CN110288006A - A kind of license plate number automatic Verification method and system - Google Patents
A kind of license plate number automatic Verification method and system Download PDFInfo
- Publication number
- CN110288006A CN110288006A CN201910475255.6A CN201910475255A CN110288006A CN 110288006 A CN110288006 A CN 110288006A CN 201910475255 A CN201910475255 A CN 201910475255A CN 110288006 A CN110288006 A CN 110288006A
- Authority
- CN
- China
- Prior art keywords
- license plate
- vehicle
- image
- vehicle face
- target detection
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of license plate number automatic Verification method and system, method include: obtain vehicle pictures and with achieve license plate sign character；Vehicle image is detected using vehicle face target detection model, obtains vehicle face area image；Vehicle face area image is detected using license plate target detection model, obtains license plate image；License plate image is detected using Character segmentation model, obtains actual license plate sign character；Actual license plate sign character is compared with from archive license plate sign character, by verification if consistent, if inconsistent unverified.Its system includes: that the memory with computer program instructions, the processor communicated with memory foundation, processor execute computer program instructions for storing data.Present invention is mainly applied to license plate numbers in automotive vehicle annual test to verify, and realize the whole-process automatic verification of review process, and checking procedure is efficient and accurate.
Description
Technical field
The present invention relates to the artificial intelligence judgment technology field of automotive vehicle annual test, in particular to a kind of license plate number is automatic
Method of calibration and system.
Background technique
Constantly improve with living standards of the people with the continuous social and economic development, Urban vehicles poputation rapidly increases
It is long.The workload of automotive vehicle annual test also increases rapidly therewith.License plate number verification mainly passes through in traditional vehicle annual test
Desk checking, this method cost of labor is higher, and efficiency is lower, and repeated verification operation is easy to produce fatigue for a long time, neglects
Equal defective modes influence to verify accuracy rate.
How accurately and rapidly license plate number to be verified, while avoiding desk checking at high cost, fatiguability is easily neglected
Etc. drawbacks, be technical problem urgently to be solved.
Summary of the invention
The purpose of the present invention is: propose a kind of license plate number automatic Verification method and system, it is automatic audit license plate number whether with
Server archive content is consistent, to meet nowadays the needs of to vehicle annual test working efficiency and accuracy rate.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of license plate number automatic Verification method, includes the following steps:
S1, vehicle image and archive license plate sign character corresponding with the vehicle are obtained from server；
S2, using the pre-established vehicle face target detection model based on deep learning to described in being got from server
Vehicle image is detected, to obtain vehicle face area image；
S3, using the pre-established license plate target detection model based on deep learning to the obtained vehicle face area image
It is detected, to obtain license plate image；
S4, the obtained license plate image is examined using the pre-established Character segmentation model based on deep learning
It surveys, to obtain the actual license plate sign character in the vehicle image；
S5, the institute corresponding with the vehicle got by the actual license plate sign character in the vehicle image and from server
It states archive license plate sign character to be compared, judges whether the two is consistent, by verification if consistent, if inconsistent do not pass through school
It tests.
Technical solution is advanced optimized, further comprising the steps of in the method:
The pre-established vehicle face target detection model based on deep learning；
The pre-established license plate target detection model based on deep learning；
The pre-established Character segmentation model based on deep learning.
Advanced optimize technical solution, obtain also needing after the license plate image in step 3 to the license plate image into
Row affine transformation correction process, specific processing step are as follows:
Edge extracting is carried out to the license plate image using Sobel edge detection algorithm；
Detection calculating is carried out using edge of the Hough line detection algorithm to the license plate image, obtains license plate horizontal sides
Edge and vertical edge tilt angle；
According to the license plate horizontal edge and vertical edge tilt angle, radiation transformation is carried out to the license plate image, is obtained
License plate image after taking correction.
Advanced optimize technical solution, the specific step of the pre-established vehicle face target detection model based on deep learning
Suddenly include:
Build vehicle face target detection deep neural network；
The vehicle image within the scope of different automobile types specified angle is obtained, the specified angle range includes: the forward direction of vehicle
It is shone according to side, and is both needed to include completely license plate and logo；
Vehicle face area image position in each Zhang Suoshu vehicle image is marked using rectangle frame, obtains vehicle face target instruction
Practice data set；
Using the vehicle face target training dataset training vehicle face target detection deep neural network of acquisition, obtain
Vehicle face target detection model based on deep learning.
Advanced optimize technical solution, the specific step of the pre-established license plate target detection model based on deep learning
Suddenly include:
Build license plate target detection deep neural network；
Obtain the vehicle face area image of different automobile types；
The position of license plate in each Zhang Suoshu vehicle face area image is marked using rectangle frame, obtains the training of license plate target
Data set；
Using the license plate target training dataset training license plate target detection deep neural network, obtain based on deep
Spend the license plate target detection model of study.
Advanced optimize technical solution, the specific steps packet of the pre-established Character segmentation model based on deep learning
It includes:
Build Character segmentation deep neural network；
Obtain the license plate image of different natural lighting conditions and different angle；
The license plate image is corrected using affine transformation；
Each character position in the license plate image is marked using rectangle frame, and records respective classes label；
Using the above-mentioned character data collection training Character segmentation deep neural network, the character based on deep learning is obtained
Parted pattern.
Technical solution is advanced optimized, described in step s 2 to obtain vehicle face area image specific step is as follows:
The vehicle image is input to the vehicle face target detection model based on deep learning, obtains a N number of dimension
Group [class, x, y, width, height], and each one-dimension array [class, x, y, width, height] corresponding one
A vehicle face target；
Wherein, class is object type, if object type is vehicle face, class 1, and if object type is not vehicle face,
Then class is 0；If x, y represent rectangle frame upper left angular coordinate, width represents rectangle width of frame, and height represents rectangle frame height
Degree；
Vehicle face distance information is constructed using the size of vehicle face region rectangle frame area, and with the maximum array of rectangle frame area
As output result；
By the rectangle frame location information in above-mentioned output result, vehicle face area image is extracted from the vehicle image.
Technical solution is advanced optimized, the specific steps for obtaining license plate image include: in step s3
The obtained vehicle face area image is input to the license plate target detection model based on deep learning, is obtained
One one-dimension array [class ', x ', y ', width ', height '], wherein first class ' of array represents object class
Not, if object type is license plate, class ' is 1, if object type is not license plate, class ' is 0；Rear four generations of array
Rectangle frame location information where table target object, wherein x ', y ' the upper left angular coordinate of rectangle frame is represented, width ' is represented
The width of rectangle frame, height ' represent the height of rectangle frame；
License plate area image is extracted from the vehicle face area image by the rectangle frame location information.
As technical solution is advanced optimized, if the vehicle face image is unverified in step s 5, will entirely locate
The result of the action of reason process records and to be uploaded to server for statistical analysis.
A kind of license plate number automatic checkout system, comprising:
Memory is configured as storing data and computer program instructions；
The processor communicated is established with the memory, the processor executes the computer program instructions and appoints to execute
The step of one above method.
The beneficial effects of the present invention are: present invention is mainly applied to license plate numbers in automotive vehicle annual test to verify, realize
The whole-process automatic verification of review process, and checking procedure is efficient and accurate；It simultaneously can be by unsanctioned verification image and original
It remains to collect evidence because passing server preservation back.Both manpower has been saved, has in turn ensured the just, openly of verifying work.
Detailed description of the invention
Fig. 1 is the overall step schematic diagram of method of calibration in the present invention.
Fig. 2 is vehicle face area image acquisition process schematic diagram.
Fig. 3 is license plate area image acquisition procedures schematic diagram.
Fig. 4 is whole verification deterministic process schematic diagram of the invention.
Specific embodiment
Below in conjunction with attached drawing.The present invention will be further described.
As shown in Figure 1, the step of middle license plate number automatic Verification method of the invention, is as follows:
First choice obtains vehicle image and archive license plate sign character corresponding with the vehicle from server.
Then, as shown in Fig. 2, using the pre-established vehicle face target detection model based on deep learning to from server
The vehicle image got is detected, to obtain vehicle face area image；As shown in figure 3, using pre-established based on depth
The license plate target detection model of degree study detects the obtained vehicle face area image, to obtain license plate image；To institute
State license plate image carry out affine transformation correction process, using the pre-established Character segmentation model based on deep learning to correction at
The license plate image after reason is detected, to obtain the actual license plate sign character in the vehicle image.
Finally, what is got by the actual license plate sign character in the vehicle image and from server is corresponding with the vehicle
The archive license plate sign character is compared, and judges whether the two is consistent, by verification if consistent, if inconsistent do not pass through
Verification.
Before carrying out above-mentioned steps, also need to do following preparation:
The pre-established vehicle face target detection model based on deep learning；
The pre-established license plate target detection model based on deep learning；
The pre-established Character segmentation model based on deep learning.
Wherein, the specific steps of the pre-established vehicle face target detection model based on deep learning include:
Build vehicle face target detection deep neural network；
The vehicle image within the scope of different automobile types specified angle is obtained, the specified angle range includes: the forward direction of vehicle
It is shone according to side, and is both needed to include completely license plate and logo；
Vehicle face area image position in each Zhang Suoshu vehicle image is marked using rectangle frame, obtains vehicle face target instruction
Practice data set；
Using the vehicle face target training dataset training vehicle face target detection deep neural network of acquisition, obtain
Vehicle face target detection model based on deep learning.
Wherein, the specific steps of the pre-established license plate target detection model based on deep learning include:
Build license plate target detection deep neural network；
Obtain the vehicle face area image of different automobile types；
The position of license plate in each Zhang Suoshu vehicle face area image is marked using rectangle frame, obtains the training of license plate target
Data set；
Using the license plate target training dataset training license plate target detection deep neural network, obtain based on deep
Spend the license plate target detection model of study.
Wherein, the specific steps of the pre-established Character segmentation model based on deep learning include:
Build Character segmentation deep neural network；
Obtain the license plate image of different natural lighting conditions and different angle；
The license plate image is corrected using affine transformation；
Each character position in the license plate image is marked using rectangle frame, and records respective classes label；
Using the above-mentioned character data collection training Character segmentation deep neural network, the character based on deep learning is obtained
Parted pattern.
Wherein, obtaining vehicle face area image, specific step is as follows:
The vehicle image is input to the vehicle face target detection model based on deep learning, obtains a N number of dimension
Group [class, x, y, width, height], and each one-dimension array [class, x, y, width, height] corresponding one
A vehicle face target；
Wherein, class is object type, if object type is vehicle face, class 1, and if object type is not vehicle face,
Then class is 0；If x, y represent rectangle frame upper left angular coordinate, width represents rectangle width of frame, and height represents rectangle frame height
Degree；
Vehicle face distance information is constructed using the size of vehicle face region rectangle frame area, and with the maximum array of rectangle frame area
As output result；
By the rectangle frame location information in above-mentioned output result, vehicle face area image is extracted from the vehicle image.
Wherein, the specific steps for obtaining license plate image include:
The obtained vehicle face area image is input to the license plate target detection model based on deep learning, is obtained
One one-dimension array [class ', x ', y ', width ', height '], wherein first class ' of array represents object class
Not, if object type is license plate, class ' is 1, if object type is not license plate, class ' is 0；Rear four generations of array
Rectangle frame location information where table target object, wherein x ', y ' the upper left angular coordinate of rectangle frame is represented, width ' is represented
The width of rectangle frame, height ' represent the height of rectangle frame；
License plate area image is extracted from the vehicle face area image by the rectangle frame location information.
Wherein, if the vehicle face image is unverified, the result of the action of entire treatment process is recorded and is uploaded to
Server is for statistical analysis.
Specific verification standard of the invention is:
Vehicle face target whether there is in vehicle face image；License plate target whether there is；Whether license plate sign character is complete；License plate number
Whether character content is consistent with server archive content；The present invention indicates verification using an one-dimension array [x1, x2, x3, x4]
State, initial value are [0,0,0,0], and flag bit x1, which represents vehicle face target, whether there is, and then x1 is 0 if it exists, if it does not exist then
X1 is 1, flag bit x2, and representing license plate target whether there is, and then x2 is 0 if it exists, and then x2 is 1 if it does not exist, flag bit x3 generation
Table extracts whether character digit is consistent with regulation character digit, and x3 is 0 if consistent, if inconsistent x3 is 1, flag bit x4 generation
Table extracts whether character content is consistent with regulation character content, and x4 is 0 if consistent, if inconsistent x4 is 1.Finally, statistics
Flag bit state, if mark is is 0, verification passes through, if it exists 1, then it verifies and does not pass through.The position occurred according to state 1
The available unsanctioned reason of verification.If x1 is 1, vehicle target or vehicle shooting angle may be not present in vehicle image
Spend it is against regulation, do not include complete vehicle body, therefore server achieve vehicle image it is undesirable, cause verification do not lead to
It crosses；If x2 is 1, possible reason is that license plate part was not photographed, license plate is lost or blocked by large area in vehicle image；If x3
It is 1, then parts against wear may occur for license plate or partial character is blocked；If x4 is 1, license plate may be by the dirt of the booties such as grease stain
Dye or character portion are worn；Determination module judges whether logo verification passes through according to verification standard, directly returns if passing through
Return verification success flag, the position back-checking failure cause and corresponding picture for being 1 according to flag bit if not passing through, after remaining
Phase audit verification.
Specifically deterministic process is verified in this programme as shown in figure 4, including the following steps:
Vehicle pictures and corresponding license plate sign character are downloaded from server；
Using the vehicle face target detection model inspection vehicle face based on deep learning network, judge that vehicle face target whether there is,
Then recording this mark if it exists is 0, extracts vehicle face area image；Then recording this mark if it does not exist is 1, and saves correlation
Picture, into statistical analysis process；
Using the license plate target detection model inspection license plate based on deep learning network, judge that license plate target whether there is,
Then recording this mark if it exists is 0, and extracts license plate image；Then recording this mark if it does not exist is 1, and saves related figure
Piece, into statistical analysis process；
License plate image is corrected using affine transformation；
Using the Character segmentation model extraction license plate sign character based on deep learning network, judge character digit whether with rule
Calibration is quasi- consistent, and it is 0 that this mark is recorded if consistent；It is 1 that this mark is recorded if inconsistent, and saves picture concerned,
Into statistical analysis process；
Judge whether obtained license plate sign character and server archive content are consistent, it is 0 that this mark is recorded if consistent；
It is 1 that this mark is recorded if inconsistent, and saves picture concerned, into statistical analysis process；
It is for statistical analysis to the result of the action of whole process, record flag bit all 0, then license plate number verification passes through,
Mark 1 if it exists, then license plate number verification does not pass through, and exports unsanctioned reason.
Finally, running hardware system involved in its method and step in the present invention includes: memory, it is configured as storage number
According to and computer program instructions；
The processor communicated is established with memory, the processor executes the computer program instructions to execute any one
The step of above method.
The advantages of basic principles and main features and this programme of this programme have been shown and described above.The technology of the industry
Personnel are it should be appreciated that this programme is not restricted to the described embodiments, and the above embodiments and description only describe this
The principle of scheme, under the premise of not departing from this programme spirit and scope, this programme be will also have various changes and improvements, these changes
Change and improvement is both fallen within the scope of claimed this programme.This programme be claimed range by appended claims and its
Equivalent thereof.
Claims (10)
1. a kind of license plate number automatic Verification method, which comprises the steps of:
S1, vehicle image and archive license plate sign character corresponding with the vehicle are obtained from server；
S2, using the pre-established vehicle face target detection model based on deep learning to the vehicle got from server
Image is detected, to obtain vehicle face area image；
S3, the obtained vehicle face area image is carried out using the pre-established license plate target detection model based on deep learning
Detection, to obtain license plate image；
S4, the obtained license plate image is detected using the pre-established Character segmentation model based on deep learning, with
Obtain the actual license plate sign character in the vehicle image；
S5, corresponding with the vehicle described depositing of being got by the actual license plate sign character in the vehicle image and from server
Shelves license plate sign character is compared, and judges whether the two is consistent, by verification if consistent, if inconsistent unverified.
2. a kind of license plate number automatic Verification method as described in claim 1, which is characterized in that further comprising the steps of:
The pre-established vehicle face target detection model based on deep learning；
The pre-established license plate target detection model based on deep learning；
The pre-established Character segmentation model based on deep learning.
3. a kind of license plate number automatic Verification method as claimed in claim 2, which is characterized in that obtain the vehicle in step 3
After board image, also need to carry out affine transformation correction process to the license plate image, specific processing step is as follows:
Edge extracting is carried out to the license plate image using Sobel edge detection algorithm；
Detection calculating is carried out using edge of the Hough line detection algorithm to the license plate image, obtain license plate horizontal edge with
Vertical edge tilt angle；
According to the license plate horizontal edge and vertical edge tilt angle, radiation transformation is carried out to the license plate image, obtains school
License plate image after just.
4. a kind of license plate number automatic Verification method as claimed in claim 2, which is characterized in that described pre-established based on depth
The specific steps of the vehicle face target detection model of study include:
Build vehicle face target detection deep neural network；
Obtain the vehicle image within the scope of different automobile types specified angle, the specified angle range include: vehicle it is positive according to and
Side is shone, and is both needed to include completely license plate and logo；
Vehicle face area image position in each Zhang Suoshu vehicle image is marked using rectangle frame, obtains vehicle face target training number
According to collection；
Using the vehicle face target training dataset training vehicle face target detection deep neural network of acquisition, it is based on
The vehicle face target detection model of deep learning.
5. a kind of license plate number automatic Verification method as claimed in claim 2, which is characterized in that described pre-established based on depth
The specific steps of the license plate target detection model of study include:
Build license plate target detection deep neural network；
Obtain the vehicle face area image of different automobile types；
The position of license plate in each Zhang Suoshu vehicle face area image is marked using rectangle frame, obtains license plate target training data
Collection；
Using the license plate target training dataset training license plate target detection deep neural network, obtains and be based on depth
The license plate target detection model of habit.
6. a kind of license plate number automatic Verification method as claimed in claim 3, which is characterized in that described pre-established based on depth
The specific steps of the Character segmentation model of study include:
Build Character segmentation deep neural network；
Obtain the license plate image of different natural lighting conditions and different angle；
The license plate image is corrected using affine transformation；
Each character position in the license plate image is marked using rectangle frame, and records respective classes label；
Using the above-mentioned character data collection training Character segmentation deep neural network, the Character segmentation based on deep learning is obtained
Model.
7. a kind of license plate number automatic Verification method as described in claim 1, which is characterized in that described in step s 2 to obtain vehicle
Specific step is as follows for face area image:
The vehicle image is input to the vehicle face target detection model based on deep learning, obtains N number of one-dimension array
[class, x, y, width, height], and each one-dimension array [class, x, y, width, height] is one corresponding
Vehicle face target；
Wherein, class is object type, if object type is vehicle face, class 1, and if object type is not vehicle face,
Class is 0；If x, y represent rectangle frame upper left angular coordinate, width represents rectangle width of frame, and height represents rectangle frame height
Degree；
Using vehicle face region rectangle frame area size construct vehicle face distance information, and using the maximum array of rectangle frame area as
Export result；
By the rectangle frame location information in above-mentioned output result, vehicle face area image is extracted from the vehicle image.
8. a kind of license plate number automatic Verification method as described in claim 1, which is characterized in that described in step s3 to obtain vehicle
The specific steps of board image include:
The obtained vehicle face area image is input to the license plate target detection model based on deep learning, obtains one
One-dimension array [class ', x ', y ', width ', height '], wherein first class ' of array represents object type, if
Object type is license plate, then class ' is 1, if object type is not license plate, class ' is 0；Latter four of array represent mesh
Mark the rectangle frame location information where object, wherein x ', y ' the upper left angular coordinate of rectangle frame is represented, width ' represents rectangle
The width of frame, height ' represent the height of rectangle frame；
License plate area image is extracted from the vehicle face area image by the rectangle frame location information.
9. a kind of license plate number automatic Verification method as described in claim 1, which is characterized in that if the vehicle face in step s 5
Image is unverified, then records the result of the action of entire treatment process and to be uploaded to server for statistical analysis.
10. a kind of license plate number automatic checkout system characterized by comprising
Memory is configured as storing data and computer program instructions；
The processor communicated is established with the memory, the processor is executed the computer program instructions and wanted with perform claim
The step of seeking any one of 1 to 9 above method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910475255.6A CN110288006A (en) | 2019-06-03 | 2019-06-03 | A kind of license plate number automatic Verification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910475255.6A CN110288006A (en) | 2019-06-03 | 2019-06-03 | A kind of license plate number automatic Verification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110288006A true CN110288006A (en) | 2019-09-27 |
Family
ID=68003235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910475255.6A Pending CN110288006A (en) | 2019-06-03 | 2019-06-03 | A kind of license plate number automatic Verification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288006A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909742A (en) * | 2019-11-19 | 2020-03-24 | 上海眼控科技股份有限公司 | License plate detection method, system, platform and storage medium |
| CN111599173A (en) * | 2020-05-12 | 2020-08-28 | 杭州云视通互联网科技有限公司 | Vehicle information automatic registration method, computer equipment and readable storage medium |
| CN111639640A (en) * | 2020-04-24 | 2020-09-08 | 深圳市金溢科技股份有限公司 | License plate recognition method, device and equipment based on artificial intelligence |
| CN111898974A (en) * | 2020-07-09 | 2020-11-06 | 上海眼控科技股份有限公司 | Vehicle inspection rechecking auxiliary method and device, computer equipment and storage medium |
| CN113780244A (en) * | 2021-10-12 | 2021-12-10 | 山东矩阵软件工程股份有限公司 | Vehicle anti-license plate replacement detection method and system |
| CN117115765A (en) * | 2023-10-16 | 2023-11-24 | 东方电子股份有限公司 | Fishing boat arrival and departure supervision method and system based on vision |
-
2019
- 2019-06-03 CN CN201910475255.6A patent/CN110288006A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909742A (en) * | 2019-11-19 | 2020-03-24 | 上海眼控科技股份有限公司 | License plate detection method, system, platform and storage medium |
| CN111639640A (en) * | 2020-04-24 | 2020-09-08 | 深圳市金溢科技股份有限公司 | License plate recognition method, device and equipment based on artificial intelligence |
| CN111639640B (en) * | 2020-04-24 | 2023-11-14 | 深圳市金溢科技股份有限公司 | License plate recognition method, device and equipment based on artificial intelligence |
| CN111599173A (en) * | 2020-05-12 | 2020-08-28 | 杭州云视通互联网科技有限公司 | Vehicle information automatic registration method, computer equipment and readable storage medium |
| CN111898974A (en) * | 2020-07-09 | 2020-11-06 | 上海眼控科技股份有限公司 | Vehicle inspection rechecking auxiliary method and device, computer equipment and storage medium |
| CN113780244A (en) * | 2021-10-12 | 2021-12-10 | 山东矩阵软件工程股份有限公司 | Vehicle anti-license plate replacement detection method and system |
| CN117115765A (en) * | 2023-10-16 | 2023-11-24 | 东方电子股份有限公司 | Fishing boat arrival and departure supervision method and system based on vision |
| CN117115765B (en) * | 2023-10-16 | 2024-01-09 | 东方电子股份有限公司 | Fishing boat arrival and departure supervision method and system based on vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288006A (en) | A kind of license plate number automatic Verification method and system | |
| CN104166841B (en) | The quick detection recognition methods of pedestrian or vehicle is specified in a kind of video surveillance network | |
| CN109447076A (en) | A kind of vehicle VIN code recognition detection method for vehicle annual test | |
| CN104268539B (en) | A kind of high performance face identification method and system | |
| CN108875600A (en) | A kind of information of vehicles detection and tracking method, apparatus and computer storage medium based on YOLO | |
| CA3154025A1 (en) | Interactive behavior recognizing method, device, computer equipment and storage medium | |
| CN107818322A (en) | A kind of vehicle VIN code tampering detection system and methods for vehicle annual test | |
| CN109344835A (en) | Altering detecting method based on vehicle VIN code character position | |
| CN109784326A (en) | A kind of vehicle chassis detection method based on deep learning | |
| CN103793708B (en) | A kind of multiple dimensioned car plate precise positioning method based on motion correction | |
| CN109376631A (en) | A kind of winding detection method and device neural network based | |
| CN104809452A (en) | Fingerprint identification method | |
| CN106340044A (en) | Camera external parameter automatic calibration method and calibration device | |
| CN110490905A (en) | A kind of method for tracking target based on YOLOv3 and DSST algorithm | |
| CN107452015A (en) | A kind of Target Tracking System with re-detection mechanism | |
| CN112001219B (en) | Multi-angle multi-face recognition attendance checking method and system | |
| CN107958200A (en) | A kind of intelligent checking system and method for car repacking exhaust fan | |
| CN106203237A (en) | The recognition methods of container-trailer numbering and device | |
| CN108257125B (en) | Depth image quality non-reference evaluation method based on natural scene statistics | |
| CN108182695A (en) | Target following model training method and device, electronic equipment and storage medium | |
| CN107798301A (en) | A kind of signature detection system and method for vehicle annual test | |
| CN109684986A (en) | A kind of vehicle analysis method and system based on automobile detecting following | |
| CN114494161A (en) | Pantograph foreign matter detection method and device based on image contrast and storage medium | |
| CN105989600A (en) | Characteristic point distribution statistics-based power distribution network device appearance detection method and system | |
| CN116229052A (en) | Method for detecting state change of substation equipment based on twin network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190927 |
|
| WD01 | Invention patent application deemed withdrawn after publication |