CN107909017A - The method, apparatus and system of Car license recognition under a kind of complex background - Google Patents
The method, apparatus and system of Car license recognition under a kind of complex background Download PDFInfo
- Publication number
- CN107909017A CN107909017A CN201711078549.2A CN201711078549A CN107909017A CN 107909017 A CN107909017 A CN 107909017A CN 201711078549 A CN201711078549 A CN 201711078549A CN 107909017 A CN107909017 A CN 107909017A
- Authority
- CN
- China
- Prior art keywords
- image
- plate
- car
- vehicle image
- license
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Character Discrimination (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides recognition methods, device and the system of car plate under a kind of complex background, relative to prior art vehicle under complex background, cannot quickly, the problem of car plate is recognized accurately, recognition methods, device and the system of car plate recover vehicle image, pre-process vehicle image by collection vehicle image under a kind of complex background provided by the invention, positioning licence plate image, split characters on license plate, and identify car plate, as a result export；The number-plate number can be identified fast and accurately under complex background.
Description
Technical field
The present invention relates to Car license recognition field, more particularly to the recognition methods of car plate under a kind of complex background, device with
And system.
Background technology
As people's living standard gradually steps up, more and more families have purchased automobile.Each automobile is equipped with car
Board, identity card of the car plate equivalent to automobile.
Car license recognition is very crucial in intelligent transportation.The continuous development of highway, is License Plate Identification technology
Development brings infinite commercial opportunities.But the more difficult identification of Chinese character in the artificial and natural cause interference of numerous complicated and China's car plate, makes state
Interior product is mature on the whole seldom, need to increase the research to license plate recognition technology.Because mainly identifying car plate outdoors, there is the back of the body
The factor interference such as scape complexity, Changes in weather, motion blur, image inclination.
Currently, it there is no technology adaptable, that car plate can be fast and accurately identified under complex background.
The content of the invention
It is an object of the present invention to provide the recognition methods of car plate, device and system under a kind of complex background,
Current vehicle is solved under complex background, it is impossible to quickly, car plate is recognized accurately.
In a first aspect, the method that the embodiment of the present application provides Car license recognition under a kind of complex background, the described method includes：
Step S101：Collection vehicle image；
Step S102：Recover vehicle image；
Step S103：Pre-process vehicle image；
Step S104：Positioning licence plate image；
Step S105：Split characters on license plate, and identify car plate；
Step S106：As a result export.
With reference to the application's in a first aspect, in second of embodiment of the application first aspect, step S103：In advance
Vehicle image is handled, including:The pretreatment is gray proces, obtains gray level image, and with histogram equalization method to ash
Spend image enhancement.
With reference to the application's in a first aspect, in the third embodiment of the application first aspect, step S104：It is fixed
Position license plate image, positions license plate image with the textural characteristics of car plate, further includes：Slant Rectify is carried out to license plate image, is used
Hough corrections calculating method is corrected.
With reference to the application's in a first aspect, in the 4th kind of embodiment of the application first aspect, step S105：Point
Characters on license plate is cut, and identifies car plate, is further included：Character picture is classified according to similarity degree, first using support vector regression
Indistinguishable character is segmented to low-resolution image rough sort, then with high-resolution image.
Second aspect, the embodiment of the present application provide a kind of device of Car license recognition under complex background, including：
Image acquisition units, for collection vehicle image；
Image restoration unit, for recovering vehicle image；
Image pre-processing unit, for pre-processing vehicle image；
Positioning unit, for positioning licence plate image；
Recognition unit, for splitting characters on license plate, and identifies car plate；
Output unit, exports for result.
With reference to the second aspect of the application, in second of embodiment of the application first aspect, image preprocessing
Unit, including:For gray proces, gray level image is obtained, and gray level image is strengthened with histogram equalization method.
With reference to the second aspect of the application, in the third embodiment of the application first aspect, positioning unit, is used
License plate image is positioned in the textural characteristics of car plate, is further included：For carrying out Slant Rectify to license plate image, rectified using Hough
Positive calculating method is corrected.
With reference to the second aspect of the application, in the 4th kind of embodiment of the application first aspect, recognition unit, is used
In segmentation characters on license plate, and identify car plate, further include：For character picture to be classified according to similarity degree, first using support to
Amount regression machine segments indistinguishable character to low-resolution image rough sort, then with high-resolution image.
The third aspect, the system that the embodiment of the present application provides Car license recognition under a kind of complex background, including：Host computer and figure
As collector；
Described image collector is connected with the host computer；
Described image collector, for collection vehicle image；
The host computer, for collection vehicle image, recovers vehicle image, pre-processes vehicle image, positioning licence plate image,
Split characters on license plate, and identify car plate, as a result export.
The method, apparatus and system of Car license recognition under a kind of complex background provided in an embodiment of the present invention, relative to existing
There is technology vehicle under complex background, it is impossible to quickly, the problem of car plate, a kind of complex background provided by the invention is recognized accurately
Recognition methods, device and the system of lower car plate are recovered vehicle image, pre-process vehicle image, determined by collection vehicle image
Position license plate image, splits characters on license plate, and identifies car plate, as a result exports；Car plate can be identified fast and accurately under complex background
Number.
Brief description of the drawings
Some specific embodiments of detailed description of the present invention by way of example, and not by way of limitation with reference to the accompanying drawings hereinafter.
Identical reference numeral denotes same or similar component or part in attached drawing.It should be appreciated by those skilled in the art that these
What attached drawing was not necessarily drawn to scale.In attached drawing：
Fig. 1 is a kind of method flow diagram of License Plate Identification of one embodiment of the invention.
Embodiment
This below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out it is clear,
Complete description, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art obtained without making creative work it is all its
His embodiment, belongs to the scope of protection of the invention.
Referring to Fig. 1, in a first aspect, a kind of method of License Plate Identification provided by the embodiments of the present application, it is described including
Following steps：
Step S101：Collection vehicle image；
Initial acquisition is carried out to vehicle image.
Step S102：Recover vehicle image；
During being absorbed, transmit, storing and being handled to vehicle image etc., some distortions can be caused to cause vehicle figure
As degenerating, image can produce fuzzy, distortion, have phenomena such as noise.Recover vehicle image to seek to recovering vehicle image
Quality is improved, and recovers the given original true appearance for recovering vehicle image as far as possible.Preferably, Wiener filtering is passed through
Method, carries out vehicle image recovery.Wiener filtering is the recovery best to image in statistical significance, noise can be amplified and carried out certainly
Dynamic to suppress, noise is stronger, and its effect is bigger, so excessive amplification of the liftering to noise can be avoided.To not Noise
Blurred picture has preferable recovery effects.
Step S103：Pre-process vehicle image；
Since many factors influence, picture quality can all decline during Scenery Imaging.This process is just called image and moves back
Change.Due to the movement of vehicle, the change of natural light brightness, image capture device itself factor etc., vehicle image can be caused to move back
Change, disturb the extraction of license board information.Therefore vehicle image will be pre-processed, to improve image to image proper transformation
Data, remove or weaken garbage, suppress unnecessary deformation or strengthen some information important to subsequent step, with increase
The reliability of image recognition.
Step S104：Positioning licence plate image；
Testing vehicle register board is positioned using mathematical morphology.Mathematical morphology is with necessarily to correspondingly-shaped in image
Morphological structuring element is measured and extracted to analyze and identify image.It, which is applied to image procossing, can greatly simplify view data, remove
Irrelevant structure is gone, keeps itself basic configuration characteristic.Therefore uneven illumination, color can be overcome using mathematical morphology positioning
The problem of distortion etc. causes, it is ensured that accurate positioning, and car plate leakage positioning phenomenon is not had.
Step S105：Split characters on license plate, and identify car plate；
License Plate Character Segmentation is that the character in license plate image is split after car plate is accurately positioned, and obtains each character
Image.The result of Character segmentation is very big to the influential effect of each character recognition.
Using upright projection combination car plate priori separating character, with bilinear interpolation value method to character normalization, use
Improved Fuzzy Support Vector Regression carries out character recognition, improves recognition speed and the accuracy of car plate.
Step S106：As a result export.
It is an object of the present invention to provide the recognition methods of car plate, device and system under a kind of complex background,
Current vehicle is solved under complex background, it is impossible to quickly, car plate is recognized accurately.
Specifically, step S103：Vehicle image is pre-processed, including:The pretreatment is gray proces, obtains gray-scale map
Picture, and gray level image is strengthened with histogram equalization method.
Gray scale refers to pure white, black and a series of intermediate colors from black to white in both.Gray scale highest is equivalent to highest
It is black, be exactly black.Gray scale is minimum black equivalent to minimum, i.e., pure white.Generally, with a byte come table after pixel value quantifies
Show.The gray value for there are black-ash-white consecutive variations is such as quantified as 256 gray levels, the scope of gray value is 0-255, is represented bright
For degree from depth to shallow, the color in correspondence image is from black to white.Black-and-white photograph contains all gray tones between black and white,
Each pixel value is one kind in 256 kinds of gray scales between black and white.
RGB (R, G, the B) values of each pixel of the coloured image acquired are converted into pair according to gray processing calculation formula
The gray value answered.
The rgb color be by red (R), green (G), blue (B) three Color Channels change and they mutually it
Between superposition obtain miscellaneous color, RGB is the color for representing three passages of red, green, blue, this standard is almost
Include all colours that human eyesight can perceive, be at present with one of most wide color system.
Gray processing calculation formula is corresponding gray value P, that is, passes through formula P=0.212671×R+0.715160×G+0.
072169 × B, is calculated gray value.Such as R=208, G=210, B=199, pass through the formula P=0.212671×R+
0.715160×G+0.072169 × B=0.212671×208+0.715160×210+0.072169 × 199=208.
780799, by the formula, change into gray level image.
Histogram equalization method can remove chosen by parameter, recovery algorithms produce ring with the factor such as noise in itself.
Specifically, step S104：Positioning licence plate image, positions license plate image with the textural characteristics of car plate, further includes：It is right
License plate image carries out Slant Rectify, is corrected using Hough corrections calculating method.
License Plate refers to the regional location that vehicle license is judged by the feature of license plate area, and is split.Car
Board zone location it is accurate whether will directly influence subsequent step.The inclination of license plate image is carried out with Hough corrections calculating method
Correction, the pinpoint method of license plate image is carried out with the textural characteristics of car plate, can preferably realize that license plate image positions.
Specifically, step S105：Split characters on license plate, and identify car plate, further include：According to similarity degree character picture
Classification, first using support vector regression to low-resolution image rough sort, then with high-resolution image to indistinguishable word
Symbol subdivision.
The method of Car license recognition under a kind of complex background provided in an embodiment of the present invention, relative to prior art vehicle multiple
Under miscellaneous background, it is impossible to quick, be recognized accurately the problem of car plate, the identification side of car plate under a kind of complex background provided by the invention
Method, device and system recover vehicle image, pre-process vehicle image, positioning licence plate image, segmentation by collection vehicle image
Characters on license plate, and identify car plate, as a result export；The number-plate number can be identified fast and accurately under complex background.
Second aspect, the embodiment of the present application provide a kind of device of Car license recognition under complex background, including：
Image acquisition units, for collection vehicle image；
Image restoration unit, for recovering vehicle image；
Image pre-processing unit, for pre-processing vehicle image；
Positioning unit, for positioning licence plate image；
Recognition unit, for splitting characters on license plate, and identifies car plate；
Output unit, exports for result.
Specifically, image pre-processing unit, including:For gray proces, gray level image is obtained, and use histogram equalization
Change method strengthens gray level image.
Gray scale refers to pure white, black and a series of intermediate colors from black to white in both.Gray scale highest is equivalent to highest
It is black, be exactly black.Gray scale is minimum black equivalent to minimum, i.e., pure white.Generally, with a byte come table after pixel value quantifies
Show.The gray value for there are black-ash-white consecutive variations is such as quantified as 256 gray levels, the scope of gray value is 0-255, is represented bright
For degree from depth to shallow, the color in correspondence image is from black to white.Black-and-white photograph contains all gray tones between black and white,
Each pixel value is one kind in 256 kinds of gray scales between black and white.
RGB (R, G, the B) values of each pixel of the coloured image acquired are converted into pair according to gray processing calculation formula
The gray value answered.
The rgb color be by red (R), green (G), blue (B) three Color Channels change and they mutually it
Between superposition obtain miscellaneous color, RGB is the color for representing three passages of red, green, blue, this standard is almost
Include all colours that human eyesight can perceive, be at present with one of most wide color system.
Gray processing calculation formula is corresponding gray value P, that is, passes through formula P=0.212671×R+0.715160×G+0.
072169 × B, is calculated gray value.Such as R=208, G=210, B=199, pass through the formula P=0.212671×R+
0.715160×G+0.072169 × B=0.212671×208+0.715160×210+0.072169 × 199=208.
780799, by the formula, change into gray level image.
Histogram equalization method can remove chosen by parameter, recovery algorithms produce ring with the factor such as noise in itself.
Specifically, positioning unit, the textural characteristics for car plate position license plate image, further include：For to car plate figure
As carrying out Slant Rectify, corrected using Hough corrections calculating method.
License Plate refers to the regional location that vehicle license is judged by the feature of license plate area, and is split.Car
Board zone location it is accurate whether will directly influence subsequent step.The inclination of license plate image is carried out with Hough corrections calculating method
Correction, the pinpoint method of license plate image is carried out with the textural characteristics of car plate, can preferably realize that license plate image positions.
Specifically, recognition unit, for splitting characters on license plate, and identifies car plate, further includes：For according to similarity degree handle
Character picture is classified, first using support vector regression to low-resolution image rough sort, then with high-resolution image to difficulty
The character subdivision of differentiation.
The device of Car license recognition under a kind of complex background provided in an embodiment of the present invention, relative to prior art vehicle multiple
Under miscellaneous background, it is impossible to quick, be recognized accurately the problem of car plate, the identification side of car plate under a kind of complex background provided by the invention
Method, device and system recover vehicle image, pre-process vehicle image, positioning licence plate image, segmentation by collection vehicle image
Characters on license plate, and identify car plate, as a result export；The number-plate number can be identified fast and accurately under complex background.
The third aspect, the system that the embodiment of the present invention also provides Car license recognition under a kind of complex background, it is characterised in that bag
Include：Host computer and image acquisition device；
Described image collector is connected with the host computer；
Described image collector, for collection vehicle image；
The host computer, for collection vehicle image, recovers vehicle image, pre-processes vehicle image, positioning licence plate image,
Split characters on license plate, and identify car plate, as a result export.
The method, apparatus and system of Car license recognition under a kind of complex background provided in an embodiment of the present invention, relative to existing
There is technology vehicle under complex background, it is impossible to quickly, the problem of car plate, a kind of complex background provided by the invention is recognized accurately
Recognition methods, device and the system of lower car plate are recovered vehicle image, pre-process vehicle image, determined by collection vehicle image
Position license plate image, splits characters on license plate, and identifies car plate, as a result exports；Car plate can be identified fast and accurately under complex background
Number.
So far, although those skilled in the art will appreciate that detailed herein have shown and described multiple showing for the present invention
Example property embodiment, still, without departing from the spirit and scope of the present invention, still can according to the present invention disclosure it is direct
Determine or derive many other variations or modifications for meeting the principle of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (9)
1. a kind of method of Car license recognition under complex background, it is characterised in that the described method includes：
Step S101：Collection vehicle image；
Step S102：Recover vehicle image；
Step S103：Pre-process vehicle image；
Step S104：Positioning licence plate image；
Step S105：Split characters on license plate, and identify car plate；
Step S106：As a result export.
2. according to the method described in claim 1, it is characterized in that, step S103：Vehicle image is pre-processed, including:It is described pre-
Handle as gray proces, obtain gray level image, and with histogram equalization method to gray level image enhancing.
3. according to the method described in claim 1, it is characterized in that, step S104：Positioning licence plate image, it is special with the texture of car plate
Sign positions license plate image, further includes：Slant Rectify is carried out to license plate image, is corrected using Hough corrections calculating method.
4. according to the method described in claim 1, it is characterized in that, step S105：Split characters on license plate, and identify car plate, also
Including：Character picture is classified according to similarity degree, first using support vector regression to low-resolution image rough sort, then with
High-resolution image segments indistinguishable character.
A kind of 5. device of Car license recognition under complex background, it is characterised in that including：
Image acquisition units, for collection vehicle image；
Image restoration unit, for recovering vehicle image；
Image pre-processing unit, for pre-processing vehicle image；
Positioning unit, for positioning licence plate image；
Recognition unit, for splitting characters on license plate, and identifies car plate；
Output unit, exports for result.
6. device according to claim 5, it is characterised in that image pre-processing unit, including:For gray proces, obtain
Gray level image is obtained, and gray level image is strengthened with histogram equalization method.
7. device according to claim 5, it is characterised in that positioning unit, the textural characteristics for car plate are to car plate figure
As positioning, further include：For carrying out Slant Rectify to license plate image, corrected using Hough corrections calculating method.
8. device according to claim 5, it is characterised in that recognition unit, for splitting characters on license plate, and identifies car
Board, further includes：It is first thick to low-resolution image using support vector regression for character picture to be classified according to similarity degree
Classification, then indistinguishable character is segmented with high-resolution image.
A kind of 9. system of Car license recognition under complex background, it is characterised in that including：Host computer and image acquisition device；
Described image collector is connected with the host computer；
Described image collector, for collection vehicle image；
The host computer, for collection vehicle image, recovers vehicle image, pre-processes vehicle image, positioning licence plate image, segmentation
Characters on license plate, and identify car plate, as a result export.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711078549.2A CN107909017A (en) | 2017-11-06 | 2017-11-06 | The method, apparatus and system of Car license recognition under a kind of complex background |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711078549.2A CN107909017A (en) | 2017-11-06 | 2017-11-06 | The method, apparatus and system of Car license recognition under a kind of complex background |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107909017A true CN107909017A (en) | 2018-04-13 |
Family
ID=61843426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711078549.2A Pending CN107909017A (en) | 2017-11-06 | 2017-11-06 | The method, apparatus and system of Car license recognition under a kind of complex background |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107909017A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5943480A (en) * | 1982-09-03 | 1984-03-10 | Ricoh Co Ltd | Character recognizing method |
| CN1037035A (en) * | 1988-04-08 | 1989-11-08 | 神经医学系统公司 | Automated cytological specimen classification system and method based on neural network |
| JPH04289987A (en) * | 1991-03-19 | 1992-10-14 | Matsushita Electric Ind Co Ltd | Character recognizing device |
| JPH08272884A (en) * | 1995-03-30 | 1996-10-18 | Oki Electric Ind Co Ltd | Form classifying and processing method and system |
| CN102880859A (en) * | 2012-08-30 | 2013-01-16 | 华南理工大学 | Method for recognizing number plate |
| CN104156731A (en) * | 2014-07-31 | 2014-11-19 | 成都易默生汽车技术有限公司 | License plate recognition system based on artificial neural network and method |
| US20150049942A1 (en) * | 2013-08-14 | 2015-02-19 | Qualcomm Incorporated | Performing vocabulary-based visual search using multi-resolution feature descriptors |
| CN104376297A (en) * | 2013-08-12 | 2015-02-25 | 株式会社理光 | Detection method and device for linear indication signs on road |
| CN104809461A (en) * | 2015-05-08 | 2015-07-29 | 内蒙古科技大学 | License plate recognition method and system combining sequence image super-resolution reconstruction |
| CN105335710A (en) * | 2015-10-22 | 2016-02-17 | 合肥工业大学 | Fine vehicle model identification method based on multi-stage classifier |
-
2017
- 2017-11-06 CN CN201711078549.2A patent/CN107909017A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5943480A (en) * | 1982-09-03 | 1984-03-10 | Ricoh Co Ltd | Character recognizing method |
| CN1037035A (en) * | 1988-04-08 | 1989-11-08 | 神经医学系统公司 | Automated cytological specimen classification system and method based on neural network |
| JPH04289987A (en) * | 1991-03-19 | 1992-10-14 | Matsushita Electric Ind Co Ltd | Character recognizing device |
| JPH08272884A (en) * | 1995-03-30 | 1996-10-18 | Oki Electric Ind Co Ltd | Form classifying and processing method and system |
| CN102880859A (en) * | 2012-08-30 | 2013-01-16 | 华南理工大学 | Method for recognizing number plate |
| CN104376297A (en) * | 2013-08-12 | 2015-02-25 | 株式会社理光 | Detection method and device for linear indication signs on road |
| US20150049942A1 (en) * | 2013-08-14 | 2015-02-19 | Qualcomm Incorporated | Performing vocabulary-based visual search using multi-resolution feature descriptors |
| CN104156731A (en) * | 2014-07-31 | 2014-11-19 | 成都易默生汽车技术有限公司 | License plate recognition system based on artificial neural network and method |
| CN104809461A (en) * | 2015-05-08 | 2015-07-29 | 内蒙古科技大学 | License plate recognition method and system combining sequence image super-resolution reconstruction |
| CN105335710A (en) * | 2015-10-22 | 2016-02-17 | 合肥工业大学 | Fine vehicle model identification method based on multi-stage classifier |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103971126B (en) | A kind of traffic sign recognition method and device | |
| CN104392205B (en) | A kind of recognition methods and system of improper license plate | |
| KR101403876B1 (en) | Method and Apparatus for Vehicle License Plate Recognition | |
| CN103198315B (en) | Based on the Character Segmentation of License Plate of character outline and template matches | |
| CN104715239B (en) | A kind of vehicle color identification method based on defogging processing and weight piecemeal | |
| CN103310211B (en) | A kind ofly fill in mark recognition method based on image procossing | |
| CN110309806B (en) | A gesture recognition system and method based on video image processing | |
| CN106384117B (en) | A kind of vehicle color identification method and device | |
| CN107066972B (en) | Natural scene text detection method based on multi-channel extreme value region | |
| CN104408449A (en) | Intelligent mobile terminal scene character processing method | |
| US20090148043A1 (en) | Method for extracting text from a compound digital image | |
| CN107767379A (en) | Pcb board marks print quality inspection method | |
| CN101584624A (en) | Guideboard recognition blind-guide device and method thereof based on DSP | |
| CN105787475A (en) | Traffic sign detection and identification method under complex environment | |
| CN105893960A (en) | Road traffic sign detecting method based on phase symmetry | |
| CN111429462A (en) | License plate positioning method based on edge detection and mathematical morphology | |
| CN104156703B (en) | License plate locating method and system based on color texture | |
| CN115082776A (en) | Electric energy meter automatic detection system and method based on image recognition | |
| CN108764230A (en) | A kind of bank's card number automatic identifying method based on convolutional neural networks | |
| CN105512662A (en) | Detection method and apparatus for unlicensed vehicle | |
| Jia et al. | Design of Traffic Sign Detection and Recognition Algorithm Based on Template Matching | |
| CN113392819B (en) | Batch academic image automatic segmentation and labeling device and method | |
| CN110298347B (en) | Method for identifying automobile exhaust analyzer screen based on GrayWorld and PCA-CNN | |
| Ouji et al. | Chromatic/achromatic separation in noisy document images | |
| CN107909017A (en) | The method, apparatus and system of Car license recognition under a kind of complex background |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180413 |
|
| WD01 | Invention patent application deemed withdrawn after publication |