0240] After the user confirms, the edited text is returned and the scene interaction operation is started.

[0241] (3) The calling client receives the returned edited text and forms recognition text corresponding to the image to be recognized based on the edited text.

[0242] (4) There is a scene interaction operation, based on which the text obtained by editing forms a recognition text corresponding to the image to be recognized, and the scene interaction operation is performed based on the recognition text.

[0243] like Fig.11 As shown in the figure, the main functional units in the architecture of the image processing method in this embodiment include an editing unit, a picture processing unit, an information processing unit and a scene interaction operation processing unit. Among them, the editing unit includes the processing of the following contents:

[0244] It is mainly based on the system keyboard, and cooperates with the image processing unit to form the overall picture of the entire component. The text displayed by the control in the keyboard can be customized by passing in external parameters, such as: the scene interaction operation is "search", "confirm", etc.

[0245] The scene interaction operation of the text confirmation control can be customized by defining a set of software interfaces. That is, the caller implements this set of interfaces and passes parameters to its specific implementation to customize the scene interaction operation associated with the text confirmation control.

[0246] Image processing unit: used to display the image to be identified, providing dragging and zooming functions, so that users can place the required information in the most convenient location for viewing.

[0247] Source of the image to be identified: The calling client passes in the local path or network URL of the image through the startup interface; when there is no image information, a photo taking function is provided to obtain the image to be identified.

[0248] Information processing unit, including:

[0249] Information input: The caller can pass in the image source, the keyboard text display copy, and the scene interaction operation associated with the text confirmation control.

[0250] Text output: After clicking OK, the text edited by the user will be returned to the calling client through the return interface; when scene interaction operations are customized, scene interaction operations will also be performed based on the edited text.

[0251] Scene interaction operation processing unit:

[0252] In the case of customized scene interaction operations, after the user clicks OK, the scene interaction operation is performed based on the recognized text, such as the search interface, the information entry interface, etc.

[0253] In the absence of customized scene interaction operations, when the user clicks the text confirmation control, the text edited by the user will be returned to the calling client through the return interface, and the operation of this component will be closed.

[0254] Among them, interface encapsulation is used for information input and output, and behavior customization requires the caller to pass it in as parameters.

[0255] The startup interface is used by the caller to start the component and specifies the parameter form as the information input of the component.

[0256] Asynchronous callback means that the text edited by the user is returned in the form of asynchronous callback.

[0257] Behavior interface means that the customization of scene interaction operations must be encapsulated based on the behavior interface.

[0258] In one embodiment, the scene interaction interface of the preset interaction scene includes a session interface of the first session, and the scene interaction result represents joining the second session; in the preset scene, the scene interaction result obtained by performing the scene interaction operation based on the recognized text is displayed, including:

[0259] The session description interface searched based on the recognition text is displayed; and in response to a session joining event on the session description interface, a second session indicated by the session description interface is joined.

[0260] The identification text is a session identifier, and the session identifier may include at least one of the following: a session name, a session jump link, or a session account.

[0261] In this embodiment, the image to be identified may also be an image displayed on the conversation interface of the first conversation.

[0262] Specifically, the terminal displays the session interface of the first session, and displays the image recognition control on the session interface. In response to the triggering event of the image recognition control, the terminal determines the image to be recognized. When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen; the image area displays the image to be recognized. An editing guide prompt for the text editing area is displayed; the editing guide prompt is used to indicate the text included in the text image to be edited in the text editing area. In response to the text editing event triggered for the text editing area, the edited text is displayed in the text editing area. In response to the text editing completion event, the recognized text of the image to be recognized is obtained, and the recognized text includes the edited text. The recognized text includes a session identifier.

[0263] The terminal searches for a session based on the session identifier and obtains a session description interface corresponding to the session identifier. The terminal displays the session description interface, and the user can trigger a session join event on the session description interface. In response to the session join event on the session description interface, the terminal adds the user identifier to the second session indicated by the session description interface.

[0264] In this embodiment, the session description interface includes a session adding control, and the user triggers the session adding control to join the second session indicated by the session description interface.

[0265] In this embodiment, the image processing method can be applied to a conversation scenario. The user can trigger the image recognition function in the conversation interface to accurately obtain the conversation identifier in the image to be recognized through machine recognition and manual editing based on the same-screen display of the image to be recognized and the text editing area, and automatically search for the second conversation indicated by the conversation identifier to join the second conversation, so that the user does not need to remember the conversation identifier when searching for a conversation, nor does he need to frequently switch between the interface for displaying the image and the input interface for the conversation identifier, thereby improving the accuracy and speed of conversation search.

[0266] In one embodiment, the image recognition trigger event includes a session adding trigger event, and the image to be recognized includes a session description image to be recognized; in response to the image recognition trigger event, determining the image to be recognized includes: displaying a session interface of the first session, and displaying a session adding control on the session interface; in response to the session adding trigger event of the session adding control, determining the session description image to be recognized;

[0267] The method further includes: displaying a session description interface searched based on the recognition text; and joining a second session indicated by the session description interface in response to a session adding event on the session description interface.

[0268] In one embodiment, the image processing method can be applied to any scenario using OCR technology and information entry scenario. Moreover, the image processing method can be applied to image processing in any field, such as finance, industry, government affairs, e-commerce, the Internet, and other fields.

[0269] In one embodiment, Fig.12 As shown, an application scenario of an image processing method is provided, which is applied in a conversation scenario, including:

[0270] The user clicks the "Scan to add friends" control in the session interface of the first session to enter the image recognition interface, clicks "Album" in the image recognition interface to enter the local image collection, and selects the image to be recognized in the local image collection.

[0271] After selection, the terminal automatically recognizes the image. When the group number is not recognized in the image, a prompt area is displayed. The recognition result prompt area displays an edit area trigger control, namely, a "manual input search" control. The recognition result prompt area also displays a prompt message indicating recognition failure, namely, "No session account was recognized", and also includes content prompting the user to trigger the text editing area, namely, "No valid information was found in the image at present, you can try to manually enter the search group number."

[0272] When the user clicks the "manual input search" control, the image area and the text editing area are displayed on the same screen. The image to be identified is displayed in the image area, and an editing guide prompt, namely "enter the group number", is displayed in the text editing area.

[0273] The user can enlarge and move the image to be identified in the image area to adjust it to a suitable size and position, and then enter the group number in the image to be identified in the text editing area. After the input is completed, the user clicks the "Confirm" control, and the terminal performs a search for the group number, thereby displaying the session description interface corresponding to the group number. The "Apply to Join Group" control is displayed on the session description interface. The user clicks the control to apply to join the group, that is, to apply to join the second session. The group number is the session identifier of the second session.

[0274] In this embodiment, the image processing method is applied to the group number search scenario, so that the user can call the image recognition function through the conversation application during the conversation. When OCR recognition fails, the image to be recognized and the text editing area are displayed on the same screen, which is convenient for the user to view the image to be recognized on the same screen, and edit the text in the text editing area according to the text included in the edited text image, so that the group number in the image can be searched quickly and accurately and the group can be added.

[0275] In one embodiment, the scene interaction interface of the preset interaction scene includes a text entry interface of a text entry scene, and the scene interaction result includes an entry result of the recognized text; in the preset scene, the scene interaction result obtained by performing the scene interaction operation based on the recognized text is displayed, including:

[0276] In the text input interface, the recognized text of the image to be recognized is displayed; in response to the text input event of the recognized text, the input result of the recognized text is prompted.

[0277] Specifically, the terminal displays a text entry interface, and displays an image recognition control on the text entry interface. The text entry interface may be an entry interface for bill information, an entry interface for certificate information, and the like.

[0278] The terminal determines the image to be recognized in response to a triggering event of an image recognition control. When the image to be recognized includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be recognized. An editing guide prompt for the text editing area is displayed; the editing guide prompt is used to instruct the text included in the text image to be edited in the text editing area. In response to a text editing event triggered for the text editing area, the edited text is displayed in the text editing area. In response to a text editing completion event, the recognized text of the image to be recognized is obtained, and the recognized text includes the edited text.

[0279] The terminal displays the recognized text of the image to be recognized on the text entry interface. The user can check the recognized text again. If it is correct, the text entry event can be triggered. In response to the text entry event for the recognized text, the terminal enters the recognized text and prompts the entry result of the recognized text. The entry result indicates whether the recognized text entry is successful or failed.

[0280] In this embodiment, the image processing method can be applied to text entry scenarios. The user can trigger the image recognition function in the text entry interface to accurately obtain the recognized text in the image to be recognized through machine recognition and manual editing based on the same-screen display of the image to be recognized and the text editing area, and automatically enter the recognized text of the image to be recognized. This allows the user to enter text without having to memorize the text in the image or frequently switch between the interface for displaying the image and the text entry interface, thereby improving the accuracy and speed of text entry.

[0281] In one embodiment, the image recognition trigger event includes a text entry trigger event; in response to the image recognition trigger event, determining the image to be recognized includes: displaying a text entry interface, displaying an entry control on the text entry interface; in response to the text entry trigger event on the entry control, determining the image to be recognized;

[0282] The method further includes: in response to a text confirmation event for the recognized text, entering the recognized text.

[0283] In one embodiment, Fig.13 As shown, an application scenario of an image processing method is provided, which is applied to the vehicle information input scenario, including:

[0284] The user can run the vehicle information entry application to enter the vehicle information entry interface.

[0285] The user clicks the image capture control on the vehicle information entry interface to directly call the terminal's camera on the entry interface, and uses the camera to capture the motor vehicle driver's license to obtain the image to be recognized. The image to be recognized is displayed on the entry interface. The user clicks the "Confirm" control on the entry interface, and the terminal recognizes the image to be recognized and displays each text recognized from the image to be recognized in the text display area.

[0286] If the terminal does not accurately identify the vehicle identification code in the image to be identified, and the identified text is "1234", the text item of the vehicle identification code is marked with an asterisk in the text display area, and a prompt is given that the length of the vehicle identification code is not less than 16 digits. When the user clicks the text "1234", the image area and the text editing area can be displayed on the same screen, the image to be identified is displayed in the image area, and the editing guide prompt, i.e. "Enter the vehicle identification number (VIN)", is displayed in the text editing area.

[0287] The user can enlarge and move the image to be identified in the image area to adjust it to a suitable size and position, and then enter the vehicle identification code, i.e. "1234567", in the text editing area. After the input is completed, the user clicks the "Confirm" control to return to the text display area, and the vehicle identification code entered by the user is displayed in the text display area. The user clicks the "Confirm Upload" control on the vehicle identification code to upload the vehicle information such as the owner, registration date, vehicle identification code, license plate number, etc. in the text display area to the vehicle information entry system. After the upload is successful, the terminal displays a prompt message indicating that the upload is successful.

[0288] In this embodiment, the image processing method is applied to the vehicle information entry scenario, and the vehicle information can be quickly and accurately entered into the system. The image processing method combines OCR and manual editing, using manual editing as an auxiliary means of automatic recognition, and can display the image to be recognized and the text editing area on the same screen when OCR recognition fails or is inaccurate, so that the vehicle information can be manually entered in the text editing area by comparing the image to be recognized, thereby accurately and delicately improving the accuracy of vehicle information entry and effectively improving the efficiency of vehicle information entry.

[0289] In one embodiment, the scene interaction interface of the preset interaction scene includes an item search interface of the item search scene; in the preset scene, the scene interaction results obtained by performing scene interaction operations based on the recognized text are displayed, including: in the item search interface, the location information of the items searched based on the recognized text is displayed.

[0290] In one embodiment, the image recognition trigger event includes an item search trigger event; in response to the image recognition trigger event, determining the image to be recognized includes: displaying an item search interface, displaying a search control on the item search interface; in response to the item search trigger event on the search control, determining the item image to be recognized;

[0291] The method further includes: displaying, on the object search interface, location information of the object searched based on the recognition text of the image of the object to be recognized.

[0292] In one embodiment, an image processing method is provided, which is applied to a terminal and includes:

[0293] Display a scene interaction interface for a preset interaction scene, and display an image import control on the scene interaction interface; in response to a trigger event of the image import control, display multiple candidate images in a local image set; in response to an image selection event among the multiple candidate images, display an image to be identified selected by the image selection event on the scene interaction interface.

[0294] Optionally, an image shooting control is displayed on the scene interaction interface; in response to a triggering operation on the image shooting control, a picture presented by the camera is displayed; in response to a shooting event triggered on the camera, an image to be identified shot by the camera is displayed on the scene interaction interface.

[0295] When the image to be identified includes a text image and the text image recognition fails, the editing area trigger control is displayed; in response to the trigger event of the editing area trigger control, the image area and the text editing area are displayed on the same screen; the image area displays the image to be identified.

[0296] Optionally, when the image to be recognized includes a text image of a preset text category, and the text format of the recognized text of the text image does not match the preset text format corresponding to the preset text category, a text display area is displayed; the text display area displays text items of the preset text category, and the text items are used to display the recognized text of the text image; in the text display area, text items of the preset text category marked by text tags are displayed; in response to a trigger event of recognizing text in the marked text items, the image area and the text editing area are displayed on the same screen.

[0297] Next, an editing guide prompt for the text editing area is displayed; the editing guide prompt is used to instruct the user to edit the text included in the text image in the text editing area.

[0298] Next, in response to a zoom event on the image to be identified, the image to be identified is zoomed in the image area according to the zoom category indicated by the zoom event; and at least a portion of the zoomed image to be identified is displayed in the image area.

[0299] Further, in response to an image movement event of the image to be recognized, the image to be recognized is moved in the image region according to the image movement direction indicated by the image movement event, so as to move the text image into the image region for display.

[0300] In response to a text editing event triggered for a text editing area, the edited text is displayed in the text editing area; in response to a text editing completion event, the recognized text of the image to be recognized is obtained, and the recognized text includes the edited text.

[0301] In a preset interaction scenario, the scene interaction results obtained by performing scene interaction operations based on the recognized text are displayed.

[0302] In this embodiment, a scene interaction interface of a preset interactive scene is displayed, and an image import control and an image shooting control are displayed on the scene interaction interface to provide an image import function on the image recognition interface, so that the user can independently select the image to be identified from multiple candidate images in the local image set, or can obtain the image to be identified by shooting in real time.

[0303] When the image to be recognized includes a text image, and the text image recognition fails or is inaccurate, the image to be recognized and the text editing area are displayed on the same screen, so that the user can obtain accurate text by manually editing in the text editing area in comparison with the image to be recognized. After obtaining the recognized text through machine recognition and manual editing, in the preset interactive scene, the recognized text obtained by image recognition is subjected to the corresponding scene interactive operation in the preset interactive scene to obtain the interactive result in the corresponding scene, so that more interactive scenes can be adapted.

[0304] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0305] Based on the same inventive concept, the embodiment of the present application also provides an image processing device for implementing the above-mentioned image processing method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more image processing device embodiments provided below can refer to the limitations on the image processing method above, and will not be repeated here.

[0306] In one embodiment, Fig.14 As shown, an image processing device 1400 is provided, comprising: an image determination module 1402, a same-screen display module 1404, a prompt module 1406, an editing module 1408 and a text obtaining module 1410, wherein:

[0307] The image determination module 1402 is configured to determine an image to be recognized in response to an image recognition triggering event.

[0308] The same-screen display module 1404 is used to display the image area and the text editing area on the same screen when the image to be recognized includes a text image; the image area displays the image to be recognized.

[0309] The prompt module 1406 is used to display an editing guide prompt for the text editing area; the editing guide prompt is used to instruct to edit the text included in the text image in the text editing area.

[0310] The editing module 1408 is used to display the edited text in the text editing area in response to a text editing event triggered for the text editing area.

[0311] The text obtaining module 1410 is used to obtain the recognized text of the image to be recognized in response to a text editing completion event, where the recognized text includes the text obtained by editing.

[0312] In this embodiment, in response to an image recognition trigger event, an image to be recognized is determined. When the image to be recognized includes a text image, an image area and a text editing area are displayed on the same screen. The image area displays the image to be recognized, so that the image to be recognized and the area for editing text are presented on the same screen, so that the user can edit the text by comparing the image, avoiding the inconvenience caused by image display and text editing on different pages. An editing guide prompt is displayed for the text editing area to instruct the user which text to edit in the text editing area through the editing guide prompt to obtain the correct text. In response to a text editing event triggered for the text editing area, the edited text is displayed in the text editing area. In response to a text editing completion event, the recognized text of the image to be recognized is obtained. The obtained recognized text includes the edited text. An interactive method is provided for obtaining the text in the image by combining machine recognition and manual editing. In the case of inaccurate machine recognition, manual editing can be used to assist, so that the text recognition of the image is more flexible and the recognized text of the image is more accurate.

[0313] In one embodiment, the same-screen display module 1404 is also used to display the editing area trigger control when the image to be identified includes a text image and the text image recognition fails; in response to a trigger event of the editing area trigger control, the image area and the text editing area are displayed on the same screen.

[0314] In this embodiment, when the image to be identified includes a text image and the text image recognition fails, an editing area trigger control automatically pops up, allowing the user to trigger the control to automatically display the image area and the text editing area on the same screen, making it convenient for the user to manually enter the text in the text image.

[0315] In one embodiment, the on-screen display module 1404 is also used to display a text display area when the image to be recognized includes a text image of a preset text category; the text display area displays text items of a preset text category, and the text items are used to display the recognized text of the text image; when the text format of the recognized text of the text image does not match the preset text format corresponding to the preset text category, a text item of the preset text category marked by a text tag is displayed; in response to a trigger event of recognizing text in the marked text item, an image area and a text editing area are displayed on the same screen.

[0316] In this embodiment, when the image to be recognized includes a text image of a preset text category, a text display area is displayed. Regardless of whether the text in the text image can be recognized, a text item of the preset text category is displayed in the text display area, so that the user can understand what content needs to be recognized. When at least a portion of the content of the text image is recognized, the recognized text can be displayed in the text item, so that the user can view the recognized text and the unrecognized text, and can also understand whether the recognition is accurate. When the text format of the recognized text of the text image does not match the preset text format, indicating that the recognition is inaccurate, a text item of the preset text category marked by a text mark is displayed to prompt the user that the part is inaccurately recognized through the text mark, so that the user can trigger the same-screen display of the image area and the text editing area for the inaccurately recognized part, so as to manually edit the part that the machine recognizes inaccurately in the text editing area, thereby obtaining an accurate recognition result.

[0317] In one embodiment, the same-screen display module 1404 is also used to respond to a text editing completion event, replace the recognized text in the text item marked in the text display area with the edited text and display it; when the text format of the edited text matches the preset text format, the recognized text of the image to be recognized is obtained.

[0318] In this embodiment, in response to the text editing completion event, the recognized text in the marked text item in the text display area is replaced with the edited text and displayed, so that the user can judge whether the obtained text is accurate by whether the text item is marked. When the text format of the edited text matches the preset text format, the complete recognized text of the image to be recognized can be accurately obtained from the text display area. In addition, the user can check all the recognition information again in the text display area, which helps to improve the accuracy of the obtained text.

[0319] In one embodiment, the same-screen display module 1404 is also used to display a picture-text comparison page when the image to be identified includes a text image; on the picture-text comparison page, an image area and a text editing area are displayed.

[0320] In this embodiment, when the image to be identified includes a text image, a picture-text comparison page is displayed. On the picture-text comparison page, an image area and a text editing area are displayed, so that the image area for displaying the image and the text editing area for editing the text can be displayed on the same page. This allows the user to edit the text in the text editing area without switching pages to view the text in the image, thereby improving the flexibility of manual input.

[0321] In one embodiment, the device further comprises a moving module; the moving module is used to move the image to be identified in the image area in response to an image movement event of the image to be identified according to the image movement direction indicated by the image movement event.

[0322] In this embodiment, the user can move the image to be identified in the image area, so that the user can move the text image in the image to be identified to a position that is easy to observe, so as to perform manual editing in the text editing area by comparing the text image.

[0323] In one embodiment, the size of the text editing area is smaller than the size of the image area, and the text editing area covers a portion of the image to be recognized in the image area;

[0324] The moving module is also used to respond to a region moving event of the text editing region and move the text editing region on the image region according to the region moving direction indicated by the region moving event.

[0325] In this embodiment, the size of the text editing area is smaller than that of the image area, and the text editing area covers a portion of the image to be identified in the image area, so that the text editing area can be moved within the range limited by the image area, so that the text editing area and the image to be identified can be displayed on the same screen no matter how they are moved, so that the user can move the image or text editing area as needed, so as to perform manual editing in the text editing area by comparing the image.

[0326] In one embodiment, the device also includes a zoom module; the zoom module is used to respond to a zoom event of the image to be identified, scale the image to be identified in the image area according to the zoom category indicated by the zoom event; and display at least a portion of the image to be identified after scaling in the image area.

[0327] In this embodiment, the image to be identified displayed in the image area can be enlarged or reduced by the user, so that the user can adjust the image to be identified to a suitable size, so as to perform manual editing in the text editing area by comparing the image.

[0328] In one embodiment, the zoom module is also used to respond to a text editing event triggered by a text editing area, enlarge the image to be identified and focus on the position of the text image for display; in the text editing area, display the text obtained by editing the focused text image.

[0329] In this embodiment, in response to a text editing event triggered for a text editing area, the image to be identified is enlarged and automatically focused to the position of the text image for display, so that the position in the image where the text needs to be obtained through manual editing can be automatically located, which is convenient for users to view. In addition, enlarging the image to be identified also enlarges the text image, so that users can more clearly identify the text included in the text image, which is convenient for users to manually edit the text included in the text image in the text editing area.

[0330] In one embodiment, the zoom module is further used to display the image to be identified by the image tag to the text image tag in response to the text editing event triggered for the text editing area;

[0331] The image to be recognized is enlarged and focused on the position of the text image marked by the image marker for display.

[0332] In this embodiment, in response to a text editing event triggered for a text editing area, the text image in the image to be identified can be automatically marked and displayed through the image mark, so that the user can be prompted which text in the image needs to be manually edited through the mark in the image. The image to be identified is enlarged and focused on the position of the text image marked by the image mark for display, so that the text included in the text image is clearer, avoiding editing errors caused by the text font being too small for the user to browse clearly, which is conducive to improving the accuracy of manual editing.

[0333] In one embodiment, the image determination module 1402 is also used to display an image recognition interface, display an image import control on the image recognition interface; in response to a trigger event of the image import control, display multiple candidate images in the local image set; in response to an image selection event among the multiple candidate images, display the image to be identified selected by the image selection event on the image recognition interface.

[0334] In this embodiment, an image import control is displayed on the image recognition interface to provide an image import function on the image recognition interface, so that the user can independently select an image to be recognized from the local. In response to a trigger event of the image import control, multiple candidate images in the local image set are displayed, and in response to an image selection event from the multiple candidate images, the image to be recognized selected by the image selection event is displayed on the image recognition interface, so that the user can select an image for recognition from the local existing images.

[0335] In one embodiment, the image determination module 1402 is also used to display an image recognition interface, display image shooting controls on the image recognition interface; in response to a triggering operation on the image shooting controls, display a picture presented by the camera; in response to a shooting event triggered on the camera, display an image to be identified shot by the camera on the image recognition interface.

[0336] In this embodiment, an image shooting control is displayed on the image recognition interface to provide a real-time shooting function on the image recognition interface. In response to the triggering operation of the image shooting control, the picture presented by the camera is displayed, and in response to the shooting event triggered by the camera, the image to be identified shot by the camera is displayed on the image recognition interface, so that the user can obtain the image to be identified by shooting in real time with the camera, and multiple ways of obtaining images can be provided for the user.

[0337] In one embodiment, the image determination module 1402 is further configured to display a scene interaction interface of a preset interaction scene, display an image recognition control on the scene interaction interface, and determine an image to be recognized in response to a triggering event of the image recognition control;

[0338] The device also includes an interaction module; the interaction module is used to display the scene interaction results obtained by performing scene interaction operations based on the recognized text in a preset interaction scene.

[0339] In this embodiment, a scene interaction interface of a preset interaction scene is displayed, an image recognition control is displayed in the scene interaction interface, and an image recognition function can be called in the preset interaction scene, so that the image to be recognized and the text editing area can be displayed on the same screen in each interaction scene, so that image recognition can be applied to each interaction scene. After obtaining the recognized text through machine recognition and manual editing, in the preset interaction scene, the recognized text obtained by image recognition is subjected to the corresponding scene interaction operation in the preset interaction scene to obtain the interaction result in the corresponding scene, so that more interaction scenes can be adapted.

[0340] In one embodiment, the image determination module 1402 is further configured to obtain an image storage path corresponding to the image to be identified in response to a triggering event of the image recognition control, and obtain the image to be identified from the image storage path;

[0341] The same-screen display module 1404 is further used to obtain the control display text corresponding to the preset interactive scene when the image to be recognized includes a text image, and generate a text confirmation control corresponding to the control display text; determine an image area for displaying the image to be recognized, and determine a text editing area including a text confirmation control, and display the image area and the text editing area on the same screen;

[0342] The interaction module is also used to perform scene interaction operations based on the recognized text when the text confirmation control has an associated scene interaction operation, and obtain the scene interaction result in the preset interaction scene.

[0343] In this embodiment, in response to a trigger event of an image recognition control, an image storage path corresponding to the image to be recognized is obtained to obtain the image to be recognized from the image storage path. When the image to be recognized includes a text image, the control display text corresponding to the preset interaction scene is obtained to generate a text confirmation control corresponding to the control display text, thereby customizing the text editing area in the preset interaction scene. Determine the image area for displaying the image to be recognized, and determine the text editing area including the text confirmation control, and display the image area and the text editing area on the same screen to facilitate the user to enter the corresponding text in the text editing area in accordance with the image to be recognized. When there is an associated scene interaction operation with the text confirmation control, the scene interaction operation is performed based on the recognized text, and the scene interaction result in the preset interaction scene is obtained, so that image recognition can be applied to more interaction scenes, so as to solve the inaccurate image recognition in each interaction scene through machine recognition and manual editing, and the situation where frequent page switching is required when manually inputting text.

[0344] In one embodiment, the scene interaction interface of the preset interaction scene includes a session interface of a first session, and the scene interaction result represents joining a second session; the interaction module is also used to display a session description interface searched based on the recognition text; and in response to a session joining event on the session description interface, join the second session indicated by the session description interface.

[0345] In this embodiment, the image processing method can be applied to a conversation scenario. The user can trigger the image recognition function in the conversation interface to accurately obtain the conversation identifier in the image to be recognized through machine recognition and manual editing based on the same-screen display of the image to be recognized and the text editing area, and automatically search for the second conversation indicated by the conversation identifier to join the second conversation, so that the user does not need to remember the conversation identifier when searching for a conversation, nor does he need to frequently switch between the interface for displaying the image and the input interface for the conversation identifier, thereby improving the accuracy and speed of conversation search.

[0346] In one embodiment, the scene interaction interface of the preset interaction scene includes a text entry interface of the text entry scene, and the scene interaction result includes the entry result of the recognized text; the interaction module is also used to display the recognized text of the image to be recognized in the text entry interface; in response to the text entry event of the recognized text, prompt the entry result of the recognized text.

[0347] In this embodiment, the image processing method can be applied to text entry scenarios. The user can trigger the image recognition function in the text entry interface to accurately obtain the recognized text in the image to be recognized through machine recognition and manual editing based on the same-screen display of the image to be recognized and the text editing area, and automatically enter the recognized text of the image to be recognized. This allows the user to enter text without having to memorize the text in the image or frequently switch between the interface for displaying the image and the text entry interface, thereby improving the accuracy and speed of text entry.

[0348] Each module in the above image processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0349] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.15 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an image processing method is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0350] Those skilled in the art will understand that Fig.15The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0351] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0352] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0353] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0354] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0355] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0356] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0357] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image processing method, characterized in that: The method comprises: In response to an image recognition triggering event, determining an image to be recognized; When the image to be identified includes a text image, an image area and a text editing area are displayed on the same screen; the image area displays the image to be identified; Displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct editing the text included in the text image in the text editing area; In response to a text editing event triggered for the text editing area, displaying the edited text in the text editing area; In response to a text editing completion event, a recognized text of the image to be recognized is obtained, wherein the recognized text includes the text obtained by the editing.

2. The method according to claim 1, characterized in that When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including: When the image to be recognized includes a text image and the recognition of the text image fails, displaying an edit area trigger control; In response to a trigger event of the editing area trigger control, the image area and the text editing area are displayed on the same screen.

3. The method according to claim 1, characterized in that When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including: When the image to be recognized includes a text image of a preset text category, a text display area is displayed; the text display area displays text items of a preset text category, and the text items are used to display the recognized text of the text image; When the text format of the recognized text of the text image does not match the preset text format corresponding to the preset text category, displaying a text item of the preset text category marked by a text mark; In response to a trigger event of recognizing text in the marked text item, an image area and a text editing area are displayed on the same screen.

4. The method according to claim 3, characterized in that The step of obtaining the recognized text of the image to be recognized in response to the text editing completion event includes: In response to a text editing completion event, replacing the recognized text in the marked text item in the text display area with the edited text and displaying the text; When the text format of the text obtained by editing matches the preset text format, the recognized text of the image to be recognized is obtained.

5. The method according to claim 1, characterized in that When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including: When the image to be identified includes a text image, displaying a text-image comparison page; On the image-text comparison page, an image area and a text editing area are displayed.

6. The method according to claim 1, characterized in that The method further comprises: In response to an image movement event for the image to be recognized, the image to be recognized is moved in the image area according to an image movement direction indicated by the image movement event.

7. The method according to claim 6, characterized in that The size of the text editing area is smaller than the size of the image area, and the text editing area covers a portion of the image to be recognized in the image area; The step of responding to an image movement event of the image to be recognized, and moving the image to be recognized in the image area according to an image movement direction indicated by the image movement event, comprises: In response to an area moving event for the text editing area, the text editing area is moved on the image area according to an area moving direction indicated by the area moving event.

8. The method according to claim 1, characterized in that The method further comprises: In response to a zoom event on the image to be identified, scaling the image to be identified in the image area according to a zoom category indicated by the zoom event; At least a portion of the image to be recognized after scaling is displayed in the image area.

9. The method according to claim 1, characterized in that: The step of displaying the edited text in the text editing area in response to the text editing event triggered for the text editing area comprises: In response to a text editing event triggered for the text editing area, the image to be recognized is enlarged and focused to the position of the text image for display; In the text editing area, text edited from the focused text image is displayed.

10. The method according to claim 9, characterized in that In response to the text editing event triggered for the text editing area, the image to be recognized is enlarged and focused to the position of the text image for display, including: In response to a text editing event triggered for the text editing area, displaying the image to be identified that is marked by an image tag on the text image; The image to be recognized is enlarged, focused on the position of the text image marked by the image mark and displayed.

11. The method according to any one of claims 1 to 10, characterized in that: The step of determining an image to be recognized in response to an image recognition triggering event includes: Displaying an image recognition interface, and displaying an image import control on the image recognition interface; In response to a triggering event of the image import control, displaying a plurality of candidate images in a local image set; In response to an image selection event among the plurality of candidate images, the image to be recognized selected by the image selection event is displayed on the image recognition interface.

12. The method according to any one of claims 1 to 10, characterized in that: The step of determining an image to be recognized in response to an image recognition triggering event includes: Displaying an image recognition interface, and displaying image capture controls on the image recognition interface; In response to a triggering operation on the image shooting control, displaying a picture presented by a camera; In response to a shooting event triggered by the camera, an image to be identified shot by the camera is displayed on the image recognition interface.

13. The method according to any one of claims 1 to 10, characterized in that: The step of determining an image to be recognized in response to an image recognition triggering event includes: Displaying a scene interaction interface of a preset interaction scene, and displaying an image recognition control on the scene interaction interface; In response to a triggering event of the image recognition control, determining an image to be recognized; The method further comprises: In the preset interaction scenario, a scene interaction result obtained by performing a scene interaction operation based on the recognized text is displayed.

14. The method according to claim 13, characterized in that The text editing completion event includes a trigger event for a text confirmation control; the determining of an image to be recognized in response to the trigger event for the image recognition control includes: In response to a triggering event of the image recognition control, obtaining an image storage path corresponding to the image to be recognized, and obtaining the image to be recognized from the image storage path; When the image to be recognized includes a text image, the image area and the text editing area are displayed on the same screen, including: When the image to be recognized includes a text image, obtaining a control display text corresponding to the preset interaction scene, and generating a text confirmation control corresponding to the control display text; Determine an image area for displaying the image to be recognized, and determine a text editing area including the text confirmation control, and display the image area and the text editing area on the same screen; The displaying of the scene interaction result obtained by performing the scene interaction operation based on the recognized text in the preset interaction scene includes: When the text confirmation control has an associated scene interaction operation, the scene interaction operation is performed based on the recognized text to obtain a scene interaction result in the preset interaction scene.

15. The method according to claim 13, characterized in that The scene interaction interface of the preset interaction scene includes a session interface of the first session, and the scene interaction result represents joining the second session; The displaying of the scene interaction result obtained by performing the scene interaction operation based on the recognized text in the preset scene includes: Displaying a conversation description interface searched based on the recognition text; In response to a session joining event in the session description interface, joining a second session indicated by the session description interface.

16. The method according to claim 13, characterized in that The scene interaction interface of the preset interaction scene includes a text entry interface of a text entry scene, and the scene interaction result includes an entry result of the recognized text; The displaying of the scene interaction result obtained by performing the scene interaction operation based on the recognized text in the preset scene includes: On the text input interface, displaying the recognition text of the image to be recognized; In response to a text input event of the recognized text, an input result of the recognized text is prompted.

17. An image processing device, characterized in that: The device comprises: An image determination module, configured to determine an image to be identified in response to an image recognition triggering event; A same-screen display module, used for displaying an image area and a text editing area on the same screen when the image to be identified includes a text image; the image area displays the image to be identified; A prompt module, used for displaying an editing guide prompt for the text editing area; the editing guide prompt is used to instruct to edit the text included in the text image in the text editing area; An editing module, configured to display the edited text in the text editing area in response to a text editing event triggered for the text editing area; The text obtaining module is used to obtain the recognized text of the image to be recognized in response to a text editing completion event, wherein the recognized text includes the text obtained by the editing.

18. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 16 are implemented.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

20. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

Images