CN111160342A - Vehicle reflective mark verification method and device, computer equipment and storage medium - Google Patents
Vehicle reflective mark verification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111160342A CN111160342A CN201911400237.8A CN201911400237A CN111160342A CN 111160342 A CN111160342 A CN 111160342A CN 201911400237 A CN201911400237 A CN 201911400237A CN 111160342 A CN111160342 A CN 111160342A
- Authority
- CN
- China
- Prior art keywords
- target image
- vehicle
- detection result
- text information
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012795 verification Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 claims abstract description 285
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 11
- 238000007689 inspection Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 239000003550 marker Substances 0.000 description 10
- 230000000694 effects Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method and a device for verifying a vehicle reflective mark, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark; verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark; inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not; and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result. The method improves the efficiency of verifying the detection result of the vehicle reflective mark displayed by the target image, and improves the accuracy of the verification result obtained by verifying the detection result of the vehicle reflective mark displayed by the target image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for verifying a vehicle reflective mark, computer equipment and a storage medium.
Background
Annual inspection of motor vehicles is of great importance for safe driving of motor vehicles. With the rapid development of social economy, the holding capacity of motor vehicles is continuously increased, so that the annual inspection workload of the motor vehicles is increased.
When the motor vehicle is annual inspected, the detection result of the motor vehicle reflective mark needs to be identified, and the identification of the detection result of the motor vehicle reflective mark is an important detection in the detection of the motor vehicle annual inspection. In the traditional technology, the method for identifying the detection result of the motor vehicle reflective mark is mainly carried out in a manual mode.
However, the traditional method for identifying the detection result of the reflecting mark of the motor vehicle has the problem of low identification efficiency.
Disclosure of Invention
Based on this, it is necessary to provide a method and an apparatus for verifying a vehicle reflective marker, a computer device, and a storage medium, for solving the problem of low recognition efficiency of the conventional method for recognizing the detection result of the vehicle reflective marker.
In a first aspect, an embodiment of the present invention provides a method for verifying a vehicle reflective identifier, where the method includes:
acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark;
verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
In one embodiment, the verifying the text information in the target image to obtain a verification result of the text information includes:
inputting the target image into a preset text detection model to obtain text information corresponding to the target image;
inputting the text information into a preset text recognition model, and recognizing character information and character information in the target image;
and checking the character information and the character information to obtain a checking result of the text information.
In one embodiment, the verifying the text information and the character information to obtain a verification result of the text information includes:
detecting whether the text information comprises a preset target field, if so, marking a verification result of the text information as a first value;
extracting a license plate number character string from the character information, judging whether the license plate number character string is consistent with a preset license plate number character string or not, and if so, marking a verification result of the license plate number as the first value;
extracting a light reflecting identification detection result numerical value from the character information, judging whether the light reflecting identification detection result numerical value has a repeated numerical value, and if not, marking a verification result of the light reflecting identification detection result numerical value as the first value;
and if the verification result of the text information, the verification result of the license plate number and the verification result of the numerical value of the light-reflecting identification detection result are the first values, determining that the verification result of the text information is a pass.
In one embodiment, the inputting the target image into a preset vehicle detection model to obtain a detection result of the target image includes:
intercepting the target image according to a preset sliding direction by adopting a window with a preset size to obtain a subimage of the target image; the preset size is determined according to the length of the text message;
inputting the subimages into the vehicle detection model to obtain the detection results of the subimages;
and if the detection result of the sub-image comprises the vehicle picture, determining that the detection result of the target image comprises the vehicle picture.
In one embodiment, the verifying the detection result of the vehicle reflective mark shown in the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result includes:
and if the test result of the text message is passed and the detection result of the target image comprises the vehicle photo, determining that the verification result of the detection result of the vehicle reflective mark displayed on the target image is passed.
In one embodiment, the vehicle detection model is a single-lens multi-box detection model; the single-lens multi-box detection model comprises a multi-hole convolution layer, the number of network layers of the single-lens multi-box detection model is smaller than a preset threshold value, and the number of default target frames on each layer of feature map of the single-lens multi-box detection model is the same.
In one embodiment, the training process of the vehicle detection model includes:
acquiring sample images obtained under different acquisition conditions; the sample image is a vehicle reflective mark detection result image;
marking the vehicle photos in the sample image by adopting a rectangular frame to obtain a marked image corresponding to the sample image;
inputting the sample image into a preset initial vehicle detection model to obtain a sample detection result;
and training the initial vehicle detection model according to the sample detection result and the labeled image to obtain the vehicle detection model.
In a second aspect, an embodiment of the present invention provides an apparatus for verifying a reflective sign of a vehicle, where the apparatus includes:
the first acquisition module is used for acquiring a target image to be detected; the target image shows the detection result of the reflective mark of the vehicle;
the second acquisition module is used for verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
the third acquisition module is used for inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and the verification module is used for verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the following steps when executing the computer program:
acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark;
verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following steps:
acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark;
verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
In the verification method and device of the vehicle reflective mark, the computer device and the storage medium provided by the embodiment, the computer device obtains a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark; verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark; inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not; and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result. In the method, the computer equipment checks the text information at least comprising the vehicle reflecting identification in the target image to obtain the checking result of the text information, inputs the target image into a preset vehicle detection model to obtain the detection result of whether the target image comprises the target image of the vehicle photo, and can quickly verify the detection result of the vehicle reflecting identification displayed by the target image according to the checking result of the text information and the detection result of the target image, so that the efficiency of verifying the detection result of the vehicle reflecting identification displayed by the target image is improved; in addition, the target image is input into the preset vehicle detection model, whether the target image comprises the vehicle photo or not can be accurately detected, the accuracy of the obtained detection result of the target image is improved, the detection result of the vehicle reflective mark displayed by the target image can be accurately verified according to the verification result of the text information and the detection result of the target image, and the accuracy of the verification result of the detection result of the vehicle reflective mark displayed by the target image is improved.
Drawings
FIG. 1 is a schematic diagram of an internal structure of a computer device according to an embodiment;
FIG. 2 is a schematic flow chart of a method for verifying a reflective sign of a vehicle according to an embodiment;
FIG. 3 is a schematic flow chart illustrating a method for verifying a reflective sign of a vehicle according to another embodiment;
FIG. 4 is a schematic flow chart illustrating a method for verifying a reflective sign of a vehicle according to another embodiment;
FIG. 5 is a schematic flow chart illustrating a method for verifying a reflective sign of a vehicle according to another embodiment;
fig. 6 is a schematic structural diagram of a vehicle reflective sign verification device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The verification method for the vehicle reflective mark provided by the embodiment of the application can be applied to computer equipment shown in fig. 1. The computer device comprises a processor and a memory connected by a system bus, wherein a computer program is stored in the memory, and the steps of the method embodiments described below can be executed when the processor executes the computer program. Optionally, the computer device may further comprise a network interface, a display screen and an input device. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a nonvolatile storage medium storing an operating system and a computer program, and an internal memory. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. Optionally, the computer device may be a server, a personal computer, a personal digital assistant, other terminal devices such as a tablet computer, a mobile phone, and the like, or a cloud or a remote server, and the specific form of the computer device is not limited in the embodiment of the present application.
It should be noted that, in the verification method for the vehicle reflective marker provided in the embodiment of the present application, an execution subject may be a verification apparatus for the vehicle reflective marker, and the verification apparatus for the vehicle reflective marker may be implemented as part or all of a computer device in a software, hardware, or a combination of software and hardware. In the following method embodiments, the execution subject is a computer device as an example.
The following describes the technical solution of the present invention and how to solve the above technical problems with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a schematic flow chart of a method for verifying a reflective sign of a vehicle according to an embodiment. The embodiment relates to a specific implementation process of verifying a detection result of a vehicle reflective mark displayed by a target image by computer equipment according to a verification result of text information of the target image and the detection result of the target image to obtain a verification result. As shown in fig. 2, the method may include:
s201, acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark.
Specifically, the computer equipment acquires a target image to be detected, wherein the target image is used for displaying a detection result of the vehicle reflective mark. Optionally, the computer device may acquire the target image to be detected from a server storing the detection result image of the vehicle reflective marker, or may acquire the target image to be detected in real time through a shooting device connected to the computer device.
S202, verifying the text information in the target image to obtain a verification result of the text information; the text message includes at least a vehicle reflective logo.
Specifically, the computer device checks the text information in the target image to obtain a check result of the text information in the target image. The text information in the target image at least comprises a vehicle reflective mark. Optionally, the computer device may extract the text information in the target image by using the text detection model, and then check the extracted text information to obtain a check result of the text information of the target image.
S203, inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises the vehicle photo.
Specifically, the computer device inputs the target image into a preset vehicle detection model to obtain a detection result of the target image, and the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not. Optionally, the detection result of the target image obtained by the computer device may be that the vehicle photograph is included, or may not be included.
And S204, verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
Specifically, the computer device verifies the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information of the target image and the detection result of the target image to obtain a verification result. Optionally, the verification result obtained by the computer device may be verification passed or verification failed. Further, if the verification result obtained by the computer device is that the verification fails, optionally, the reason for the failure of the verification may be that the verification result of the text information fails, or that the detection result of the target image fails.
In this embodiment, the computer device verifies the text information at least including the vehicle reflective mark in the target image to obtain a verification result of the text information, inputs the target image into a preset vehicle detection model to obtain a detection result of whether the target image includes the target image of the vehicle photo, and can quickly verify the detection result of the vehicle reflective mark displayed in the target image according to the verification result of the text information and the detection result of the target image, so that the efficiency of verifying the detection result of the vehicle reflective mark displayed in the target image is improved; in addition, the target image is input into the preset vehicle detection model, whether the target image comprises the vehicle picture or not can be accurately detected, the accuracy of the obtained detection result of the target image is improved, the detection result of the vehicle reflective mark displayed by the target image can be accurately verified according to the verification result of the text information and the detection result of the target image, and the accuracy of the verification result obtained by verifying the detection result of the vehicle reflective mark displayed by the target image is improved.
Fig. 3 is a schematic flow chart of a method for verifying a reflective sign of a vehicle according to another embodiment. The embodiment relates to a specific implementation process of verifying text information in a target image by computer equipment to obtain a verification result of the text information. As shown in fig. 3, on the basis of the foregoing embodiment, as an optional implementation manner, the foregoing S202 includes:
s301, inputting the target image into a preset text detection model to obtain text information corresponding to the target image.
Specifically, the computer device inputs the target image into a preset text detection model to obtain text information corresponding to the target image. Optionally, the text information corresponding to the target image obtained by the computer device may include a vehicle reflective identification field, a license plate number, a reflective identification detection result value, and a vehicle photo field. Optionally, before the computer device inputs the target image into the preset text detection model, a text correction method based on deep learning may be applied to the obtained target image to be detected, the target image is rotationally corrected according to the text direction in the image to obtain a rotated image, and the rotated image is input into the preset text detection model.
S302, inputting the text information into a preset text recognition model, and recognizing the character information and the character information in the target image.
Specifically, the computer device inputs text information corresponding to the target image into a preset text recognition model, and recognizes character information and character information in the target image. The character information is a field composed of characters, and the character information is a character string composed of numerical values and symbols. For example, the text information in the recognized target image may be a reflective mark or a photo; the character information in the recognized target image may be C02561 or 1384. It will be appreciated that the training process for the text recognition model may be the process described below: the computer equipment can obtain a plurality of sample images comprising character information and character information, label the character information and the character information in the sample images in advance, input the sample images into a preset initial text recognition model to obtain recognition results of the character information and the character information in the sample images, compare the obtained recognition results of the character information and the character information with labels of the character information and the character information in the sample images in advance to obtain a loss function value of the initial text recognition model, and train the initial text recognition model according to the loss function value of the initial text recognition model to obtain the text recognition model.
And S303, checking the character information and the character information to obtain a checking result of the text information.
Specifically, the computer device checks the character information and the character information in the identified target image to obtain a check result of the text information corresponding to the target image. Optionally, the computer device may detect whether the text information in the target image includes a preset target field, and if so, mark the verification result of the text information as a first value, where the target field is a reflective identifier; extracting a license plate number character string from the character information, judging whether the extracted license plate number character string is consistent with a preset license plate number character string or not, and if so, marking a verification result of the license plate number as a first value; extracting a light reflecting identification detection result numerical value from the character information, judging whether the light reflecting identification detection result numerical value has a repeated numerical value, and if not, marking a verification result of the light reflecting identification detection result numerical value as a first value; and if the verification result of the character information, the verification result of the license plate number and the verification result of the numerical value of the reflective identification detection result are all first values, the computer equipment determines that the verification result of the text information corresponding to the target image is a pass. It should be noted that the preset license plate number character string is a license plate number character string corresponding to a detection result of the vehicle reflective mark displayed on the target image. It is understood that the license plate number character string is a character string composed of letters and numbers; the numerical value of the detection result of the reflective marker is a group of numerical values stored in sequence.
In this embodiment, the computer device inputs the target image into the preset text detection model, and can accurately detect the text information in the target image, so as to improve the accuracy of the obtained text information corresponding to the target image, and the text information and the character information in the target image are obtained by inputting the text information corresponding to the target image into the preset text recognition model for recognition, so that the accuracy of the recognized text information and the character information in the target image is also improved, and further, the accuracy of the verification result of the text information obtained by verifying the text information and the character information in the target image is improved.
Fig. 4 is a flowchart illustrating a method for verifying a reflective sign of a vehicle according to another embodiment. The embodiment relates to a specific implementation process of inputting a target image into a preset vehicle detection model by computer equipment to obtain a detection result of a vehicle photo in the target image. As shown in fig. 4, on the basis of the foregoing embodiment, as an optional implementation manner, the foregoing S203 includes:
s401, intercepting a target image according to a preset sliding direction by adopting a window with a preset size to obtain a sub-image of the target image; the preset size is determined according to the length of the text message.
Specifically, the computer device intercepts the target image according to a preset sliding direction by using a window with a preset size, and acquires a sub-image of the target image. The preset size is determined according to the length of the character information in the target image. For example, the computer device may obtain the preset size of the window according to the distance between the leftmost text information and the rightmost text information in the target image, and optionally, the computer device may determine one third of the distance between the leftmost text information and the rightmost text information in the target image as the preset size of the window. Optionally, the computer device may intercept the target image according to the sliding directions from left to right and from top to bottom on the target image according to the set horizontal interval and vertical interval, so as to obtain the sub-image of the target image. Alternatively, the computer device may acquire all sub-images of the target image, or may acquire only a portion of the sub-images of the target image.
S402, inputting the sub-image into the vehicle detection model to obtain the detection result of the sub-image.
Specifically, the computer device inputs the obtained sub-image of the target image into the vehicle detection model to obtain the detection result of the sub-image of the target image. Optionally, the detection result of the sub-image may include the vehicle photograph or may not include the vehicle photograph. Alternatively, the computer device may input the sub-images of the target image into the vehicle detection model in the order of the sub-images acquired.
And S403, if the detection result of the sub-image comprises the vehicle picture, determining that the detection result of the target image comprises the vehicle picture.
Specifically, if the detection result of the sub-image includes a vehicle photograph, the computer device determines that the detection result of the target image includes the vehicle photograph. Illustratively, assuming that the computer device obtains 50 sub-images of the target image, and the 10 th sub-image is input into the vehicle detection model, and the obtained detection result is that the vehicle picture is included, the computer device determines that the detection result of the target image includes the vehicle picture.
In this embodiment, the computer device intercepts the target according to the preset sliding direction by using the window with the preset size, obtains the sub-image of the target image, and inputs the sub-image into the vehicle detection model, and because the sub-image has a small size and contains more information, the vehicle detection model can accurately detect the sub-image of the target image, so that the accuracy of the obtained detection result of the sub-image is improved, and the accuracy of the detection result of the target image determined according to the detection result of the sub-image of the target image is further improved.
On the basis of the foregoing embodiment, as an optional implementation manner, the foregoing S204 includes: and if the test result of the text information is passed and the detection result of the target image comprises the vehicle photo, determining that the verification result of the detection result of the vehicle reflective mark displayed on the target image is passed.
Specifically, if the verification result of the text information corresponding to the target image is that the text information passes and the detection result of the target image includes the vehicle photo, the computer device determines that the verification result of the detection result of the vehicle reflective mark displayed on the target image passes. That is, if the computer device detects that the text information corresponding to the target image includes the reflective identifier, the number character string in the text information is consistent with the preset number character string, no repeated numerical value exists in the detection result numerical value of the reflective identifier, and the detection result of the target image includes the vehicle photo, the computer device determines that the verification result of the detection result of the reflective identifier of the vehicle displayed on the target image is passed. Optionally, if the computer device determines that the verification result of the detection result of the vehicle reflective mark displayed on the target image is not passed, the computer device may return a reason why the verification result of the detection result of the vehicle reflective mark displayed on the target image is not passed. Optionally, the reason why the verification result of the detection result of the vehicle reflective mark displayed on the target image returned by the computer device fails may be that the verification result of the text information corresponding to the target image fails, or that the detection result of the target image does not include a vehicle photo, further, the verification result of the text information corresponding to the target image fails, or that the text information in the target image does not include a preset target field, or that a license plate number character string in the character information in the target image is not consistent with a preset vehicle number character string, or that there is a repeated numerical value in the reflective mark detection result numerical value in the character information in the target image.
In this embodiment, if the test result of the text message is a pass and the detection result of the target image includes a vehicle photo, it is determined that the verification result of the detection result of the vehicle reflective mark shown in the target image is a pass, and the computer device can accurately obtain the verification result of the detection result of the vehicle reflective mark shown in the target image through the process, thereby improving the accuracy of the obtained verification result of the detection result of the vehicle reflective mark shown in the target image.
On the basis of the above embodiment, as an optional implementation manner, the vehicle detection model is a single-lens multi-box detection model; the single-lens multi-box detection model comprises a multi-hole convolution layer, the number of network layers of the single-lens multi-box detection model is smaller than a preset threshold value, and the number of default target frames on each layer of feature map of the single-lens multi-box detection model is the same.
Specifically, the vehicle detection model is a Single Shot multi-box detection (SSD) model. The single-lens multi-box detection model comprises a multi-hole convolution layer, the number of network layers of the single-lens multi-box detection model is smaller than a preset threshold value, and the number of default target frames on each layer of feature map of the single-lens multi-box detection model is the same. Optionally, the preset threshold may be 16, and the default number of target frames may be 6. For example, the single-lens multi-box inspection model may be a model that includes a multi-aperture convolutional layer, has a layer 13 network, and has a default number of target boxes of 6 on each layer of the feature map. Optionally, when the single-lens multi-box detection model is a 13-layer network, the network structure of the single-lens multi-box detection model may be that two full-connected layers fc6 and fc7 in the standard single-lens multi-box detection model are changed into two 19 × 19 convolutional layers, and then the two convolutional layers are connected with 4 convolutional layers, then the two convolutional layers are connected with the full-connected layers, and finally the target classification detection output layer is formed.
In this embodiment, the vehicle detection model is a single-lens multi-box detection model, a multi-aperture convolution layer included in the single-lens multi-box detection model can expand the receptive field of a convolution network by using multi-aperture convolution, and high-level semantic information features with low resolution are extracted, so that the learning capability of the network on small-target detail features is improved, and the probability of detecting a vehicle photo can be increased by setting the number of default target frames on each layer of feature map of the single-lens multi-box detection model to be the same value; in addition, the number of network layers of the single-lens multi-box detection model is smaller than a preset threshold value, so that network parameters can be reduced, and the detection efficiency of the single-lens multi-box detection model on the vehicle photos is improved.
Fig. 5 is a flowchart illustrating a method for verifying a reflective sign of a vehicle according to another embodiment. The embodiment relates to a specific implementation process for training a vehicle detection model by computer equipment. As shown in fig. 5, the training process of the vehicle detection model may include:
s501, obtaining sample images obtained under different acquisition conditions; the sample image is a vehicle reflective mark detection result image.
Specifically, the computer equipment acquires sample images obtained under different acquisition conditions, wherein the sample images are vehicle reflective mark detection result images. Alternatively, the different acquisition conditions may include different illumination and different angles. Optionally, the sample image may be an image of different size, or may be an image of a detection result of a reflective marker of different vehicle types, for example, an image of a detection result of a reflective marker of a large truck, an image of a detection result of a reflective marker of a van.
And S502, marking the vehicle photos in the sample image by adopting a rectangular frame to obtain a marked image corresponding to the sample image.
Specifically, the computer device labels the vehicle photos in the sample image by using a rectangular frame to obtain a labeled image corresponding to the sample image. Optionally, the computer device may label the vehicle photos in the sample image by using a rectangular frame with a size larger than that of the vehicle photos in the sample image, or label the vehicle photos in the sample image by using a circumscribed rectangle of the license plate photos in the sample image.
And S503, inputting the sample image into a preset initial vehicle detection model to obtain a sample detection result.
Specifically, the computer device inputs the sample image into a preset initial vehicle detection model to obtain a sample detection result. Optionally, the obtained sample detection result may be an image marked with a vehicle photo, or an image not marked with a vehicle photo, and it can be understood that if the obtained sample detection result is an image marked with a vehicle photo, it indicates that the corresponding sample image includes the vehicle photo; if the obtained sample detection result is an image without the marked vehicle picture, the corresponding sample image does not include the vehicle picture.
S504, training the initial vehicle detection model according to the sample detection result and the labeled image to obtain the vehicle detection model.
Specifically, the computer device obtains a loss function value of the initial vehicle detection model according to the sample detection result and the labeled image corresponding to the sample image, and trains the initial vehicle detection model according to the loss function value of the initial vehicle detection model to obtain the vehicle detection model.
In this embodiment, the computer device acquires sample images of vehicle reflective identification detection results obtained under different acquisition conditions, marks vehicle photos in the sample images by using a rectangular frame to obtain marked images corresponding to the sample images, inputs the sample images into a preset initial vehicle detection model to obtain sample detection results, trains the initial vehicle detection model according to the sample detection results and the marked images, and can train the initial vehicle detection model more accurately through a large number of sample images, thereby improving the accuracy of the obtained vehicle detection model.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
Fig. 6 is a schematic structural diagram of a vehicle reflective sign verification device according to an embodiment. As shown in fig. 6, the apparatus may include: a first obtaining module 10, a second obtaining module 11, a third obtaining module 12 and a verification module 13.
Specifically, the first obtaining module 10 is configured to obtain a target image to be detected; the target image shows the detection result of the reflective mark of the vehicle;
the second obtaining module 11 is configured to verify the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
the third obtaining module 12 is configured to input the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and the verification module 13 is configured to verify the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image, so as to obtain a verification result.
Optionally, the vehicle detection model is a single-lens multi-box detection model; the single-lens multi-box detection model comprises a multi-hole convolution layer, the number of network layers of the single-lens multi-box detection model is smaller than a preset threshold value, and the number of default target frames on each layer of feature map of the single-lens multi-box detection model is the same.
The verification device for the vehicle reflective mark provided by the embodiment can execute the method embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
On the basis of the foregoing embodiment, optionally, the second obtaining module 11 includes: the device comprises a first acquisition unit, a recognition unit and a second acquisition unit.
Specifically, the first obtaining unit is configured to input a target image into a preset text detection model to obtain text information corresponding to the target image;
the recognition unit is used for inputting the text information into a preset text recognition model and recognizing the character information and the character information in the target image;
and the second acquisition unit is used for verifying the character information and the character information to obtain a verification result of the text information.
The verification device for the vehicle reflective mark provided by the embodiment can execute the method embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
On the basis of the foregoing embodiment, optionally, the second obtaining unit is specifically configured to detect whether the text information includes a preset target field, and if so, mark a verification result of the text information as a first value; extracting a license plate number character string from the character information, judging whether the license plate number character string is consistent with a preset license plate number character string or not, and if so, marking a verification result of the license plate number as a first value; extracting a light reflecting identification detection result numerical value from the character information, judging whether the light reflecting identification detection result numerical value has a repeated numerical value, and if not, marking a verification result of the light reflecting identification detection result numerical value as a first value; and if the verification result of the text information, the verification result of the license plate number and the verification result of the numerical value of the reflective identification detection result are all first values, determining that the verification result of the text information is a pass.
The verification device for the vehicle reflective mark provided by the embodiment can execute the method embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
On the basis of the foregoing embodiment, optionally, the third obtaining module 12 includes: a third acquisition unit, a fourth acquisition unit, and a determination unit.
Specifically, the third obtaining unit is configured to intercept the target image according to a preset sliding direction by using a window with a preset size, and obtain a sub-image of the target image; the preset size is determined according to the length of the text information;
the fourth acquisition unit is used for inputting the subimages into the vehicle detection model to obtain the detection results of the subimages;
and the determining unit is used for determining that the detection result of the target image comprises the vehicle picture if the detection result of the sub-image comprises the vehicle picture.
The verification device for the vehicle reflective mark provided by the embodiment can execute the method embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
On the basis of the foregoing embodiment, optionally, the verification module 13 includes: and an authentication unit.
Specifically, the verification unit is configured to determine that the verification result of the detection result of the vehicle reflective mark displayed on the target image is passed if the verification result of the text information is passed and the detection result of the target image includes a vehicle photo.
The verification device for the vehicle reflective mark provided by the embodiment can execute the method embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
On the basis of the foregoing embodiment, optionally, the apparatus further includes: the device comprises a fourth acquisition module, a labeling module, a fifth acquisition module and a training module.
Specifically, the fourth acquiring module is used for acquiring sample images obtained under different acquisition conditions; the sample image is a vehicle reflective mark detection result image;
the marking module is used for marking the vehicle photos in the sample image by adopting a rectangular frame to obtain a marked image corresponding to the sample image;
the fifth acquisition module is used for inputting the sample image into a preset initial vehicle detection model to obtain a sample detection result;
and the training module is used for training the initial vehicle detection model according to the sample detection result and the labeled image to obtain the vehicle detection model.
The verification device for the vehicle reflective mark provided by the embodiment can execute the method embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
For specific definition of the vehicle reflective mark verification device, reference may be made to the above definition of the vehicle reflective mark verification method, and details are not repeated here. The modules in the vehicle reflecting sign verification device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark;
verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark;
verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of validating a vehicle retroreflective sign, the method comprising:
acquiring a target image to be detected; the target image is used for displaying the detection result of the vehicle reflective mark;
verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
2. The method according to claim 1, wherein the verifying the text information in the target image to obtain a verification result of the text information comprises:
inputting the target image into a preset text detection model to obtain text information corresponding to the target image;
inputting the text information into a preset text recognition model, and recognizing character information and character information in the target image;
and checking the character information and the character information to obtain a checking result of the text information.
3. The method of claim 2, wherein the verifying the text information and the character information to obtain a verification result of the text information comprises:
detecting whether the text information comprises a preset target field, if so, marking a verification result of the text information as a first value;
extracting a license plate number character string from the character information, judging whether the license plate number character string is consistent with a preset license plate number character string or not, and if so, marking a verification result of the license plate number as the first value;
extracting a light reflecting identification detection result numerical value from the character information, judging whether the light reflecting identification detection result numerical value has a repeated numerical value, and if not, marking a verification result of the light reflecting identification detection result numerical value as the first value;
and if the verification result of the text information, the verification result of the license plate number and the verification result of the numerical value of the light-reflecting identification detection result are the first values, determining that the verification result of the text information is a pass.
4. The method according to claim 3, wherein the inputting the target image into a preset vehicle detection model to obtain the detection result of the target image comprises:
intercepting the target image according to a preset sliding direction by adopting a window with a preset size to obtain a subimage of the target image; the preset size is determined according to the length of the text message;
inputting the subimages into the vehicle detection model to obtain the detection results of the subimages;
and if the detection result of the sub-image comprises the vehicle picture, determining that the detection result of the target image comprises the vehicle picture.
5. The method according to claim 4, wherein the verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result comprises:
and if the test result of the text message is passed and the detection result of the target image comprises the vehicle photo, determining that the verification result of the detection result of the vehicle reflective mark displayed on the target image is passed.
6. The method of claim 1, wherein the vehicle inspection model is a single lens multi-box inspection model; the single-lens multi-box detection model comprises a multi-hole convolution layer, the number of network layers of the single-lens multi-box detection model is smaller than a preset threshold value, and the number of default target frames on each layer of feature map of the single-lens multi-box detection model is the same.
7. The method of claim 6, wherein the training process of the vehicle detection model comprises:
acquiring sample images obtained under different acquisition conditions; the sample image is a vehicle reflective mark detection result image;
marking the vehicle photos in the sample image by adopting a rectangular frame to obtain a marked image corresponding to the sample image;
inputting the sample image into a preset initial vehicle detection model to obtain a sample detection result;
and training the initial vehicle detection model according to the sample detection result and the labeled image to obtain the vehicle detection model.
8. An apparatus for authenticating a retroreflective sign of a vehicle, the apparatus comprising:
the first acquisition module is used for acquiring a target image to be detected; the target image shows the detection result of the reflective mark of the vehicle;
the second acquisition module is used for verifying the text information in the target image to obtain a verification result of the text information; the text information at least comprises a vehicle reflective mark;
the third acquisition module is used for inputting the target image into a preset vehicle detection model to obtain a detection result of the target image; the detection result of the target image is used for indicating whether the target image comprises a vehicle photo or not;
and the verification module is used for verifying the detection result of the vehicle reflective mark displayed by the target image according to the verification result of the text information and the detection result of the target image to obtain a verification result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911400237.8A CN111160342A (en) | 2019-12-30 | 2019-12-30 | Vehicle reflective mark verification method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911400237.8A CN111160342A (en) | 2019-12-30 | 2019-12-30 | Vehicle reflective mark verification method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111160342A true CN111160342A (en) | 2020-05-15 |
Family
ID=70559446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911400237.8A Pending CN111160342A (en) | 2019-12-30 | 2019-12-30 | Vehicle reflective mark verification method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160342A (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184386A (en) * | 2011-04-22 | 2011-09-14 | 马鞍山马钢华阳设备诊断工程有限公司 | Online wheel identification character recognition method and online wheel identification character detection system |
| EP2549408A1 (en) * | 2011-07-20 | 2013-01-23 | Delphi Technologies, Inc. | Method for detecting and classifying objects |
| CN103077390A (en) * | 2012-10-23 | 2013-05-01 | 马鞍山马钢华阳设备诊断工程有限公司 | Annular identification character online recognition device applied to wheel detection |
| CN104678970A (en) * | 2015-02-13 | 2015-06-03 | 王明文 | Big Dipper and/or GPS-based system and method for supervising and monitoring safety protection products and identifiers of transportation vehicles |
| CN107170352A (en) * | 2017-07-05 | 2017-09-15 | 王明文 | Road transport goods vehicle sign board and method for anti-counterfeit |
| CN108629344A (en) * | 2018-05-10 | 2018-10-09 | 广州市腾畅交通科技有限公司 | Vehicle reflection label detection method, apparatus and equipment |
| CN109271980A (en) * | 2018-08-28 | 2019-01-25 | 上海萃舟智能科技有限公司 | A kind of vehicle nameplate full information recognition methods, system, terminal and medium |
| WO2019024771A1 (en) * | 2017-07-31 | 2019-02-07 | 阿里巴巴集团控股有限公司 | Car insurance image processing method, apparatus, server and system |
| CN109447076A (en) * | 2018-09-20 | 2019-03-08 | 上海眼控科技股份有限公司 | A kind of vehicle VIN code recognition detection method for vehicle annual test |
| CN109657674A (en) * | 2018-11-28 | 2019-04-19 | 新华三技术有限公司 | A kind of vehicles identifications determine method and device |
| CN109784326A (en) * | 2018-11-27 | 2019-05-21 | 上海眼控科技股份有限公司 | A kind of vehicle chassis detection method based on deep learning |
| CN110276295A (en) * | 2019-06-20 | 2019-09-24 | 上海眼控科技股份有限公司 | Vehicle identification number detection recognition method and equipment |
| CN110276347A (en) * | 2019-06-11 | 2019-09-24 | 上海眼控科技股份有限公司 | Text category information detection recognition method and equipment |
| CN110490135A (en) * | 2019-08-20 | 2019-11-22 | 上海眼控科技股份有限公司 | Vehicle annual test method, apparatus, computer equipment and storage medium |
| CN110598687A (en) * | 2019-09-18 | 2019-12-20 | 上海眼控科技股份有限公司 | Vehicle identification code detection method and device and computer equipment |
| CN110619330A (en) * | 2019-09-18 | 2019-12-27 | 上海眼控科技股份有限公司 | Recognition model training method and device, computer equipment and recognition method |
-
2019
- 2019-12-30 CN CN201911400237.8A patent/CN111160342A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184386A (en) * | 2011-04-22 | 2011-09-14 | 马鞍山马钢华阳设备诊断工程有限公司 | Online wheel identification character recognition method and online wheel identification character detection system |
| EP2549408A1 (en) * | 2011-07-20 | 2013-01-23 | Delphi Technologies, Inc. | Method for detecting and classifying objects |
| CN103077390A (en) * | 2012-10-23 | 2013-05-01 | 马鞍山马钢华阳设备诊断工程有限公司 | Annular identification character online recognition device applied to wheel detection |
| CN104678970A (en) * | 2015-02-13 | 2015-06-03 | 王明文 | Big Dipper and/or GPS-based system and method for supervising and monitoring safety protection products and identifiers of transportation vehicles |
| CN107170352A (en) * | 2017-07-05 | 2017-09-15 | 王明文 | Road transport goods vehicle sign board and method for anti-counterfeit |
| WO2019024771A1 (en) * | 2017-07-31 | 2019-02-07 | 阿里巴巴集团控股有限公司 | Car insurance image processing method, apparatus, server and system |
| CN108629344A (en) * | 2018-05-10 | 2018-10-09 | 广州市腾畅交通科技有限公司 | Vehicle reflection label detection method, apparatus and equipment |
| CN109271980A (en) * | 2018-08-28 | 2019-01-25 | 上海萃舟智能科技有限公司 | A kind of vehicle nameplate full information recognition methods, system, terminal and medium |
| CN109447076A (en) * | 2018-09-20 | 2019-03-08 | 上海眼控科技股份有限公司 | A kind of vehicle VIN code recognition detection method for vehicle annual test |
| CN109784326A (en) * | 2018-11-27 | 2019-05-21 | 上海眼控科技股份有限公司 | A kind of vehicle chassis detection method based on deep learning |
| CN109657674A (en) * | 2018-11-28 | 2019-04-19 | 新华三技术有限公司 | A kind of vehicles identifications determine method and device |
| CN110276347A (en) * | 2019-06-11 | 2019-09-24 | 上海眼控科技股份有限公司 | Text category information detection recognition method and equipment |
| CN110276295A (en) * | 2019-06-20 | 2019-09-24 | 上海眼控科技股份有限公司 | Vehicle identification number detection recognition method and equipment |
| CN110490135A (en) * | 2019-08-20 | 2019-11-22 | 上海眼控科技股份有限公司 | Vehicle annual test method, apparatus, computer equipment and storage medium |
| CN110598687A (en) * | 2019-09-18 | 2019-12-20 | 上海眼控科技股份有限公司 | Vehicle identification code detection method and device and computer equipment |
| CN110619330A (en) * | 2019-09-18 | 2019-12-27 | 上海眼控科技股份有限公司 | Recognition model training method and device, computer equipment and recognition method |
Non-Patent Citations (4)
| Title |
|---|
| JUN-WEI HSIEH: "Symmetrical SURF and Its Applications to Vehicle Detection and Vehicle Make and Model Recognition" * |
| ZAKRIA等: "Efficient and Deep Vehicle Re-Identification Using Multi-Level Feature Extraction" * |
| 曹利民: "视频监控中汽车车前窗特征提取研究" * |
| 杨攀: "基于深度学习的车型识别方法研究与应用" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390666B (en) | Road damage detection method, device, computer equipment and storage medium | |
| CN109947967B (en) | Image recognition method, image recognition device, storage medium and computer equipment | |
| US9053361B2 (en) | Identifying regions of text to merge in a natural image or video frame | |
| CN112861648B (en) | Character recognition method, character recognition device, electronic equipment and storage medium | |
| US20200311460A1 (en) | Character identification method and device | |
| WO2021012382A1 (en) | Method and apparatus for configuring chat robot, computer device and storage medium | |
| CN111242126A (en) | Irregular text correction method and device, computer equipment and storage medium | |
| CN111144358A (en) | Vehicle quality certificate verification method and device, computer equipment and storage medium | |
| CN111192392B (en) | Identity verification method and device, computer equipment and computer-readable storage medium | |
| CN111144372A (en) | Vehicle detection method, device, computer equipment and storage medium | |
| CN113239910B (en) | Certificate identification method, device, equipment and storage medium | |
| CN111144400A (en) | Identification method and device for identity card information, terminal equipment and storage medium | |
| US20210303899A1 (en) | Systems and methods for automatic recognition of vehicle information | |
| CN112712703A (en) | Vehicle video processing method and device, computer equipment and storage medium | |
| CN111753592B (en) | Traffic sign recognition method, device, computer equipment and storage medium | |
| CN114663871A (en) | Image recognition method, training method, device, system and storage medium | |
| CN112580499A (en) | Text recognition method, device, equipment and storage medium | |
| CN112580457A (en) | Vehicle video processing method and device, computer equipment and storage medium | |
| CN111325256A (en) | Vehicle appearance detection method and device, computer equipment and storage medium | |
| CN110728680A (en) | Automobile data recorder detection method and device, computer equipment and storage medium | |
| CN110781887A (en) | License plate screw detection method and device and computer equipment | |
| CN111160342A (en) | Vehicle reflective mark verification method and device, computer equipment and storage medium | |
| CN111626244A (en) | Image recognition method, image recognition device, electronic equipment and medium | |
| CN111340837A (en) | Image processing method, device, equipment and storage medium | |
| CN117115823A (en) | Tamper identification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240510 |