CN111444911B - Training method and device of license plate recognition model and license plate recognition method and device - Google Patents
Training method and device of license plate recognition model and license plate recognition method and device Download PDFInfo
- Publication number
- CN111444911B CN111444911B CN201911282626.5A CN201911282626A CN111444911B CN 111444911 B CN111444911 B CN 111444911B CN 201911282626 A CN201911282626 A CN 201911282626A CN 111444911 B CN111444911 B CN 111444911B
- Authority
- CN
- China
- Prior art keywords
- license plate
- training
- image
- recognition model
- target
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06V20/625—License plates
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Character Discrimination (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a device for training a license plate recognition model, and a method and a device for recognizing a license plate, wherein the method for training the license plate recognition model comprises the following steps: obtaining a vehicle image training sample, wherein the vehicle image training sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image; extracting a first target training characteristic according to the vehicle image training sample; training the first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; segmenting a license plate image output by the license plate recognition model to obtain target training characters; extracting a second target training characteristic according to the target training character; and training the depth separable convolution neural network model according to the second target training characteristics to obtain a depth separable convolution license plate recognition model. By adopting the separable convolutional neural network model, the invention can realize the decoupling of the spatial information and the depth information, reduce the network parameters and improve the training accuracy.
Description
Technical Field
The invention relates to the technical field of recognition, in particular to a method and a device for training a license plate recognition model and a license plate recognition method and a license plate recognition device.
Background
The license plate recognition system is an application of computer video image recognition technology in vehicle license plate recognition. License plate recognition is widely applied to highway vehicle management, and in parking lot management, the license plate recognition technology is also a main means for recognizing vehicle identities. However, the ever-increasing amount of data poses new challenges for quickly and accurately recognizing license plate content.
The traditional license plate recognition algorithm comprises a large number of manual feature extraction processes, the extraction process is complex and slow, the feature extraction based on the convolutional neural network can be used for directly processing images and automatically extracting features, but the network parameter amount in the extraction process is huge, the training process is complex, the training speed is slow, and the training accuracy is low.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to overcome the defect of large network parameter quantity during feature extraction based on the convolutional neural network in the prior art, so that a license plate recognition model training method and device, and a license plate recognition method and device are provided.
According to a first aspect, the embodiment of the invention discloses a training method of a license plate recognition model, which comprises the following steps: obtaining a vehicle image training sample, wherein the vehicle image training sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image; extracting a first target training feature according to the vehicle image training sample; training a first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; segmenting the license plate image output by the license plate recognition model to obtain target training characters; extracting a second target training characteristic according to the target training character; and training the depth separable convolution neural network model according to the second target training characteristics to obtain a depth separable convolution license plate recognition model.
With reference to the first aspect, in a first implementation manner of the first aspect, before the license plate image output by the license plate recognition model is segmented to obtain a target training character, the method further includes: determining the inclination of the license plate in the license plate image; and when the inclination of the license plate does not meet a first preset condition, performing inclination correction on the license plate image.
With reference to the first aspect, in a second implementation manner of the first aspect, after the first deep learning network model is trained according to the first target training feature to obtain a license plate recognition model, the method further includes: obtaining a vehicle image test sample, wherein the vehicle image test sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image; extracting a first test feature according to the vehicle image test sample; testing the license plate recognition model according to the first test characteristic to obtain a first test result; and when the first test result meets a second preset condition, determining the license plate recognition model as an available license plate recognition model.
With reference to the second implementation manner of the first aspect, in a third implementation manner of the first aspect, after the deep separable convolutional neural network model is trained according to the second target training feature to obtain a deep separable convolutional license plate recognition model, the method further includes: obtaining a license plate image test sample, wherein the license plate image test sample is a license plate image test sample output by the license plate recognition model; extracting a second test characteristic according to the license plate image test sample; testing the depth separable convolution license plate recognition model according to the second test characteristic to obtain a second test result; and when the second test result meets a third preset condition, determining the depth separable convolution license plate recognition model as an available depth separable convolution license plate recognition model.
According to a second aspect, the embodiment of the invention also discloses a license plate recognition method, which comprises the following steps: acquiring a vehicle image to be identified; carrying out license plate positioning recognition on the vehicle image to be recognized according to the license plate recognition model to obtain a target recognition license plate image; segmenting the target recognition license plate image to obtain target recognition characters; extracting target recognition characteristics according to the target recognition characters; identifying the target identification characteristics according to a depth separable convolution license plate identification model to obtain a character identification result; combining the character recognition results to obtain the license plate number of the license plate to be recognized; the license plate recognition model obtained by the license plate recognition model training method and the depth separable convolution license plate recognition model are obtained by training according to the license plate recognition model training method described in the first aspect or any one of the embodiments of the first aspect.
With reference to the second aspect, in a first implementation manner of the second aspect, before the segmenting the target recognition license plate image to obtain target recognition characters, the method further includes: determining the inclination of the license plate in the target recognition license plate image; and when the inclination of the license plate does not meet a first preset condition, performing inclination correction on the target recognition license plate image.
According to a third aspect, an embodiment of the present invention further discloses a training device for a license plate recognition model, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring vehicle image training samples, and the vehicle image training samples comprise positive sample images with license plate images and negative sample images without license plate images; the first extraction module is used for extracting a first target training feature according to the vehicle image training sample; the first training module is used for training a first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; the first segmentation module is used for segmenting the license plate image output by the license plate recognition model to obtain target training characters; the second extraction module is used for extracting second target training characteristics according to the target training characters; and the second training module is used for training the depth separable convolution neural network model according to the second target training characteristics to obtain a depth separable convolution license plate recognition model.
According to a fourth aspect, an embodiment of the present invention further discloses a license plate recognition apparatus, including: the second acquisition module is used for acquiring the image of the vehicle to be identified; the first recognition module is used for carrying out license plate positioning recognition on the vehicle image to be recognized according to the license plate recognition model to obtain a target recognition license plate image; the second segmentation module is used for segmenting the target recognition license plate image to obtain target recognition characters; the third extraction module is used for extracting target identification characteristics according to the target identification characters; the second recognition module is used for recognizing the target recognition characteristics according to the depth separable convolution license plate recognition model to obtain a character recognition result; the combination module is used for combining the character recognition results to obtain the license plate number of the license plate to be recognized; the license plate recognition model obtained by the license plate recognition model training method and the depth separable convolution license plate recognition model are obtained by training according to the license plate recognition model training method described in the first aspect or any one of the embodiments of the first aspect.
According to a fifth aspect, an embodiment of the present invention further discloses an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the processor to cause the processor to perform a method for training a license plate recognition model according to the first aspect or any embodiment of the first aspect, or a method for recognizing a license plate according to the second aspect or any embodiment of the second aspect.
According to a sixth aspect, the present invention further discloses a computer-readable storage medium, on which computer instructions are stored, and the computer instructions, when executed by a processor, implement the method for training the license plate recognition model according to the first aspect or any embodiment of the first aspect, or the method for recognizing the license plate according to any embodiment of the second aspect or any embodiment of the second aspect.
The technical scheme of the invention has the following advantages:
1. according to the training method and device for the license plate recognition model, vehicle image training samples are obtained, wherein the vehicle image training samples comprise positive sample images with license plate images and negative sample images without license plate images; extracting a first target training characteristic according to the vehicle image training sample; training the first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; segmenting a license plate image output by the license plate recognition model to obtain target training characters; extracting a second target training characteristic according to the target training character; and training the depth separable convolution neural network model according to the second target training characteristics to obtain the depth separable convolution license plate recognition model, so that the decoupling of the spatial information and the depth information can be realized, the network parameters are reduced, and the training accuracy is improved.
2. According to the license plate recognition method and device provided by the invention, the image of the vehicle to be recognized is obtained; carrying out license plate positioning recognition on a vehicle image to be recognized according to a license plate recognition model to obtain a target recognition license plate image; segmenting the target recognition license plate image to obtain target recognition characters; extracting target identification characteristics according to the target identification characters; identifying target identification characteristics according to the depth separable convolution license plate identification model to obtain a character identification result; and combining the character recognition results to obtain the license plate number of the license plate to be recognized, so that the parameter quantity of a network is reduced, and the vehicle recognition accuracy is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a specific example of a training method of a license plate recognition model according to embodiment 1 of the present invention;
fig. 2 is a schematic block diagram of a specific example of the training apparatus for the license plate recognition model according to embodiment 1 of the present invention;
fig. 3 is a flowchart of a specific example of a license plate recognition method in embodiment 3 of the present invention;
fig. 4 is a functional block diagram of a specific example of the license plate recognition apparatus according to embodiment 4 of the present invention;
fig. 5 is a diagram of an embodiment of an electronic terminal in embodiments 5 and 6 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment provides a training method of a license plate recognition model, as shown in fig. 1, including the following steps:
s11: and obtaining a vehicle image training sample, wherein the vehicle image training sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image.
Illustratively, the vehicle image training sample may be obtained from a certain road segment monitoring video, may be pre-stored in a terminal, or may be obtained by searching in a search engine, where the vehicle image training sample includes multiple vehicles such as a common car, a motorcycle, a tricycle, and the like, multiple license plates such as a continental license plate with a unified license plate format and license plates in hong kong and australian areas with various license plate formats, and multiple backgrounds such as a background improve training accuracy. The embodiment of the invention does not limit the vehicle image training sample and the acquisition method thereof, and a person skilled in the art can select the training sample according to the actual situation.
S12: and extracting a first target training characteristic according to the vehicle image training sample.
For example, the first target training feature may be a type of a license plate, a size of the license plate, a color of the license plate, and the like, and the first target training feature is not specifically limited in the embodiment of the present invention and may be set by a person skilled in the art according to actual needs.
S13: and training the first deep learning network model according to the first target training characteristics to obtain a license plate recognition model.
Exemplarily, a first target training characteristic is input into a first deep learning network model, supervised or unsupervised training is carried out on the first deep learning network model, each weight of the first deep learning network model is continuously adjusted through a second target characteristic, training optimization is carried out, and a license plate recognition model is obtained. The training method is not limited in the embodiment of the invention, and can be selected by a person skilled in the art according to actual conditions.
S14: and segmenting the license plate image output by the license plate recognition model to obtain target training characters.
Illustratively, the target training characters in the license plate image comprise Chinese characters, English letters and numbers, the license plate image is segmented to obtain the target training characters, and the character segmentation method can be a projection-based basic field segmentation method and a structural feature-based character segmentation method, wherein the projection-based basic field segmentation method uses vertical or horizontal projection, the license plate image is subjected to binarization processing firstly and then is projected horizontally or vertically, and the characters are segmented comprehensively through the aspect ratio of the characters and the projection information; the character segmentation based on the structural features uses feature points on the character structure to perform segmentation, and mainly performs character analysis on some local extreme values of the character, the features of corner points, the point spacing, the contour change degree and other features. The character segmentation method is not limited in the embodiment of the invention, and can be selected by a person skilled in the art according to actual conditions.
S15: and extracting a second target training characteristic according to the target training character.
Illustratively, the second target training feature may be a character color, a character type, or the like. The second target training characteristic is not specifically limited in the embodiment of the present invention, and those skilled in the art can set the second target training characteristic according to actual needs.
S16: and training the depth separable convolution neural network model according to the second target training characteristics to obtain a depth separable convolution license plate recognition model.
Illustratively, the first target training features are input into the deep separable convolutional neural network model, and each weight of the deep separable convolutional neural network model is continuously adjusted through the second target features for training and optimization, so that the deep separable convolutional license plate recognition model is obtained. The conventional convolution operation is to realize the joint mapping of the channel correlation and the spatial correlation, the deep separable convolution is to decouple the channel correlation and the spatial correlation, and map the channel correlation and the spatial correlation separately, i.e. the conventional convolution operation is changed into a two-layer convolution operation, i.e. the original standard convolution operation is factorized into a depthwise contribution of 3 x 3 and a pointwise contribution of 1 x 1, so that the number of network parameters is reduced, and the training accuracy is improved.
According to the training method of the license plate recognition model, a vehicle image training sample is obtained, wherein the vehicle image training sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image; extracting a first target training characteristic according to the vehicle image training sample; training the first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; segmenting a license plate image output by the license plate recognition model to obtain target training characters; extracting a second target training characteristic according to the target training character; and training the depth separable convolution neural network model according to the second target training characteristics to obtain the depth separable convolution license plate recognition model, so that the decoupling of the spatial information and the depth information can be realized, the network parameters are reduced, and the training accuracy is improved.
As an alternative embodiment of the present application, before step S14, the method further includes:
firstly, determining the inclination of the license plate in the license plate image.
For example, the inclination of the license plate may be an inclination of a currently obtained license plate image relative to a horizontal line or a vertical line, and the inclination may be represented by an inclination angle, where the inclination angle may be an included angle between a bottom edge of the license plate image and the horizontal line, or an included angle between a vertical edge of the license plate image and the vertical line. The representation of the inclination angle is not limited in the embodiment of the present invention, and may be set according to actual conditions.
And secondly, when the inclination of the license plate does not meet a first preset condition, performing inclination correction on the license plate image.
For example, the first preset condition may be that the inclination angle of the license plate is smaller than or equal to a preset value, or that the inclination angle is within a preset range; the preset value may be set to 3o or 5o, and the preset range may be set to 2o to 4 o.
When the inclination of the license plate is larger than a preset value or the inclination of the license plate is not within a preset range, the inclination correction of the license plate image is needed, the inclination correction method can adopt image rotation, namely the inclined license plate image is rotated to be horizontal, the rotation point of the image can be the center point of the image or can be based on the vertex of the image.
As an alternative embodiment of the present application, after step S13, the method further includes:
firstly, a vehicle image test sample is obtained, wherein the vehicle image test sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image.
For example, the vehicle image test sample may be obtained from a certain road segment monitoring video, may be pre-stored in the terminal, or may be obtained by searching in a search engine, and the vehicle image test sample and the vehicle image training sample may not be the same image set, and therefore, may be according to 7: a scale of 3 assigns the acquired image set. The proportion is not limited in the embodiment of the present invention, and may be set according to the specific image set obtained.
Second, a first test feature is extracted from the vehicle image test sample.
For example, the first test feature may be the same as the first target training feature described above, so as to improve the detection accuracy, and the specific implementation manner is shown in "extracting the first target training feature according to the vehicle image training sample" in example 1, which is not described herein again.
And thirdly, testing the license plate recognition model according to the first test characteristic to obtain a first test result.
Illustratively, the embodiment of the invention uses the first test characteristic test data set to evaluate the quality of the license plate recognition model, inputs the first test characteristic into the license plate recognition model to obtain a first test result, and compares the first test result with the actual output to judge the quality of the license plate recognition model.
And finally, when the first test result meets a second preset condition, determining the license plate recognition model as an available license plate recognition model.
For example, the second preset condition may be a ratio of the number of correct positive samples to the number of all positive samples, for example, if the number of positive sample images having license plate images in the vehicle image test sample is 10, and the number of correct positive samples to be recognized is 8, the license plate recognition model may be determined as an available license plate recognition model. The second preset condition is not limited in the embodiment of the application, and can be determined according to actual use requirements.
As an alternative embodiment of the present application, after step S16, the method further includes:
firstly, a license plate image test sample is obtained, and the license plate image test sample is a license plate image test sample output by a license plate recognition model.
For example, the license plate image test sample may be a license plate image recognized and output by the above license plate recognition model, and the output license plate image may be stored in the terminal after the license plate recognition model recognizes the vehicle image test sample, and is directly called from the terminal when in use.
And secondly, extracting a second test characteristic according to the license plate image test sample.
For example, the first test feature may be the same as the second target training feature described above, so as to improve the detection accuracy, and the specific implementation manner is shown in "extracting the second target training feature according to the target training character" in embodiment 1, which is not described herein again.
And thirdly, testing the depth separable convolution license plate recognition model according to the second test characteristic to obtain a second test result.
Illustratively, in the embodiment of the present invention, the second test feature is used to evaluate the quality of the depth separable convolution license plate recognition model, the second test feature is input into the license plate recognition model to obtain a second test result, and the first test result is compared with the actual output result to determine the quality of the depth separable convolution license plate recognition model.
And finally, when the second test result meets a third preset condition, determining the depth separable convolution license plate recognition model as an available depth separable convolution license plate recognition model.
For example, the third preset condition may be a ratio of the number of correct identifications to the number of all samples, for example, if the number of license plate images in the test sample of the license plate image is 100 and the number of correct identifications is 95, the depth separable convolutional license plate identification model may be determined as an available depth separable convolutional license plate identification model. The third preset condition is not limited in the embodiment of the present application, and a person skilled in the art can determine the third preset condition according to actual use requirements.
Example 2
An embodiment of the present invention further provides a license plate recognition method, as shown in fig. 2, including the following steps:
s21: and acquiring an image of the vehicle to be identified.
For example, the vehicle image to be recognized may be an image captured by a road camera in real time, or may also be an image that is captured in advance and stored in a terminal, and is called from the terminal when recognition is performed.
S22: and carrying out license plate positioning and recognition on the vehicle image to be recognized according to the license plate recognition model to obtain a target recognition license plate image.
Illustratively, the license plate recognition model is obtained by the license plate recognition model training method in embodiment 1, the target recognition license plate image is an image determined based on the license plate position in the vehicle image to be recognized, and the license plate of the vehicle image to be recognized is positioned and recognized according to the license plate recognition model to obtain the target recognition license plate image.
S23: and segmenting the target recognition license plate image to obtain target recognition characters. The specific implementation manner is shown in step S14 in embodiment 1, and details are not described here.
S24: and extracting target recognition characteristics according to the target recognition characters. The specific implementation manner is shown in step S15 in embodiment 1, and details are not described here.
S25: and identifying the target identification characteristics according to the depth separable convolution license plate identification model to obtain a character identification result.
Illustratively, the depth-separable convolution license plate recognition model is obtained by the depth-separable convolution license plate recognition model training method in embodiment 1, and the target recognition features are input into the depth-separable convolution license plate recognition model for recognition, so as to obtain a character recognition result.
S26: combining the character recognition results to obtain the license plate number of the license plate to be recognized;
the license plate recognition method provided by the invention comprises the steps of obtaining an image of a vehicle to be recognized; carrying out license plate positioning recognition on a vehicle image to be recognized according to a license plate recognition model to obtain a target recognition license plate image; segmenting the target recognition license plate image to obtain target recognition characters; extracting target identification characteristics according to the target identification characters; identifying target identification characteristics according to the depth separable convolution license plate identification model to obtain a character identification result; and combining the character recognition results to obtain the license plate number of the license plate to be recognized, so that the parameter quantity of a network is reduced, and the vehicle recognition accuracy is improved.
As an alternative embodiment of the present application, before step S23, the method further includes:
firstly, the inclination of the license plate in the target recognition license plate image is determined. The specific implementation manner is shown in the step "determining the inclination of the license plate in the license plate image" in embodiment 1, which is not described herein again.
And secondly, when the inclination of the license plate does not meet a first preset condition, performing inclination correction on the target recognition license plate image. The specific implementation manner is shown in the step "when the inclination of the license plate does not satisfy the first preset condition, the inclination of the license plate image is corrected" in embodiment 1, which is not described herein again.
Example 3
An embodiment of the present invention further provides a training device for a license plate recognition model, as shown in fig. 3, including:
the first obtaining module 31 is configured to obtain a vehicle image training sample, where the vehicle image training sample includes a positive sample image with a license plate image and a negative sample image without the license plate image; the specific implementation manner is shown in step S11 in embodiment 1, and details are not described here.
A first extraction module 32, configured to extract a first target training feature according to the vehicle image training sample; the specific implementation manner is shown in step S12 in embodiment 1, and details are not described here.
The first training module 33 is used for training the first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; the specific implementation manner is shown in step S13 in embodiment 1, and details are not described here.
The first segmentation module 34 is configured to segment the license plate image output by the license plate recognition model to obtain target training characters; the specific implementation manner is shown in step S14 in embodiment 1, and details are not described here.
The second extraction module 35 is configured to extract a second target training feature according to the target training character; the specific implementation manner is shown in step S15 in embodiment 1, and details are not described here.
And the second training module 36 is configured to train the deep separable convolutional neural network model according to the second target training characteristics to obtain a deep separable convolutional license plate recognition model. The specific implementation manner is shown in step S16 in embodiment 1, and details are not described here.
According to the training device of the license plate recognition model, vehicle image training samples are obtained, wherein the vehicle image training samples comprise positive sample images with license plate images and negative sample images without license plate images; extracting a first target training characteristic according to the vehicle image training sample; training the first deep learning network model according to the first target training characteristics to obtain a license plate recognition model; segmenting a license plate image output by the license plate recognition model to obtain target training characters; extracting a second target training characteristic according to the target training character; and training the depth separable convolution neural network model according to the second target training characteristics to obtain the depth separable convolution license plate recognition model, so that the decoupling of the spatial information and the depth information can be realized, the network parameters are reduced, and the training accuracy is improved.
As an optional embodiment of the present application, the apparatus further comprises:
the first determining module is used for determining the inclination of the license plate in the license plate image; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
And the first inclination correction module is used for performing inclination correction on the license plate image when the inclination of the license plate does not meet a first preset condition. The specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
As an optional embodiment of the present application, the apparatus further comprises:
the vehicle image test sample acquisition module is used for acquiring a vehicle image test sample, and the vehicle image test sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
The first test feature extraction module is used for extracting first test features according to the vehicle image test sample; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
The first testing module is used for testing the license plate recognition model according to the first testing characteristics to obtain a first testing result; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
And the license plate recognition model determining module is used for determining the license plate recognition model as an available license plate recognition model when the first test result meets a second preset condition. The specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
As an optional embodiment of the present application, the apparatus further comprises:
the license plate image test sample acquisition module is used for acquiring a license plate image test sample, and the license plate image test sample is a license plate image test sample output by the license plate recognition model; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
The second test feature extraction module is used for extracting second test features according to the license plate image test samples; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
The second testing module is used for testing the depth separable convolution license plate recognition model according to a second testing characteristic to obtain a second testing result; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
And the depth separable convolution license plate recognition model determining module is used for determining the depth separable convolution license plate recognition model as an available depth separable convolution license plate recognition model when the second test result meets a third preset condition. The specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
Example 4
An embodiment of the present invention further provides a license plate recognition apparatus, as shown in fig. 4, including:
a second obtaining module 41, configured to obtain an image of a vehicle to be identified; the specific implementation manner is shown in step S21 in embodiment 2, and details are not described here.
The first recognition module 42 is used for performing license plate positioning recognition on a vehicle image to be recognized according to the license plate recognition model to obtain a target recognition license plate image; the specific implementation manner is shown in step S22 in embodiment 2, and details are not described here.
The second segmentation module 43 is configured to segment the target recognition license plate image to obtain target recognition characters; the specific implementation manner is shown in step S23 in embodiment 2, and details are not described here.
A third extraction module 44, configured to extract a target recognition feature according to the target recognition character; the specific implementation manner is shown in step S24 in embodiment 2, and details are not described here.
The second recognition module 45 is used for recognizing the target recognition characteristics according to the depth separable convolution license plate recognition model to obtain a character recognition result; the specific implementation manner is shown in step S25 in embodiment 2, and details are not described here.
The combination module 46 is used for combining the character recognition results to obtain the license plate number of the license plate to be recognized; the license plate recognition model obtained by the license plate recognition model training method and the depth separable convolution license plate recognition model are obtained by training according to the license plate recognition model training method of embodiment 1. The specific implementation manner is shown in step S26 in embodiment 2, and details are not described here.
The license plate recognition device provided by the invention obtains the image of the vehicle to be recognized; carrying out license plate positioning recognition on a vehicle image to be recognized according to a license plate recognition model to obtain a target recognition license plate image; segmenting the target recognition license plate image to obtain target recognition characters; extracting target identification characteristics according to the target identification characters; identifying target identification characteristics according to the depth separable convolution license plate identification model to obtain a character identification result; and combining the character recognition results to obtain the license plate number of the license plate to be recognized, so that the parameter quantity of a network is reduced, and the vehicle recognition accuracy is improved.
As an optional embodiment of the present application, the apparatus further comprises:
the second determining module is used for determining the inclination of the license plate in the target recognition license plate image; the specific implementation manner is shown in the corresponding steps in embodiment 2, and is not described herein again.
And the second inclination correction module is used for performing inclination correction on the target recognition license plate image when the inclination of the license plate does not meet the first preset condition. The specific implementation manner is shown in the corresponding steps in embodiment 2, and is not described herein again.
Example 5
An embodiment of the present invention further provides a license plate recognition model training device, as shown in fig. 5, the electronic device may include a processor 51 and a memory 52, where the processor 51 and the memory 52 may be connected by a bus or in another manner, and fig. 5 takes the example of connection by a bus.
The processor 51 may be a Central Processing Unit (CPU). The Processor 51 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 52 is a non-transitory computer-readable storage medium, and can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the license plate recognition model training method in embodiment 1 of the present invention (for example, the first obtaining module 31, the first extracting module 32, the first training model 33, the first segmenting module 34, the second extracting module 35, and the second training module 36 shown in fig. 3). The processor 51 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 52, so as to implement the license plate recognition model training method in the above-described method embodiment.
The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 51, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 52, and when executed by the processor 51, perform the license plate recognition model training method in embodiment 1 shown in fig. 1.
The specific details of the license plate recognition model training device may be understood by referring to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.
Example 6
An embodiment of the present invention further provides a license plate recognition device, as shown in fig. 5, the electronic device may include a processor 51 and a memory 52, where the processor 51 and the memory 52 may be connected through a bus or in another manner, and fig. 5 takes the example of connection through a bus as an example.
The processor 51 may be a Central Processing Unit (CPU). The Processor 51 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 52, which is a non-transitory computer-readable storage medium, may be used for storing non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the license plate recognition method in the embodiment of the present invention (for example, the second obtaining module 41, the first recognition module 42, the second segmentation module 43, the third extraction module 44, the second recognition module 45, and the combination module 46 shown in fig. 4). The processor 51 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 52, so as to implement the license plate recognition method in the above method embodiment 2.
The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 51, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 52 and, when executed by the processor 51, perform the license plate recognition method in the embodiment shown in fig. 2.
The specific details of the license plate recognition device can be understood by referring to the corresponding related description and effects in embodiment 2 shown in fig. 2, which are not described herein again.
Example 7
The embodiment of the invention also provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the training method of the license plate recognition model in the embodiment 1. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Memory Access (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Example 8
The embodiment of the invention also provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the license plate identification method in the embodiment 2. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Memory Access (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (8)
1. A training method of a license plate recognition model is characterized by comprising the following steps:
obtaining a vehicle image training sample, wherein the vehicle image training sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image;
extracting a first target training feature according to the vehicle image training sample;
training a first deep learning network model according to the first target training characteristics to obtain a license plate recognition model;
segmenting the license plate image output by the license plate recognition model to obtain target training characters;
extracting a second target training characteristic according to the target training character;
training a depth separable convolution neural network model according to the second target training characteristics to obtain a depth separable convolution license plate recognition model; the deep separable convolutional neural network model is decoupled according to channel correlation and spatial correlation, and the channel correlation and the spatial correlation are mapped separately;
the method for segmenting the license plate image output by the license plate recognition model to obtain the target training character comprises the following steps: carrying out binarization processing on the license plate image output by the license plate recognition model; projecting in a horizontal direction or a vertical direction; segmenting according to a preset character length-width ratio and projection information to obtain target training characters;
after the first deep learning network model is trained according to the first target training characteristics to obtain a license plate recognition model, the method further comprises the following steps:
obtaining a vehicle image test sample, wherein the vehicle image test sample comprises a positive sample image with a license plate image and a negative sample image without the license plate image;
extracting a first test feature according to the vehicle image test sample;
testing the license plate recognition model according to the first test characteristic to obtain a first test result;
when the first test result meets a second preset condition, determining the license plate recognition model as an available license plate recognition model;
after the deep separable convolution neural network model is trained according to the second target training characteristics to obtain a deep separable convolution license plate recognition model, the method further comprises the following steps:
obtaining a license plate image test sample, wherein the license plate image test sample is a license plate image test sample output by the license plate recognition model;
extracting a second test characteristic according to the license plate image test sample;
testing the depth separable convolution license plate recognition model according to the second test characteristic to obtain a second test result;
and when the second test result meets a third preset condition, determining the depth separable convolution license plate recognition model as an available depth separable convolution license plate recognition model.
2. The method of claim 1, wherein before the segmenting the license plate image output by the license plate recognition model to obtain the target training character, the method further comprises:
determining the inclination of the license plate in the license plate image;
and when the inclination of the license plate does not meet a first preset condition, performing inclination correction on the license plate image.
3. A license plate recognition method is characterized by comprising the following steps:
acquiring a vehicle image to be identified;
carrying out license plate positioning recognition on the vehicle image to be recognized according to the license plate recognition model to obtain a target recognition license plate image;
segmenting the target recognition license plate image to obtain target recognition characters;
extracting target recognition characteristics according to the target recognition characters;
identifying the target identification characteristics according to a depth separable convolution license plate identification model to obtain a character identification result;
combining the character recognition results to obtain the license plate number of the vehicle to be recognized;
the license plate recognition model and the depth separable convolution license plate recognition model are obtained by training according to the license plate recognition model training method of claim 1 or 2.
4. The method of claim 3, wherein before the segmenting the target recognition license plate image to obtain target recognition characters, the method further comprises:
determining the inclination of the license plate in the target recognition license plate image;
and when the inclination of the license plate does not meet a first preset condition, performing inclination correction on the target recognition license plate image.
5. A training device for a license plate recognition model is characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring vehicle image training samples, and the vehicle image training samples comprise positive sample images with license plate images and negative sample images without license plate images;
the first extraction module is used for extracting a first target training feature according to the vehicle image training sample;
the first training module is used for training a first deep learning network model according to the first target training characteristics to obtain a license plate recognition model;
the first segmentation module is used for segmenting the license plate image output by the license plate recognition model to obtain target training characters;
the second extraction module is used for extracting second target training characteristics according to the target training characters;
the second training module is used for training the depth separable convolution neural network model according to the second target training characteristics to obtain a depth separable convolution license plate recognition model; the deep separable convolutional neural network model is decoupled according to channel correlation and spatial correlation, and the channel correlation and the spatial correlation are mapped separately;
the method for segmenting the license plate image output by the license plate recognition model to obtain the target training character comprises the following steps: carrying out binarization processing on the license plate image output by the license plate recognition model; projecting in a horizontal direction or a vertical direction; segmenting according to a preset character length-width ratio and projection information to obtain target training characters;
this training device of license plate recognition model still includes:
the system comprises a vehicle image test sample acquisition module, a vehicle image test sample acquisition module and a vehicle image test sample processing module, wherein the vehicle image test sample acquisition module is used for acquiring a vehicle image test sample which comprises a positive sample image with a license plate image and a negative sample image without the license plate image;
the first test feature extraction module is used for extracting first test features according to the vehicle image test sample;
the first testing module is used for testing the license plate recognition model according to the first testing characteristic to obtain a first testing result;
the license plate recognition model determining module is used for determining the license plate recognition model as an available license plate recognition model when the first test result meets a second preset condition;
this training device of license plate recognition model still includes:
the license plate image test sample acquisition module is used for acquiring a license plate image test sample, and the license plate image test sample is a license plate image test sample output by the license plate recognition model;
the second test feature extraction module is used for extracting second test features according to the license plate image test sample;
the second testing module is used for testing the depth separable convolution license plate recognition model according to the second testing characteristic to obtain a second testing result;
and the depth separable convolution license plate recognition model determining module is used for determining the depth separable convolution license plate recognition model as an available depth separable convolution license plate recognition model when the second test result meets a third preset condition.
6. A license plate recognition device, comprising:
the second acquisition module is used for acquiring the image of the vehicle to be identified;
the first recognition module is used for carrying out license plate positioning recognition on the vehicle image to be recognized according to the license plate recognition model to obtain a target recognition license plate image;
the second segmentation module is used for segmenting the target recognition license plate image to obtain target recognition characters;
the third extraction module is used for extracting target identification characteristics according to the target identification characters;
the second recognition module is used for recognizing the target recognition characteristics according to the depth separable convolution license plate recognition model to obtain a character recognition result;
the combination module is used for combining the character recognition results to obtain the license plate number of the vehicle to be recognized;
the license plate recognition model and the depth separable convolution license plate recognition model are obtained by training according to the license plate recognition model training method of claim 1 or 2.
7. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of training the license plate recognition model of claim 1 or 2 or the method of recognizing the license plate of claim 3 or 4.
8. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the method for training a license plate recognition model according to claim 1 or 2 or the method for recognizing a license plate according to claim 3 or 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911282626.5A CN111444911B (en) | 2019-12-13 | 2019-12-13 | Training method and device of license plate recognition model and license plate recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911282626.5A CN111444911B (en) | 2019-12-13 | 2019-12-13 | Training method and device of license plate recognition model and license plate recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111444911A CN111444911A (en) | 2020-07-24 |
| CN111444911B true CN111444911B (en) | 2021-02-26 |
Family
ID=71626909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911282626.5A Active CN111444911B (en) | 2019-12-13 | 2019-12-13 | Training method and device of license plate recognition model and license plate recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111444911B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914842A (en) * | 2020-08-10 | 2020-11-10 | 深圳市视美泰技术股份有限公司 | License plate information identification method and device, computer equipment and storage medium |
| CN111950490B (en) * | 2020-08-18 | 2024-04-09 | 东软睿驰汽车技术（沈阳）有限公司 | Parking rod identification method and training method and device of identification model thereof |
| CN112232237B (en) * | 2020-10-20 | 2024-03-12 | 城云科技（中国）有限公司 | Method, system, computer device and storage medium for monitoring vehicle flow |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
| CN103207992A (en) * | 2013-04-07 | 2013-07-17 | 布法罗机器人科技（苏州）有限公司 | Character and color combined recognition method of license plates |
| CN105335743A (en) * | 2015-10-28 | 2016-02-17 | 重庆邮电大学 | Vehicle license plate recognition method |
| CN106056751A (en) * | 2016-05-20 | 2016-10-26 | 聚龙股份有限公司 | Prefix number identification method and system |
| CN106096607A (en) * | 2016-06-12 | 2016-11-09 | 湘潭大学 | A kind of licence plate recognition method |
| CN107729801A (en) * | 2017-07-11 | 2018-02-23 | 银江股份有限公司 | A kind of vehicle color identifying system based on multitask depth convolutional neural networks |
| CN107730905A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Multitask fake license plate vehicle vision detection system and method based on depth convolutional neural networks |
| CN108399370A (en) * | 2018-02-02 | 2018-08-14 | 达闼科技（北京）有限公司 | The method and cloud system of Expression Recognition |
| WO2018156846A1 (en) * | 2017-02-27 | 2018-08-30 | Dolphin AI, Inc. | Machine learning-based recognition of weather damage |
| KR101970442B1 (en) * | 2018-12-04 | 2019-04-19 | 주식회사 넥스파시스템 | Illegal parking enforcement system Using Fast R-CNN based on Vehicle detection |
| CN109815956A (en) * | 2018-12-28 | 2019-05-28 | 安徽清新互联信息科技有限公司 | A kind of license plate character recognition method based on adaptive location segmentation |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298976B (en) * | 2014-10-16 | 2017-09-26 | 电子科技大学 | Detection method of license plate based on convolutional neural networks |
| CN104809443B (en) * | 2015-05-05 | 2018-12-28 | 上海交通大学 | Detection method of license plate and system based on convolutional neural networks |
| CN104992147A (en) * | 2015-06-09 | 2015-10-21 | 中国石油大学(华东) | License plate identification method of deep learning based on fast and slow combination cloud calculation environment |
| US9911055B2 (en) * | 2016-03-08 | 2018-03-06 | Conduent Business Services, Llc | Method and system for detection and classification of license plates |
| US10733460B2 (en) * | 2016-09-14 | 2020-08-04 | Nauto, Inc. | Systems and methods for safe route determination |
| CN106650740B (en) * | 2016-12-15 | 2019-08-13 | 深圳市华尊科技股份有限公司 | A kind of licence plate recognition method and terminal |
| CN108009543B (en) * | 2017-11-29 | 2020-05-26 | 深圳市华尊科技股份有限公司 | License plate recognition method and device |
| CN110490179B (en) * | 2018-05-15 | 2022-08-05 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device and storage medium |
| CN109214443A (en) * | 2018-08-24 | 2019-01-15 | 北京第视频科学技术研究院有限公司 | Car license recognition model training method, licence plate recognition method, device and equipment |
| CN110210475B (en) * | 2019-05-06 | 2021-05-18 | 浙江大学 | License plate character image segmentation method based on non-binarization and edge detection |
-
2019
- 2019-12-13 CN CN201911282626.5A patent/CN111444911B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
| CN103207992A (en) * | 2013-04-07 | 2013-07-17 | 布法罗机器人科技（苏州）有限公司 | Character and color combined recognition method of license plates |
| CN105335743A (en) * | 2015-10-28 | 2016-02-17 | 重庆邮电大学 | Vehicle license plate recognition method |
| CN106056751A (en) * | 2016-05-20 | 2016-10-26 | 聚龙股份有限公司 | Prefix number identification method and system |
| CN106096607A (en) * | 2016-06-12 | 2016-11-09 | 湘潭大学 | A kind of licence plate recognition method |
| WO2018156846A1 (en) * | 2017-02-27 | 2018-08-30 | Dolphin AI, Inc. | Machine learning-based recognition of weather damage |
| CN107730905A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Multitask fake license plate vehicle vision detection system and method based on depth convolutional neural networks |
| CN107729801A (en) * | 2017-07-11 | 2018-02-23 | 银江股份有限公司 | A kind of vehicle color identifying system based on multitask depth convolutional neural networks |
| CN108399370A (en) * | 2018-02-02 | 2018-08-14 | 达闼科技（北京）有限公司 | The method and cloud system of Expression Recognition |
| KR101970442B1 (en) * | 2018-12-04 | 2019-04-19 | 주식회사 넥스파시스템 | Illegal parking enforcement system Using Fast R-CNN based on Vehicle detection |
| CN109815956A (en) * | 2018-12-28 | 2019-05-28 | 安徽清新互联信息科技有限公司 | A kind of license plate character recognition method based on adaptive location segmentation |
Non-Patent Citations (2)
| Title |
|---|
| Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines;GOU C等;《IEEE transactions on intelligent transportation systems》;20161231;第17卷(第4期);第1096-1107页 * |
| 基于样本扩充的小样本车牌识别;尤鸣宇等;《南京师大学报(自然科学版)》;20190920;第42卷(第3期);第1-10页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111444911A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111435446A (en) | License plate identification method and device based on L eNet | |
| TWI497422B (en) | A system and method for recognizing license plate image | |
| US20210192227A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| WO2020038138A1 (en) | Sample labeling method and device, and damage category identification method and device | |
| CN111444911B (en) | Training method and device of license plate recognition model and license plate recognition method and device | |
| CN112329881B (en) | License plate recognition model training method, license plate recognition method and device | |
| CN110807491A (en) | License plate image definition model training method, definition detection method and device | |
| CN105989334B (en) | Road detection method based on monocular vision | |
| CN111435445A (en) | Training method and device of character recognition model and character recognition method and device | |
| CN110909598B (en) | Non-motor vehicle lane traffic violation driving identification method based on deep learning | |
| CN111582339B (en) | Vehicle detection and recognition method based on deep learning | |
| CN112906471A (en) | Traffic signal lamp identification method and device | |
| CN114820679B (en) | Image labeling method and device electronic device and storage medium | |
| CN106778777A (en) | A kind of vehicle match method and system | |
| CN110728680A (en) | Automobile data recorder detection method and device, computer equipment and storage medium | |
| CN111104826B (en) | License plate character recognition method and device and electronic equipment | |
| CN115797314A (en) | Part surface defect detection method, system, equipment and storage medium | |
| CN110781887A (en) | License plate screw detection method and device and computer equipment | |
| CN115311522A (en) | Target detection method and device for automatic driving, electronic equipment and medium | |
| CN113313110B (en) | License plate type recognition model construction and license plate type recognition method | |
| CN113902740A (en) | Construction method of image blurring degree evaluation model | |
| CN113435350A (en) | Traffic marking detection method, device, equipment and medium | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN108985197B (en) | Automatic detection method for taxi driver smoking behavior based on multi-algorithm fusion | |
| CN118230279A (en) | Traffic signal lamp identification method, equipment, medium and vehicle based on twin network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |