Vehicle frame number recognition method and device, storage medium and electronic device

CN113673416BActive Publication Date: 2024-11-29ZHEJIANG DAHUA TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110950416.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-18
Publication Date
2024-11-29
Estimated Expiration
2041-08-18

AI Technical Summary

Technical Problem

In the prior art, the method of manually recording non-motor vehicle frame numbers is inefficient, resulting in low information recording efficiency.

Method used

The frame number of the non-motor vehicle is collected through the target terminal to evaluate the image quality. If the recognition conditions are not met, a guide information is sent for re-acquisition until the conditions are met, and text recognition is performed to obtain the frame number.

Benefits of technology

Improves the recording efficiency of non-motor vehicle frame numbers, ensures accurate identification and simplifies user operations, and reduces manual intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113673416B_ABST
    Figure CN113673416B_ABST
Patent Text Reader

Abstract

The present application discloses a method and device for recognizing a vehicle frame number, a storage medium and an electronic device, wherein the method comprises: performing image acquisition of the vehicle frame number of a non-motor vehicle through a target terminal to obtain a first acquired image; when the image quality of the first acquired image does not meet the image recognition condition, sending a first guidance message through the target terminal, wherein the first guidance message is used to guide the use of the target terminal to re-acquire the image of the vehicle frame number of the non-motor vehicle; re-acquire the image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a second acquired image; when the image quality of the second acquired image meets the image recognition condition, performing text recognition on the second acquired image to obtain the vehicle frame number of the non-motor vehicle. The present application solves the problem of low efficiency of information recording in the related art of manually recording the non-motor vehicle frame number.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communications, and more specifically, to a method and device for identifying a vehicle frame number, a storage medium, and an electronic device. Background Art

[0002] With the frequent occurrence of non-motor vehicle traffic accidents, the importance of non-motor vehicle registration review and violation control is gradually increasing. At present, the main method of recording accident vehicles is manual identification and recording of vehicle frame numbers, which is relatively inefficient. Here, the vehicle frame number of a non-motor vehicle is a set of numbers assigned by the manufacturer to each non-motor vehicle, which is equivalent to the ID card of a non-motor vehicle.

[0003] It can be seen that the method of manually recording non-motor vehicle frame numbers in the related art has the problem of low efficiency in information recording. Summary of the invention

[0004] The embodiments of the present application provide a method and device for recognizing a frame number, a storage medium, and an electronic device, so as to at least solve the problem of low efficiency of information recording in the related art by manually recording the frame number of non-motor vehicles.

[0005] According to one aspect of an embodiment of the present application, a method for recognizing a vehicle frame number is provided, comprising: performing image capture of a non-motor vehicle frame number through a target terminal to obtain a first captured image; in a case where the image quality of the first captured image does not meet an image recognition condition, issuing a first guidance message through the target terminal, wherein the first guidance message is used to guide the use of the target terminal to re-capture an image of the non-motor vehicle frame number; re-capturing an image of the non-motor vehicle frame number through the target terminal to obtain a second captured image; in a case where the image quality of the second captured image meets the image recognition condition, performing text recognition on the second captured image to obtain the frame number of the non-motor vehicle.

[0006] In an exemplary embodiment, before the target terminal performs image capture of the vehicle frame number of the non-motor vehicle to obtain the first captured image, the method further includes: in response to a detected shooting trigger operation, issuing a second guidance information through the target terminal, wherein the second guidance information is used to guide the use of the target terminal to perform image capture of the vehicle frame number of the non-motor vehicle.

[0007] In an exemplary embodiment, after performing image capture of the vehicle frame number of the non-motor vehicle through the target terminal to obtain the first captured image, the method further includes: evaluating the first captured image according to target image attributes to obtain a target evaluation result of the first captured image, wherein the target image attributes are used to characterize the image quality of the first captured image; and determining, based on the target evaluation result, that the image quality of the first captured image does not meet the image recognition condition.

[0008] In an exemplary embodiment, sending the first guidance information through the target terminal includes at least one of the following: when it is detected that the target terminal is in a non-landscape state, sending a landscape prompt information through the target terminal, wherein the landscape prompt information is used to prompt the use of the landscape screen for image capture; displaying a guide frame on the image capture interface of the target terminal, wherein the guide frame is used to guide at least one of the following: the image capture angle, the position of the frame number of the non-motor vehicle, the direction of the frame number of the non-motor vehicle, and the second captured image is the image captured by the target terminal and located in the guide frame.

[0009] In an exemplary embodiment, performing text recognition on the second acquired image to obtain the frame number of the non-motor vehicle includes: performing text line detection on the second acquired image to obtain text line vertices corresponding to a target text line in the second acquired image, wherein the target text line is located in a text line image with the text line vertices as vertices; performing transmission transformation on the text line image according to a target resolution to obtain the text line image after transmission transformation; performing text line recognition on the text line image after transmission transformation to obtain the frame number of the non-motor vehicle.

[0010] In an exemplary embodiment, after the first guidance information is sent through the target terminal, the method further includes: sending format selection indication information through the target terminal, wherein the format selection indication information is used to indicate the selection of the frame number format of the non-motor vehicle from multiple frame number formats; in response to the detected format selection operation, determining the frame number format of the non-motor vehicle and the number of captured images corresponding to the frame number format of the non-motor vehicle, wherein different frame number formats among the multiple frame number formats correspond to different numbers of captured images.

[0011] In an exemplary embodiment, the target terminal re-captures an image of the frame number of the non-motor vehicle to obtain the second captured image, including: when the frame number format of the non-motor vehicle is the target format, the target terminal re-captures the frame number of the non-motor vehicle twice to obtain two sub-captured images, wherein the target format is a format in which the direction of the frame number of the non-motor vehicle is perpendicular to the direction of the pole of the non-motor vehicle, and the second captured image includes the two sub-captured images, and the two sub-captured images correspond to different shooting angles.

[0012] In an exemplary embodiment, after re-capturing the frame number of the non-motor vehicle twice through the target terminal to obtain the two sub-captured images, the method further includes: stitching the two sub-captured images to obtain a stitched image; and before performing text recognition on the second captured image to obtain the frame number of the non-motor vehicle, the method further includes: splitting the stitched image to obtain the two sub-captured images.

[0013] In an exemplary embodiment, performing text recognition on the second captured image to obtain the frame number of the non-motor vehicle includes: performing text recognition on the first sub-captured image of the two sub-captured images in a target direction to obtain a first sub-frame number; performing text recognition on the second sub-captured image of the two sub-captured images in a direction opposite to the target direction to obtain a second sub-frame number; and splicing the first sub-frame number and the second sub-frame number to obtain the frame number of the non-motor vehicle.

[0014] According to another aspect of an embodiment of the present application, a frame number recognition device is also provided, including: a first acquisition unit, used to perform image acquisition of the frame number of a non-motor vehicle through a target terminal to obtain a first acquired image; a first guidance unit, used to send a first guidance message through the target terminal when the image quality of the first acquired image does not meet the image recognition condition, wherein the first guidance message is used to guide the use of the target terminal to re-acquire the image of the frame number of the non-motor vehicle; a second acquisition unit, used to re-acquire the image of the frame number of the non-motor vehicle through the target terminal to obtain a second acquired image; and an identification unit, used to perform text recognition on the second acquired image when the image quality of the second acquired image meets the image recognition condition to obtain the frame number of the non-motor vehicle.

[0015] In an exemplary embodiment, the device also includes: a second guidance unit, which is used to send a second guidance message through the target terminal in response to a detected shooting trigger operation before performing image capture of the frame number of the non-motor vehicle through the target terminal to obtain the first captured image, wherein the second guidance message is used to guide the use of the target terminal to capture the image of the frame number of the non-motor vehicle.

[0016] In an exemplary embodiment, the device also includes: an evaluation unit, which is used to perform image capture of the frame number of the non-motor vehicle through the target terminal to obtain the first captured image, and then evaluate the first captured image according to target image attributes to obtain a target evaluation result of the first captured image, wherein the target image attributes are used to characterize the image quality of the first captured image; and a first determination unit, which is used to determine, based on the target evaluation result, that the image quality of the first captured image does not meet the image recognition condition.

[0017] In an exemplary embodiment, the first guiding unit includes at least one of the following: a prompt module, which is used to issue a horizontal screen prompt message through the target terminal when it is detected that the target terminal is in a non-horizontal screen state, wherein the horizontal screen prompt message is used to prompt the use of the horizontal screen for image acquisition; a display module, which is used to display a guide frame on the image acquisition interface of the target terminal, wherein the guide frame is used to guide at least one of the following: the image acquisition angle, the position of the frame number of the non-motor vehicle, the direction of the frame number of the non-motor vehicle, and the second acquired image is the image acquired by the target terminal and located in the guide frame.

[0018] In an exemplary embodiment, the recognition unit includes: a detection module, used to perform text line detection on the second acquired image to obtain text line vertices corresponding to the target text line in the second acquired image, wherein the target text line is located in a text line image with the text line vertices as vertices; a transformation module, used to perform transmission transformation on the text line image according to a target resolution to obtain the text line image after transmission transformation; and a first recognition module, used to perform text line recognition on the text line image after transmission transformation to obtain the frame number of the non-motor vehicle.

[0019] In an exemplary embodiment, the device also includes: an indication unit, which is used to send format selection indication information through the target terminal after the first guidance information is sent through the target terminal, wherein the format selection indication information is used to indicate the selection of the frame number format of the non-motor vehicle from multiple frame number formats; a second determination unit, which is used to determine the frame number format of the non-motor vehicle and the number of captured images corresponding to the frame number format of the non-motor vehicle in response to a detected format selection operation, wherein different frame number formats among the multiple frame number formats correspond to different numbers of captured images.

[0020] In an exemplary embodiment, the second acquisition unit includes: an acquisition module, which is used to re-acquire the frame number of the non-motor vehicle twice through the target terminal when the frame number layout of the non-motor vehicle is the target layout, so as to obtain two sub-acquired images, wherein the target layout is a layout in which the direction of the frame number of the non-motor vehicle is perpendicular to the direction of the pole of the non-motor vehicle, and the second acquired image includes the two sub-acquired images, and the two sub-acquired images correspond to different shooting angles.

[0021] In an exemplary embodiment, the device also includes: a splicing unit, which is used to stitch the two sub-captured images to obtain a spliced ​​image after re-capturing the frame number of the non-motor vehicle twice through the target terminal to obtain the two sub-captured images; and a splitting unit, which is used to split the spliced ​​image to obtain the two sub-captured images before performing text recognition on the second captured image to obtain the frame number of the non-motor vehicle.

[0022] In an exemplary embodiment, the recognition unit includes: a second recognition module, used to perform text recognition on the first sub-captured image of the two sub-captured images according to a target direction to obtain a first sub-frame number; a third recognition module, used to perform text recognition on the second sub-captured image of the two sub-captured images according to a direction opposite to the target direction to obtain a second sub-frame number; and a splicing module, used to splice the first sub-frame number and the second sub-frame number to obtain the frame number of the non-motor vehicle.

[0023] According to another aspect of the embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned vehicle frame number recognition method when running.

[0024] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the vehicle frame number recognition method through the computer program.

[0025] In an embodiment of the present application, a method of performing image capture on the frame number of a non-motor vehicle and guiding re-image capture based on the image quality is adopted, and the frame number of the non-motor vehicle is captured by a target terminal to obtain a first captured image; when the image quality of the first captured image does not meet the image recognition condition, a first guidance information is sent by the target terminal, wherein the first guidance information is used to guide the use of the target terminal to re-capture the frame number of the non-motor vehicle; the frame number of the non-motor vehicle is re-captured by the target terminal to obtain a second captured image; when the image quality of the second captured image meets the image recognition condition, text recognition is performed on the second captured image to obtain the frame number of the non-motor vehicle. Since the image capture of the frame number of the non-motor vehicle can reduce user operations, and at the same time, the frame number recognition based on the image quality can ensure accurate recognition of the frame number, and guiding the image capture process by the guidance information can speed up the image capture process. Therefore, the technical effect of improving the recording efficiency of the non-motor vehicle frame number can be achieved, thereby solving the problem of low efficiency of information recording in the related art by manually recording the non-motor vehicle frame number. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 is a schematic diagram of a hardware environment of an optional vehicle frame number recognition method according to an embodiment of the present application;

[0029] Figure 2 is a flow chart of an optional method for identifying a vehicle frame number according to an embodiment of the present application;

[0030] Figure 3 is a schematic diagram of an optional method for identifying a vehicle frame number according to an embodiment of the present application;

[0031] Figure 4is a schematic diagram of another optional method for identifying a vehicle frame number according to an embodiment of the present application;

[0032] Figure 5 is a schematic diagram of an optional image acquisition process according to an embodiment of the present application;

[0033] Figure 6 is a schematic diagram of an optional text recognition process according to an embodiment of the present application;

[0034] Figure 7 is a structural block diagram of an optional vehicle frame number recognition device according to an embodiment of the present application;

[0035] Figure 8 It is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0037] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] According to one aspect of an embodiment of the present application, a method for identifying a vehicle frame number is provided. Optionally, in this embodiment, the above-mentioned method for identifying a vehicle frame number can be applied to Figure 1 In the hardware environment composed of the terminal 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104.

[0039] The network may include but is not limited to at least one of the following: a wired network, a wireless network. The wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal 102 may not be limited to a PC, a mobile phone, a tablet computer, etc.

[0040] The vehicle frame number recognition method of the embodiment of the present application can be executed by the server 104, or by the terminal 102, or by both the server 104 and the terminal 102. The vehicle frame number recognition method of the embodiment of the present application can be executed by the terminal 102 or by a client installed thereon.

[0041] Taking the vehicle frame number recognition method in this embodiment executed by the terminal 102 as an example, Figure 2 is a flow chart of an optional method for identifying a vehicle frame number according to an embodiment of the present application, such as Figure 2 As shown, the process of the method may include the following steps:

[0042] Step S202: Capture an image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a first captured image.

[0043] The frame number recognition method in this embodiment can be applied to the scenario of recording the frame number of non-motor vehicles. Relevant personnel can use their terminal equipment (for example, the target terminal) to capture the image of the frame number of the non-motor vehicle, and perform text recognition on the captured image to obtain the frame number of the non-motor vehicle. The frame number recognition method in this embodiment can be executed by the target terminal, or by the target server, or by the target terminal and the target server. In this embodiment, the above-mentioned frame number recognition method is executed by the target terminal as an example for explanation.

[0044] In order to record the frame number of a non-motor vehicle, the target object (the object corresponding to the target terminal, which can be used to identify relevant personnel using the target terminal) can use the image acquisition component (for example, a camera) on the target terminal to capture an image of the frame number of the non-motor vehicle, and the captured image is the first captured image.

[0045] Step S204, when the image quality of the first captured image does not meet the image recognition condition, a first guidance message is sent through the target terminal, wherein the first guidance message is used to guide the target terminal to re-capture the image of the frame number of the non-motor vehicle.

[0046] The text on the frame number of a motor vehicle is printed, while the frame number of a non-motor vehicle is generally a stamped body. The stamped text image obtained by photographing it (for example, the first acquired image) may have text and background colors that are similar or the same, and low image contrast.

[0047] In order to avoid the failure to correctly identify the vehicle frame number due to poor image quality (for example, the contrast of the steel-stamped text image is too low), thereby affecting the efficiency of the vehicle frame number recognition, after obtaining the first acquired image, the target terminal can determine whether the image quality of the first acquired image meets the image recognition conditions. For example, a quality assessment module can be added to the target terminal to assess the image quality of the first acquired image and determine whether the image quality of the first acquired image meets the image recognition conditions. The above-mentioned image recognition conditions can be recognition conditions corresponding to specific image attributes, such as the clarity of the image, the number of digits contained in the image, etc. If the image quality of the first acquired image meets the image recognition conditions, the target terminal can perform text recognition on the first acquired image to obtain the vehicle frame number of the non-motor vehicle.

[0048] If the image quality of the first captured image does not meet the image recognition condition, the target terminal may prompt the user to recapture the image. In order to improve the image quality of the captured image and address the problem of low contrast in the steel-stamped text image, a shooting guidance module may be added to the target terminal. The shooting guidance module may be a program module on the target terminal for shooting guidance. Optionally, shooting guidance may also be performed by other program modules or components. In this embodiment, the shooting guidance module is used as an example for explanation.

[0049] The target terminal may send a first guidance message, for example, by sending the first guidance message through a shooting guidance module, and the first guidance message is used to guide the target terminal to re-capture the image of the non-motor vehicle frame number. The first guidance message may be sent through a visual display method such as text or a guide frame, or may be sent through an auditory method such as a prompt voice, which is not limited in this embodiment.

[0050] Step S206: re-capture the image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a second captured image.

[0051] The target terminal can also re-capture the frame number of the non-motor vehicle through the image acquisition component of the target terminal based on the first guidance information to obtain a second captured image. The second captured image can include the frame number of the non-motor vehicle.

[0052] If the number of numbers included in the first captured image is less than a preset number threshold, the first guidance information can be used to guide the target terminal to re-capture the image of the non-motor vehicle frame number by the number of images required, for example, at least two. Correspondingly, the number of the second captured images can be one or more.

[0053] Step S208: When the image quality of the second collected image meets the image recognition condition, text recognition is performed on the second collected image to obtain the frame number of the non-motor vehicle.

[0054] For the second collected image, the target terminal may determine whether the image quality of the second collected image meets the image recognition condition in a similar manner as the first collected image. If the image quality of the second collected image meets the image recognition condition, the target terminal (or the target server that is in communication with the target terminal) may perform text recognition on the second collected image to obtain the frame number of the non-motor vehicle, and the number of digits contained in the recognized frame number of the non-motor vehicle is the target number, for example, 15.

[0055] Optionally, the second collected image can be sent to a recognizer for recognition to obtain the number content. There can be multiple text recognition methods used, including but not limited to: CRNN (Convolution Recurrent Neural Network) based on deep learning.

[0056] If the image quality of the second captured image does not meet the image recognition conditions, a method similar to the above can be used to guide the re-image capture of the non-motor vehicle frame number, or a target prompt information can be issued through the target terminal, which is used to prompt the manual recording of the non-motor vehicle frame number.

[0057] Through the above steps, the frame number of the non-motor vehicle is imaged through the target terminal to obtain a first captured image; when the image quality of the first captured image does not meet the image recognition condition, the first guidance information is sent through the target terminal, wherein the first guidance information is used to guide the use of the target terminal to re-capture the image of the frame number of the non-motor vehicle; the frame number of the non-motor vehicle is imaged again through the target terminal to obtain a second captured image; when the image quality of the second captured image meets the image recognition condition, text recognition is performed on the second captured image to obtain the frame number of the non-motor vehicle, which solves the problem of low efficiency of information recording in the related art of manually recording the frame number of the non-motor vehicle, and improves the recording efficiency of the frame number of the non-motor vehicle.

[0058] In an exemplary embodiment, before the target terminal performs image acquisition of the vehicle frame number of the non-motor vehicle to obtain the first acquired image, the method further includes:

[0059] S11, in response to the detected shooting trigger operation, a second guidance information is sent through the target terminal, wherein the second guidance information is used to guide the use of the target terminal to capture an image of the vehicle frame number of the non-motor vehicle.

[0060] Before using the target terminal to collect images of the vehicle frame number of the non-motor vehicle, the target object can trigger the entry into the image acquisition interface by performing a shooting trigger operation on the target terminal. The shooting trigger operation can be an operation performed on the target terminal, such as clicking, double-clicking, sliding, or a combination of multiple operations performed on the target terminal to enter the image acquisition interface through a multi-level menu. This is not limited in this embodiment.

[0061] After the shooting trigger operation is detected, the image acquisition interface can be displayed on the target terminal. At the same time, the second guidance information can also be sent through the target terminal, for example, the second guidance information is sent through the shooting guidance module, and the second guidance information is used to guide the use of the target terminal to collect images of the frame number of the non-motor vehicle. The guidance method is similar to that in the above embodiment, and will not be repeated here.

[0062] Through this embodiment, the image acquisition interface is triggered based on the detected shooting trigger operation, and the image shooting is guided by the guide information, which can improve the interactivity between the user and the terminal and improve the efficiency of image shooting.

[0063] In an exemplary embodiment, after the target terminal performs image acquisition of the vehicle frame number of the non-motor vehicle to obtain the first acquired image, the method further includes:

[0064] S21, evaluating the first acquired image according to the target image attribute to obtain a target evaluation result of the first acquired image, wherein the target image attribute is used to characterize the image quality of the first acquired image;

[0065] S22: Determine, based on the target evaluation result, that the image quality of the first acquired image does not satisfy an image recognition condition.

[0066] When determining whether the image quality of the first acquired image meets the image recognition conditions, the quality assessment module can automatically judge image attributes such as image contrast, clarity, and frame number integrity to ensure the quality of the image sent to the recognition module (a program module on the target terminal used for text recognition).

[0067] The image quality assessment module can evaluate the image quality of the first acquired image (i.e., the vehicle frame number image) from dimensions such as contrast, clarity, and text integrity (i.e., target image attributes), and obtain evaluation results of the first acquired image on each target image attribute respectively. The target evaluation result of the first acquired image can be a fusion of the evaluation results of the first acquired image on each target image attribute, for example, a weighted average.

[0068] For example, the image quality assessment module can evaluate the image quality of the collected vehicle frame number image from three dimensions: contrast, clarity, and text integrity, and obtain three scores. The total score is the weighted average of the three.

[0069] Optionally, when conducting the evaluation, a classification-based deep learning network can be used to first extract the feature vector of the image, then introduce GAP (Global Average Pooling) and FPN (Feature Pyramid Network) to optimize feature extraction, and finally add the head module of the deep learning network for prediction. The network outputs the probabilities corresponding to the three labels of contrast, clarity, and text completeness, and finally weights the scores to obtain the final quality evaluation result.

[0070] If the target evaluation result indicates that the first acquired image meets the image recognition conditions (for example, the total score reaches the target score), the acquired image can be output; if the target evaluation result indicates that the first acquired image does not meet the image recognition conditions, re-image acquisition is triggered.

[0071] Through this embodiment, by performing quality assessment on the collected images, the quality of the images used for vehicle frame number recognition can be guaranteed, thereby improving the accuracy of vehicle frame number recognition.

[0072] In an exemplary embodiment, the shooting guidance module may guide image acquisition from multiple angles, which may include but are not limited to at least one of the following: the terminal status of the target terminal, and the shooting status of the target terminal.

[0073] As an optional implementation manner, sending the first guidance information through the target terminal includes:

[0074] When it is detected that the target terminal is in a non-landscape state, a landscape prompt message is sent through the target terminal, wherein the landscape prompt message is used to prompt the user to use the landscape screen for image acquisition:

[0075] S31, when it is detected that the target terminal is in a non-landscape state, sending a landscape prompt message through the target terminal, wherein the landscape prompt message is used to prompt the use of the landscape screen for image acquisition.

[0076] In order to take high-quality pictures as much as possible and improve the recognition rate, the shooting guidance module can automatically detect whether the target terminal is in a horizontal screen state. When it is detected that the target terminal is in a non-horizontal screen state, a horizontal screen prompt message can be issued through the target terminal to prompt the use of the horizontal screen for image acquisition. There are many ways to issue a horizontal screen prompt message, which may include but are not limited to at least one of the following: a horizontal screen prompt pop-up window, a horizontal screen prompt text, and a horizontal screen prompt voice.

[0077] For example, a shooting guidance module can be added to a mobile phone (an example of a target terminal). When collecting images, the shooting guidance module can automatically detect whether the mobile phone is in horizontal screen mode. If not, it will prompt to use horizontal screen shooting and improve the resolution of long rows of numbered characters.

[0078] As another optional implementation manner, sending the first guidance information through the target terminal includes:

[0079] S32, displaying a guide frame on the image acquisition interface of the target terminal, wherein the guide frame is used to guide at least one of the following: the acquisition angle of the image, the position of the frame number of the non-motor vehicle, the direction of the frame number of the non-motor vehicle, and the second acquired image is an image acquired by the target terminal and located in the guide frame.

[0080] In this embodiment, the image capture process can be guided by a guide frame. Taking the shooting guidance performed by the shooting guidance module in the aforementioned embodiment as an example, in order to capture high-quality pictures as much as possible and improve the recognition rate of the frame number, the shooting guidance module can display a guide frame on the image acquisition interface of the target terminal to guide the shooting of the non-motor vehicle frame number. The guide frame can be used to guide the acquisition parameters of the image acquisition, for example, guiding the shooting angle of the image (i.e., the acquisition angle), guiding the position of the non-motor vehicle frame number, and guiding the direction of the non-motor vehicle frame number. The second captured image can be a complete image captured by the target terminal, or it can be an image captured by the target terminal and located in the guide frame.

[0081] For example, the shooting guidance module can add a guide frame to the shooting interface to guide the shooting angle, frame number position, text direction, etc. of the imaging picture, and only capture the sub-image in the guide frame for use, thereby improving the quality of the collected picture.

[0082] Through this embodiment, horizontal screen shooting is prompted by horizontal screen prompt information, and / or, by using a guide frame to guide the image acquisition of the non-motor vehicle frame number, the quality of the captured image can be improved, thereby improving the recognition rate of the image to be identified.

[0083] In an exemplary embodiment, after the first guidance information is sent through the target terminal, the method further includes:

[0084] S41, issuing format selection instruction information through the target terminal, wherein the format selection instruction information is used to instruct to select a frame number format of a non-motor vehicle from multiple frame number formats;

[0085] S42, in response to the detected layout selection operation, determining the frame number layout of the non-motor vehicle and the number of captured images corresponding to the frame number layout of the non-motor vehicle, wherein different frame number layouts among the multiple frame number layouts correspond to different numbers of captured images.

[0086] The frame number of a motor vehicle is usually located on a nameplate suitable for writing, while the frame number of a non-motor vehicle is located on a cylindrical pole. Due to the different formats of different manufacturers, there are two types according to the direction of the text. One is in the same direction as the pole, such as Figure 3 As shown in the version 1 in the figure, the other is the vertical direction of the pole, such as Figure 3 As shown in Layout 2 in FIG, for Layout 2 (i.e., a layout with text in a direction perpendicular to the pole, such as a double-line curved frame number), it is difficult to capture a complete frame number. In addition to the above two layouts, there may be other layouts that have special requirements for image acquisition (e.g., three or more images need to be captured).

[0087] When performing image acquisition, the target terminal may issue format selection indication information, and the format selection indication information is used to indicate the selection of a non-motor vehicle frame number format from multiple frame number formats. Different frame number formats among the multiple frame number formats correspond to different numbers of acquired images, which may include but are not limited to: format 1, format 2, and may also include other types of specific formats, or non-specific formats (for example, other formats). The above non-specific formats can be set by the number of acquired images required.

[0088] The target object may perform a layout selection operation on the target terminal, and select a layout corresponding to the current non-motor vehicle frame number from multiple frame number layouts. The target terminal may detect the above-mentioned layout selection operation. In response to the detected layout selection operation, the target terminal may determine the frame number layout of the non-motor vehicle, and based on the corresponding relationship between the frame number layout and the number of collected images, determine the number of collected images corresponding to the frame number layout of the non-motor vehicle.

[0089] The determined number of captured images can be used to guide the image capture process. For example, if it is format 1, the number of captured images is 1, and the target terminal can perform subsequent processing after capturing an image that meets the image recognition conditions. For another example, if it is format 2, the number of captured images is 2, and the target terminal can perform subsequent processing after capturing two images that meet the image recognition conditions. For another example, if it is a non-specific format, the subsequent processing can be performed in response to the detected shooting end operation.

[0090] Through this embodiment, by prompting to select a frame number format and determining the number of captured images based on the selected frame number format, it can be applicable to different frame number formats, thereby improving the convenience of image capture.

[0091] In an exemplary embodiment, re-capturing the vehicle frame number of the non-motor vehicle by the target terminal to obtain the second captured image includes:

[0092] S51, when the frame number format of the non-motor vehicle is the target format, the frame number of the non-motor vehicle is re-imaged twice through the target terminal to obtain two sub-captured images, wherein the target format is a format in which the direction of the frame number of the non-motor vehicle is perpendicular to the direction of the pole of the non-motor vehicle, and the second captured image includes two sub-captured images, and the two sub-captured images correspond to different shooting angles.

[0093] For a layout in which the direction of the non-motor vehicle frame number is the same as the direction of the non-motor vehicle pole (e.g., layout 1), the target terminal can normally capture an image, for example, based on the guide frame, and output the image. For a layout in which the direction of the non-motor vehicle frame number is perpendicular to the direction of the non-motor vehicle pole, that is, the target layout (e.g., layout 2), this embodiment provides a collection mode adapted thereto.

[0094] If the frame number format of the non-motor vehicle is the target format, the target terminal can capture the frame number of the non-motor vehicle at least twice at different shooting angles to obtain at least two captured images. For the convenience of frame number recognition, the number of captured images can be two, that is, the target terminal can re-capture the frame number of the non-motor vehicle twice to obtain two sub-captured images, and the second captured image includes the two sub-captured images.

[0095] For example, considering that it is difficult to take a complete shot of format 2 (that is, double-row curved frame numbers) at one time, a collection mode suitable for double-row curved frame numbers can be introduced, that is, a multiple-shot mode. If it belongs to format 2, two images can be shot through the guide frame, for example, one shot on each side. In the above manner, the problem that format 2 is difficult to take a complete shot at one time can be solved, and it is only necessary to ensure that the two pictures cover the complete number information, and there is no requirement for the number of repeated numbers in the two pictures, which is convenient for user operation.

[0096] Through this embodiment, by taking two pictures in a format in which the direction of the non-motor vehicle frame number is perpendicular to the direction of the non-motor vehicle pole, the integrity of information coverage can be ensured and the convenience of user operation can be improved.

[0097] In an exemplary embodiment, after the target terminal re-captures the image of the vehicle frame number of the non-motor vehicle twice to obtain two sub-captured images, the method further includes:

[0098] S61, stitching the two sub-captured images to obtain a stitched image.

[0099] In order to quickly access and manage the two sub-captured images (i.e., the two images taken for format 2), the target terminal can stitch the two sub-captured images into one, and finally return a stitched image, i.e., a stitched image. The stitching can be done by stitching up and down or by stitching left and right, which is not limited in this embodiment.

[0100] Correspondingly, before performing text recognition on the second collected image to obtain the vehicle frame number of the non-motor vehicle, the above method further includes:

[0101] S62, splitting the stitched image to obtain two sub-captured images.

[0102] When performing vehicle frame number recognition, text recognition can be directly performed on the spliced ​​intermediate image, that is, text recognition can be performed on the spliced ​​image to obtain the vehicle frame number of the non-motor vehicle.

[0103] For example, a spliced ​​image of a double-line curved frame number can be directly sent to a detection module (i.e., a program module for text recognition) and distinguished by the number of text lines output by the detection module (for example, for an image spliced ​​together from top to bottom, the number of text lines output is 4).

[0104] Optionally, in this embodiment, before performing text recognition, the target terminal may split the spliced ​​image into two images, i.e., two sub-captured images, and then perform text recognition on the split sub-captured images respectively. Performing text recognition on the second captured image to obtain the frame number of the non-motor vehicle may include: performing text recognition on the two sub-captured images to obtain the frame number of the non-motor vehicle.

[0105] It should be noted that the sub-captured image before stitching may not be completely consistent with the sub-captured image after splitting. For example, the splitting position may not be completely consistent with the stitching position, as long as the numbers contained in the sub-captured image before stitching and the sub-captured image after splitting are consistent.

[0106] For example, for non-motor vehicle frame number images, different image naming suffixes can be used to distinguish different layouts. When performing text recognition, the layout identification module can be used to identify the layout of the non-motor vehicle frame number according to the image naming suffix to determine whether it is layout 2. If so, the read image can be split into two images and text recognition can be performed separately.

[0107] Through this embodiment, by splicing and splitting the frame number images of non-motor vehicles in the target format, the convenience of image access and management can be improved, and the accuracy of frame number recognition can also be improved.

[0108] In an exemplary embodiment, performing text recognition on the second collected image to obtain the frame number of the non-motor vehicle includes:

[0109] S71, performing text line detection on the second acquired image to obtain text line vertices corresponding to a target text line in the second acquired image, wherein the target text line is located in a text line image having the text line vertices as vertices;

[0110] S72, performing transmission transformation on the text line image according to the target resolution to obtain a text line image after transmission transformation;

[0111] S73, performing text line recognition on the text line image after the transmission transformation to obtain the frame number of the non-motor vehicle.

[0112] When performing text recognition on the second acquired image, the processing can be performed through three modules (program modules on the target terminal): text line detection, text correction, and text line recognition. Text line detection can perform text line detection on the second acquired image to obtain text line vertices corresponding to the target text line in the second acquired image, and the target text line is located in the text line image with the text line vertices as vertices. Here, the number of text line vertices can be four.

[0113] For the above target format, text line recognition can be performed on the two sub-captured images respectively to obtain text line vertices corresponding to the target text line in each sub-captured image. The number of target text lines can be one or more, and correspondingly, each target text line can correspond to a different text line vertex.

[0114] For example, due to various transmission and rotation problems when users shoot, it is necessary to correct the captured images. Before correction, text line detection can be performed. The text line detection method uses a method with 4 points as the output result, such as east, dbnet, etc. If it is format 2, the two pictures can be sent to the text line detection module separately.

[0115] For any text line image with the detected text line vertex as a vertex, the text line image can be subjected to a transmission transformation according to the target resolution to obtain a text line image after the transmission transformation. If the direction of the text line in the text line image after the transmission transformation is not the predetermined direction, the text line image after the transmission transformation can be controlled to be oriented (for example, rotated) to obtain a text line image after the orientation adjustment.

[0116] For example, the text correction module can include two parts: transmission transformation and text line direction classification. The text correction module can first expand the coordinates of the four points of each text line outward by a certain proportion along the long and short sides; then, according to the actual average aspect ratio of the frame number, set the image resolution after the transmission transformation, for example, 32*320, and then perform correction according to the transmission transformation formula to obtain one or two positive or 180-degree frame number images. Finally, the text correction module can determine whether each text line after the transmission transformation is 0 degrees or 180 degrees by training the text direction classifier. If it is 180 degrees, a rotation operation is performed to obtain text line images that are all positive.

[0117] For the text line image after transmission transformation (or the text line image after direction adjustment), text line recognition can be performed on it to obtain the frame number of the non-motor vehicle. For example, the text line image can be sent to a recognizer for recognition to obtain the number content.

[0118] Through this embodiment, by performing text line detection, text correction and character recognition on the captured image, the accuracy of non-motor vehicle frame number recognition can be improved.

[0119] In an exemplary embodiment, performing text recognition on the second collected image to obtain the frame number of the non-motor vehicle includes:

[0120] S81, performing text recognition on a first sub-collected image of the two sub-collected images according to a target direction to obtain a first sub-frame number;

[0121] S82, performing text recognition on the second sub-collected image of the two sub-collected images in the direction opposite to the target direction to obtain a second sub-frame number;

[0122] S83, concatenating the first sub-frame number and the second sub-frame number to obtain a frame number of the non-motor vehicle.

[0123] For the second captured image whose frame number format is the target format, text recognition can be performed on the two sub-captured images respectively to obtain the corresponding sub-frame number (part of the frame number of the non-motor vehicle), and then the sub-frame numbers are spliced ​​to obtain the frame number of the non-motor vehicle.

[0124] For example, for layout 2, text recognition can be performed on two images separately, and the results of the two images can be spliced. Compared with the method of splicing two images first and then performing text recognition, this method of first performing text recognition separately and then splicing the two recognition results has higher recognition accuracy and is less complex than image splicing.

[0125] When performing text recognition, using the prior knowledge that the accuracy of the front digits in the left-side picture is better than that of the rear digits and vice versa for the right-side picture, text recognition can be performed on the first sub-captured image of the two sub-captured images in the target direction (for example, text recognition is performed from left to right for the picture taken on the left) to obtain the first sub-frame number (the number of characters contained in the first-character frame number is the first number), and text recognition can be performed on the second sub-captured image of the two sub-captured images in the opposite direction of the target direction (for example, text recognition is performed from right to left for the picture taken on the right) to obtain the second sub-frame number (the number of characters contained in the second-character frame number is the second number).

[0126] Optionally, for the double-row curved frame number, the two text lines in each sub-captured image may be respectively recognized from top to bottom to obtain two sub-frame numbers corresponding to each sub-captured image. Then, according to the order of the sub-frame numbers contained in the text lines of each sub-captured image in the frame number of the non-motor vehicle, the two sub-frame numbers corresponding to each sub-captured image are spliced ​​to obtain the frame number of the non-motor vehicle.

[0127] For example, Figure 4 As shown in the figure, for a double-line curved frame number, four text lines and corresponding contents will be obtained after text recognition. The detection frames of the left-side picture are Num1 and Num2 from top to bottom, and the detection frames of the right-side picture are Num3 and Num4 from top to bottom. Using the prior that the accuracy of the front digits in the left-side picture is better than that of the back digits and vice versa, the splicing formula can be obtained, as shown in formula (1):

[0128]

[0129] Among them, y t Indicates the tth digit of the 15-digit numbering result, Num3(-1) indicates the last digit in the Num3 result, Num3(1) indicates the first positive digit in the Num3 result, and the other digits and other results are similar. The physical meaning of the splicing method is that the first 4 digits of the output result are the first 4 digits of Num1, 5 to 7 digits are the last 3 digits of Num3, 8 to 11 digits are the first 4 digits of Num2, and 12 to 15 digits are the last 4 digits of Num4.

[0130] Through this embodiment, by performing text recognition on different photographed images of the target format in different ways, the accuracy of non-motor vehicle frame number recognition can be improved.

[0131] The following is an explanation of the vehicle frame number recognition method in the embodiment of the present application in conjunction with an optional example. In this optional example, the target terminal is a mobile phone.

[0132] For motor vehicles, a deep learning network can be customized based on the number of digits in the frame number to improve recognition accuracy. However, unlike the 17-digit VIN (Vehicle Identification Number) code of motor vehicles, the frame number of non-motor vehicles has a total of 15 digits, all digital, with specific coding rules, and no check digit. Therefore, the above method is applicable to motor vehicles but not non-motor vehicles, and cannot solve the problems of low contrast and difficulty in taking complete photos of the frame number of non-motor vehicles.

[0133] In addition, for motor vehicles, the reference marks around the frame number can be used to correct the original frame number image, improve the accuracy of frame number image generation, and thus improve the accuracy of frame number recognition. However, it is difficult to take a complete picture of the double-row curved frame number plate, so the above method cannot solve the problem that it is difficult to take a complete picture of non-motor vehicles. Therefore, the method for motor vehicle frame number recognition cannot solve the problem that the contrast of the columnar steel-printed text image of the non-motor vehicle frame number is too low, and the double-row curved frame number plate is difficult to take a complete picture.

[0134] In an optional example, a method for identifying a non-motor vehicle frame number is provided, which may include: image acquisition, text recognition, and splicing recognition results as needed. Figure 5 As shown in Figure 1, a shooting guidance module, a special acquisition mode adapted to double-row curved frame numbers, and an image quality assessment module are added to the image acquisition process. Figure 5 As shown, the picture collection process may include the following steps:

[0135] Step S502, start shooting using the mobile phone.

[0136] Step S504: guiding the picture taking by means of the taking guidance module.

[0137] Step S506, selecting a vehicle frame number format.

[0138] Relevant personnel can operate the mobile phone to select the frame number format, and can also automatically match the frame number format by recognizing the text in the guide frame. The frame number format can include: Format 1, that is, the format in which the text direction is parallel to the pole; Format 2, that is, the format in which the text direction is perpendicular to the pole.

[0139] Step S508, completing the picture shooting.

[0140] For layout 1, you can collect one picture. For layout 2, you can collect one picture on the left and one on the right, stitch the pictures together, and rename them with a special suffix.

[0141] Step S510, the picture quality assessment module performs a quality assessment on the collected picture to determine whether the picture quality meets the image recognition conditions. If so, execute step S512; otherwise, execute step S508 to re-shoot (or, execute step S506 to re-select the frame number format).

[0142] Step S512, output the picture.

[0143] For the collected images, text recognition can be performed. Text recognition can be performed by a text recognition module, which includes layout discrimination, text line detection, text correction, text line recognition and other modules. The text recognition process can be as follows: Figure 6 As shown, the process may include the following steps:

[0144] Step S602, reading in the picture, that is, reading the collected picture;

[0145] Step S604, layout determination, that is, determining whether the layout of the vehicle frame number is layout 1 or layout 2, and using different recognition methods to perform text recognition;

[0146] Step S606, text line detection;

[0147] Step S608, text line correction;

[0148] Step S610: text line recognition.

[0149] Through this optional example, in order to solve the problem that it is difficult to capture a complete double-row curved frame number, a solution is proposed to capture each side once, and corresponding adaptation is made during text recognition, so as to finally obtain a complete spliced ​​frame number recognition result; in order to solve the problem that the contrast of stamped text images is too low, a shooting guidance module and a quality assessment module are newly added. The shooting guidance module guides users to capture higher quality images, and the quality assessment module automatically judges the image contrast, clarity, frame number integrity, etc., to ensure the quality of the image sent to the recognition module.

[0150] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0152] According to another aspect of the embodiments of the present application, a vehicle frame number recognition device for implementing the above-mentioned vehicle frame number recognition method is also provided. Figure 7 is a structural block diagram of an optional vehicle frame number recognition device according to an embodiment of the present application, such as Figure 7 As shown, the device may include:

[0153] The first acquisition unit 702 is used to acquire an image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a first acquired image;

[0154] The first guiding unit 704 is used to send a first guiding message through the target terminal when the image quality of the first collected image does not meet the image recognition condition, wherein the first guiding message is used to guide the target terminal to re-collect the image of the frame number of the non-motor vehicle;

[0155] The second acquisition unit 706 is used to re-acquire the image of the frame number of the non-motor vehicle through the target terminal to obtain a second acquired image;

[0156] The recognition unit 708 is used to perform text recognition on the second collected image to obtain the frame number of the non-motor vehicle when the image quality of the second collected image meets the image recognition condition.

[0157] It should be noted that the first acquisition unit 702 in this embodiment can be used to execute the above step S202, the first guidance unit 704 in this embodiment can be used to execute the above step S204, the second acquisition unit 706 in this embodiment can be used to execute the above step S206, and the identification unit 708 in this embodiment can be used to execute the above step S208.

[0158] Through the above-mentioned module, the frame number of the non-motor vehicle is imaged through the target terminal to obtain a first captured image; when the image quality of the first captured image does not meet the image recognition conditions, the first guidance information is sent through the target terminal, wherein the first guidance information is used to guide the use of the target terminal to re-capture the image of the frame number of the non-motor vehicle; the frame number of the non-motor vehicle is imaged again through the target terminal to obtain a second captured image; when the image quality of the second captured image meets the image recognition conditions, text recognition is performed on the second captured image to obtain the frame number of the non-motor vehicle, which solves the problem of low efficiency of information recording in the method of manually recording the frame number of the non-motor vehicle in the related art, and improves the recording efficiency of the frame number of the non-motor vehicle.

[0159] In an exemplary embodiment, the above device further comprises:

[0160] The second guidance unit is used to capture the image of the frame number of the non-motor vehicle through the target terminal and before obtaining the first captured image, in response to a detected shooting trigger operation, send a second guidance message through the target terminal, wherein the second guidance message is used to guide the use of the target terminal to capture the image of the frame number of the non-motor vehicle.

[0161] In an exemplary embodiment, the above device further comprises:

[0162] An evaluation unit is used for, after acquiring an image of the vehicle frame number of the non-motor vehicle through the target terminal and obtaining a first acquired image, evaluating the first acquired image according to a target image attribute to obtain a target evaluation result of the first acquired image, wherein the target image attribute is used to characterize the image quality of the first acquired image;

[0163] The first determining unit is configured to determine, according to a target evaluation result, that the image quality of the first acquired image does not satisfy an image recognition condition.

[0164] In an exemplary embodiment, the first guiding unit 704 includes at least one of the following:

[0165] A prompt module, used for sending a horizontal screen prompt message through the target terminal when detecting that the target terminal is in a non-horizontal screen state, wherein the horizontal screen prompt message is used to prompt the use of the horizontal screen for image acquisition;

[0166] A display module is used to display a guide frame on the image acquisition interface of the target terminal, wherein the guide frame is used to guide at least one of the following: an image acquisition angle, a position of a non-motor vehicle frame number, a direction of a non-motor vehicle frame number, and the second acquired image is an image acquired by the target terminal and located in the guide frame.

[0167] In an exemplary embodiment, the identification unit 708 includes:

[0168] A detection module, configured to perform text line detection on the second acquired image to obtain text line vertices corresponding to a target text line in the second acquired image, wherein the target text line is located in a text line image having the text line vertices as vertices;

[0169] A transformation module, used for performing a transmission transformation on the text line image according to a target resolution to obtain a text line image after the transmission transformation;

[0170] The first recognition module is used to perform text line recognition on the text line image after the transmission transformation to obtain the frame number of the non-motor vehicle.

[0171] In an exemplary embodiment, the above device further comprises:

[0172] An instruction unit, used for sending format selection instruction information through the target terminal after sending the first guidance information through the target terminal, wherein the format selection instruction information is used to instruct to select a frame number format of a non-motor vehicle from multiple frame number formats;

[0173] The second determination unit is used to determine the frame number layout of the non-motor vehicle and the number of captured images corresponding to the frame number layout of the non-motor vehicle in response to the detected layout selection operation, wherein different frame number layouts among the multiple frame number layouts correspond to different numbers of captured images.

[0174] In an exemplary embodiment, the second acquisition unit 706 includes:

[0175] The acquisition module is used to re-acquire the frame number of the non-motor vehicle twice through the target terminal when the frame number format of the non-motor vehicle is the target format, so as to obtain two sub-acquired images, wherein the target format is a format in which the direction of the frame number of the non-motor vehicle is perpendicular to the direction of the pole of the non-motor vehicle, and the second acquired image includes two sub-acquired images, and the two sub-acquired images correspond to different shooting angles.

[0176] In an exemplary embodiment, the above device further comprises:

[0177] A stitching unit, used for performing image stitching on the two sub-captured images to obtain a stitched image after re-capturing the frame number of the non-motor vehicle twice through the target terminal to obtain two sub-captured images;

[0178] The splitting unit is used to split the spliced ​​image to obtain two sub-collected images before performing text recognition on the second collected image to obtain the frame number of the non-motor vehicle.

[0179] In an exemplary embodiment, the identification unit 708 includes:

[0180] A second recognition module is used to perform text recognition on a first sub-collected image of the two sub-collected images according to a target direction to obtain a first sub-frame number;

[0181] A third recognition module is used to perform text recognition on the second sub-collected image of the two sub-collected images in the opposite direction of the target direction to obtain a second sub-frame number;

[0182] The splicing module is used to splice the first sub-frame number and the second sub-frame number to obtain the frame number of the non-motor vehicle.

[0183] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0184] According to another aspect of the embodiment of the present application, a storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned vehicle frame number recognition methods in the embodiment of the present application.

[0185] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0186] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0187] S1, collecting images of the vehicle frame number of the non-motor vehicle through a target terminal to obtain a first collected image;

[0188] S2, when the image quality of the first collected image does not meet the image recognition condition, sending a first guidance message through the target terminal, wherein the first guidance message is used to guide the target terminal to re-collect the image of the frame number of the non-motor vehicle;

[0189] S3, re-capturing the image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a second captured image;

[0190] S4, when the image quality of the second collected image meets the image recognition condition, perform text recognition on the second collected image to obtain the frame number of the non-motor vehicle.

[0191] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0192] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0193] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned vehicle frame number recognition method is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0194] Figure 8 is a structural block diagram of an optional electronic device according to an embodiment of the present application, such as Figure 8 As shown, it includes a processor 802, a communication interface 804, a memory 806 and a communication bus 808, wherein the processor 802, the communication interface 804 and the memory 806 communicate with each other through the communication bus 808, wherein,

[0195] Memory 806, used for storing computer programs;

[0196] The processor 802 is used to implement the following steps when executing the computer program stored in the memory 806:

[0197] S1, collecting images of the vehicle frame number of the non-motor vehicle through a target terminal to obtain a first collected image;

[0198] S2, when the image quality of the first collected image does not meet the image recognition condition, sending a first guidance message through the target terminal, wherein the first guidance message is used to guide the target terminal to re-collect the image of the frame number of the non-motor vehicle;

[0199] S3, re-capturing the image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a second captured image;

[0200] S4, when the image quality of the second collected image meets the image recognition condition, perform text recognition on the second collected image to obtain the frame number of the non-motor vehicle.

[0201] Optionally, in this embodiment, the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The communication interface is used for communication between the electronic device and other devices.

[0202] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the processor.

[0203] As an example, the memory 806 may include, but is not limited to, the first acquisition unit 702, the first guidance unit 704, the second acquisition unit 706, and the recognition unit 708 in the vehicle frame number recognition device. In addition, it may also include, but is not limited to, other module units in the vehicle frame number recognition device, which will not be repeated in this example.

[0204] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0205] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0206] It can be understood by those skilled in the art that Figure 8 The structure shown is for illustration only. The device for implementing the above-mentioned vehicle frame number recognition method may be a terminal device, which may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 8 The structure of the electronic device is not limited. Figure 8 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 8 Different configurations shown.

[0207] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0208] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0209] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0210] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0211] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0212] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0213] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0214] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for identifying a vehicle frame number, characterized in that: include: Capturing the image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a first captured image; When the image quality of the first collected image does not meet the image recognition condition, a first guidance message is sent through the target terminal, wherein the first guidance message is used to guide the target terminal to re-collect the image of the frame number of the non-motor vehicle; Re-capturing the image of the vehicle frame number of the non-motor vehicle by the target terminal to obtain a second captured image; When the image quality of the second collected image meets the image recognition condition, performing text recognition on the second collected image to obtain the vehicle frame number of the non-motor vehicle; Wherein, after the first guidance information is sent through the target terminal, the method further includes: sending format selection indication information through the target terminal, wherein the format selection indication information is used to indicate the selection of the frame number format of the non-motor vehicle from multiple frame number formats; in response to the detected format selection operation, determining the frame number format of the non-motor vehicle and the number of captured images corresponding to the frame number format of the non-motor vehicle, wherein different frame number formats among the multiple frame number formats correspond to different numbers of captured images.

2. The method according to claim 1, characterized in that Before acquiring the first acquired image by performing image acquisition of the vehicle frame number of the non-motor vehicle through the target terminal, the method further includes: In response to the detected shooting trigger operation, second guidance information is sent through the target terminal, wherein the second guidance information is used to guide the use of the target terminal to capture an image of the frame number of the non-motor vehicle.

3. The method according to claim 1, characterized in that After the target terminal performs image acquisition of the vehicle frame number of the non-motor vehicle to obtain the first acquired image, the method further includes: Evaluate the first acquired image according to a target image attribute to obtain a target evaluation result of the first acquired image, wherein the target image attribute is used to characterize the image quality of the first acquired image; According to the target evaluation result, it is determined that the image quality of the first acquired image does not meet the image recognition condition.

4. The method according to claim 1, characterized in that: Sending the first guidance information by the target terminal includes at least one of the following: When it is detected that the target terminal is in a non-landscape state, a landscape prompt message is sent through the target terminal, wherein the landscape prompt message is used to prompt the user to use the landscape screen for image acquisition; A guide frame is displayed on the image acquisition interface of the target terminal, wherein the guide frame is used to guide at least one of the following: an acquisition angle of the image, a position of the frame number of the non-motor vehicle, and a direction of the frame number of the non-motor vehicle, and the second acquired image is an image acquired by the target terminal and located in the guide frame.

5. The method according to any one of claims 1 to 4, characterized in that Performing text recognition on the second collected image to obtain the vehicle frame number of the non-motor vehicle includes: Performing text line detection on the second acquired image to obtain text line vertices corresponding to a target text line in the second acquired image, wherein the target text line is located in a text line image having the text line vertices as vertices; Performing a transmission transformation on the text line image according to a target resolution to obtain the text line image after the transmission transformation; The text line image after the transmission transformation is subjected to text line recognition to obtain the frame number of the non-motor vehicle.

6. The method according to claim 1, characterized in that Re-capturing the image of the vehicle frame number of the non-motor vehicle by the target terminal to obtain the second captured image includes: When the frame number format of the non-motor vehicle is the target format, the frame number of the non-motor vehicle is re-imaged twice by the target terminal to obtain two sub-captured images, wherein the target format is a format in which the direction of the frame number of the non-motor vehicle is perpendicular to the direction of the pole of the non-motor vehicle, and the second captured image includes the two sub-captured images, and the two sub-captured images correspond to different shooting angles.

7. The method according to claim 6, characterized in that After the target terminal re-captures the vehicle frame number of the non-motor vehicle twice to obtain the two sub-captured images, the method further includes: stitching the two sub-captured images to obtain a stitched image; Before performing text recognition on the second collected image to obtain the frame number of the non-motor vehicle, the method further includes: performing image splitting on the spliced ​​image to obtain the two sub-collected images.

8. The method according to claim 6, characterized in that Performing text recognition on the second collected image to obtain the vehicle frame number of the non-motor vehicle includes: Performing text recognition on a first sub-collected image of the two sub-collected images according to a target direction to obtain a first sub-frame number; Performing text recognition on a second sub-collected image of the two sub-collected images in a direction opposite to the target direction to obtain a second sub-frame number; The first sub-frame number and the second sub-frame number are concatenated to obtain the frame number of the non-motor vehicle.

9. A vehicle frame number recognition device, characterized in that: include: A first acquisition unit is used to acquire an image of the vehicle frame number of the non-motor vehicle through a target terminal to obtain a first acquired image; A first guiding unit, configured to send a first guiding message through the target terminal when the image quality of the first collected image does not meet the image recognition condition, wherein the first guiding message is used to guide the target terminal to re-collect the image of the vehicle frame number of the non-motor vehicle; A second acquisition unit is used to re-acquire an image of the vehicle frame number of the non-motor vehicle through the target terminal to obtain a second acquired image; a recognition unit, configured to perform text recognition on the second collected image to obtain the vehicle frame number of the non-motor vehicle when the image quality of the second collected image meets the image recognition condition; The device further includes: an indication unit for sending a format selection indication information through the target terminal after the first guidance information is sent through the target terminal, wherein the format selection indication information is used to indicate the selection of the frame number format of the non-motor vehicle from multiple frame number formats; a second determination unit for determining the frame number format of the non-motor vehicle and the number of acquired images corresponding to the frame number format of the non-motor vehicle in response to a detected format selection operation, wherein different frame number formats among the multiple frame number formats correspond to different numbers of acquired images.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 8 when executed.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 8 through the computer program.

Citation Information

Patent Citations

  • A target object recommendation method and a mobile terminal

    CN109740493A

  • Method and device for recognizing characters in claim settlement receipts online and client side

    CN111291619A