CN103279739A - Fake license plate detection method based on vehicle characteristic matching - Google Patents

Fake license plate detection method based on vehicle characteristic matching Download PDF

Info

Publication number
CN103279739A
CN103279739A CN2013101757635A CN201310175763A CN103279739A CN 103279739 A CN103279739 A CN 103279739A CN 2013101757635 A CN2013101757635 A CN 2013101757635A CN 201310175763 A CN201310175763 A CN 201310175763A CN 103279739 A CN103279739 A CN 103279739A
Authority
CN
China
Prior art keywords
current pixel
channel value
belong
bin
headstock
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.)
Granted
Application number
CN2013101757635A
Other languages
Chinese (zh)
Other versions
CN103279739B (en
Inventor
尚凌辉
蒋宗杰
王弘玥
高勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZHEJIANG ICARE VISION TECHNOLOGY Co Ltd
Original Assignee
ZHEJIANG ICARE VISION TECHNOLOGY Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ZHEJIANG ICARE VISION TECHNOLOGY Co Ltd filed Critical ZHEJIANG ICARE VISION TECHNOLOGY Co Ltd
Priority to CN201310175763.5A priority Critical patent/CN103279739B/en
Publication of CN103279739A publication Critical patent/CN103279739A/en
Application granted granted Critical
Publication of CN103279739B publication Critical patent/CN103279739B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention relates to a fake license plate detection method based on vehicle characteristic matching. According to the fake license plate detection method based on vehicle characteristic matching, the distribution rule of a prior license plate on a vehicle is utilized to normalize vehicle images according to the corresponding ratio of the license plate, and a headstock area corresponding to the license plate is selected so as to generate the corresponding headstock characteristic. According to the comparison of a characteristic database, whether the current characteristic is matched with the characteristic of a vehicle corresponding to the license plate in the database is obtained. According to the fake license plate detection method based on the vehicle characteristic matching, which is disclosed by the invention, the headstock characteristic can be utilized under the situation that the precise position of the license plate is known, the similarity between the headstock to be judged and the headstock in the database can be accurately judged, and the fake license plate detection method is slightly influenced by the environmental factor and is free from the limitation of a vehicle logo identification type.

Description

A kind of cover board detection method based on the vehicle characteristics coupling
Technical field
The invention belongs to the intelligent transport technology field, relate to a kind of cover board detection method based on the vehicle characteristics coupling.
Background technology
Identification mainly is to judge to determine by the car mark whether vehicle has cover board suspicion to fake-licensed car in the industry at present.It is very high that present this existent method identifies other requirement to car, and the car target is of a great variety, even the car mark of a brand also has various ways, and car target kind is also in continuous increase.General car identifies other algorithm can only tolerate about 20 kinds of car targets identification, detects to fake-licensed car and has brought very big difficulty.
Summary of the invention
The invention provides a kind of cover board detection method based on the vehicle matching characteristic, by using the distribution rule of priori car plate on vehicle, with the corresponding ratio normalization of vehicle image according to car plate, and the headstock zone of selection car plate correspondence, corresponding headstock feature generated with this.By the comparison of property data base, obtain the whether corresponding vehicle characteristics of car plate in the matching database of current feature, this method has overcome general car and has identified other algorithm and be suitable for restriction, thereby has improved the accuracy that the cover board detects.
A kind of cover board detection method based on the vehicle matching characteristic comprises:
(1) car plate width and the high computational headstock zone R that utilizes car plate identification to obtain.The headstock zone is divided into 15 sub-pieces
Figure 2013101757635100002DEST_PATH_IMAGE002
(2) the vehicle body image is carried out the pre-service of normalization, sharpen edges and removal noise.
(3) calculate each sub-piece
Figure 885980DEST_PATH_IMAGE002
The hsv color space, the color of each sub-piece is carried out statistics with histogram.
(4) calculate each sub-piece
Figure 111556DEST_PATH_IMAGE002
N key point
Figure 2013101757635100002DEST_PATH_IMAGE004
Textural characteristics.
(5) characteristic sequence of the current headstock of comparison
Figure 2013101757635100002DEST_PATH_IMAGE006
Headstock characteristic sequence with corresponding license plate number in the database
Figure 2013101757635100002DEST_PATH_IMAGE008
If both covariances (Mahalanobis) distances is less than 0.4 then this car does not overlap board, otherwise it is fake-licensed car.
(1) described car plate width and the high computational headstock zone R that utilizes car plate identification to obtain specifically comprises: according to the origin coordinates of car plate in the middle of image
Figure 2013101757635100002DEST_PATH_IMAGE010
With the car plate width
Figure 2013101757635100002DEST_PATH_IMAGE012
, the relative position of calculating headstock.
Figure 2013101757635100002DEST_PATH_IMAGE014
;
;
Figure 2013101757635100002DEST_PATH_IMAGE018
;
Figure 2013101757635100002DEST_PATH_IMAGE020
;
(
Figure 2013101757635100002DEST_PATH_IMAGE022
The origin coordinates in vehicle body zone,
Figure 2013101757635100002DEST_PATH_IMAGE024
The width of vehicle body,
Figure 2013101757635100002DEST_PATH_IMAGE026
The height of vehicle body).
(2) described the vehicle body image is carried out the pre-service of normalization, sharpen edges and removal noise, specifically may further comprise the steps:
1) adopts known bilinear interpolation method, with the vehicle body image normalization extremely
Figure 2013101757635100002DEST_PATH_IMAGE028
2) use known gaussian filtering, the license plate image after the normalization is transported capable sharpen edges handle.
3) adopt known Gauss's low-pass filtering method, to the noise processed of removing of the license plate image behind the sharpen edges.
(3) calculate each sub-piece
Figure 887358DEST_PATH_IMAGE002
The hsv color space, the color of each sub-piece is carried out the statistics with histogram method comprises:
1) the known RGB of employing changes each the sub-piece among the HSV algorithm calculating headstock zone R
Figure 68941DEST_PATH_IMAGE002
Do color conversion.
2) to each sub-piece
Figure 320930DEST_PATH_IMAGE002
Carry out statistics with histogram, statistic histogram is divided into 10 class Bin[i] [10], i
Figure 2013101757635100002DEST_PATH_IMAGE030
[0,14], each pixel wherein
Figure 2013101757635100002DEST_PATH_IMAGE032
Divide according to following rule:
If a) current pixel The V channel value
Figure 2013101757635100002DEST_PATH_IMAGE034
, current pixel Belong to Bin[0];
B) if current pixel
Figure 646455DEST_PATH_IMAGE032
The V channel value , and the S channel value
Figure 2013101757635100002DEST_PATH_IMAGE038
, current pixel
Figure 882395DEST_PATH_IMAGE032
Belong to Bin[1];
C) if current pixel
Figure 331831DEST_PATH_IMAGE032
The V channel value , and the S channel value
Figure 2013101757635100002DEST_PATH_IMAGE042
, current pixel
Figure 888583DEST_PATH_IMAGE032
Belong to Bin[2];
D) if current pixel
Figure 156010DEST_PATH_IMAGE032
The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE044
, and S, V channel value belong to (0.2,1], current pixel
Figure 828431DEST_PATH_IMAGE032
Belong to Bin[3];
E) if current pixel
Figure 499583DEST_PATH_IMAGE032
The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE046
, and S, V channel value belong to (0.2,1], current pixel
Figure 46977DEST_PATH_IMAGE032
Belong to Bin[4];
F) if current pixel
Figure 870708DEST_PATH_IMAGE032
The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE048
, and S, V channel value belong to (0.2,1], current pixel
Figure 233073DEST_PATH_IMAGE032
Belong to Bin[5];
G) if current pixel
Figure 391522DEST_PATH_IMAGE032
The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE050
, and S, V channel value belong to (0.2,1], current pixel
Figure 916175DEST_PATH_IMAGE032
Belong to Bin[6];
H) if current pixel
Figure 843680DEST_PATH_IMAGE032
The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE052
, and S, V channel value belong to (0.2,1], current pixel Belong to Bin[7];
I) if current pixel The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE054
, and S, V channel value belong to (0.2,1], current pixel
Figure 379463DEST_PATH_IMAGE032
Belong to Bin[8];
J) if current pixel
Figure 364736DEST_PATH_IMAGE032
The H channel value
Figure 2013101757635100002DEST_PATH_IMAGE056
, and S, V channel value belong to (0.2,1], current pixel
Figure 549861DEST_PATH_IMAGE032
Belong to Bin[9];
All sub-pieces
Figure 682902DEST_PATH_IMAGE002
Bin[i] [10] totally 150 dimensional features.
(4) calculate the texture histogram feature and comprise, adopt each sub-piece of known sift feature calculation
Figure 47893DEST_PATH_IMAGE002
N key point
Figure 763040DEST_PATH_IMAGE004
128 dimensional features.
(5) characteristic sequence of the current headstock of comparison
Figure 306016DEST_PATH_IMAGE006
Headstock characteristic sequence with corresponding license plate number in the database Comprise 150 dimension color characteristic Bin[i] [10] and
Figure DEST_PATH_IMAGE058
Individual sift feature is combined into the associating feature In existing property data base, search the headstock feature of this license plate number correspondence
Figure 333862DEST_PATH_IMAGE008
, calculate
Figure 47741DEST_PATH_IMAGE006
With
Figure 404641DEST_PATH_IMAGE008
The Mahalanobis distance.If both distances are less than 0.4 then this car does not overlap board, otherwise it is fake-licensed car.
Beneficial effect of the present invention: under the situation of the exact position of known car plate, can utilize the headstock feature, accurately judge the similarity of waiting to judge headstock in headstock and the database.And be subjected to environmental factor little, needn't be subjected to car to identify the restriction of other kind.Apply to intelligent transportation, distinguish the guarantee that provides favourable for fake-licensed car, have wide practical use.
Description of drawings
Fig. 1 is method flow diagram of the present invention.
Embodiment
The present invention is further illustrated below in conjunction with accompanying drawing.
As shown in Figure 1, a kind of cover board detection method based on the vehicle characteristics coupling comprises:
(1) car plate width and the high computational headstock zone R that utilizes car plate identification to obtain is according to the origin coordinates of car plate in the middle of image
Figure 862168DEST_PATH_IMAGE010
With the car plate width
Figure 286327DEST_PATH_IMAGE012
, the relative position of calculating headstock.
;
Figure 955916DEST_PATH_IMAGE016
;
Figure 217133DEST_PATH_IMAGE018
;
;
(
Figure 754742DEST_PATH_IMAGE022
The origin coordinates in vehicle body zone,
Figure 509071DEST_PATH_IMAGE024
The width of vehicle body,
Figure 557667DEST_PATH_IMAGE026
The height of vehicle body)
(2) the vehicle body image is carried out the pre-service of normalization, sharpen edges and removal noise, comprising:
1) adopts known bilinear interpolation method, with the vehicle body image normalization extremely
Figure 143370DEST_PATH_IMAGE028
2) use known gaussian filtering, the license plate image after the normalization is transported capable sharpen edges handle.
3) adopt known Gauss's low-pass filtering method, to the noise processed of removing of the license plate image behind the sharpen edges.
(3) calculate each sub-piece
Figure 386263DEST_PATH_IMAGE002
The hsv color space, the color of each sub-piece is carried out the statistics with histogram method comprises:
1) the known RGB of employing changes each the sub-piece among the HSV algorithm calculating headstock zone R Do color conversion.
2) to each sub-piece
Figure 965329DEST_PATH_IMAGE002
Carry out statistics with histogram, statistic histogram is divided into 10 class Bin[i] [10], i
Figure 917455DEST_PATH_IMAGE030
[0,14], each pixel wherein
Figure 314938DEST_PATH_IMAGE032
Divide according to following rule:
If a) current pixel
Figure 856909DEST_PATH_IMAGE032
The V channel value
Figure 998040DEST_PATH_IMAGE034
, current pixel
Figure 496018DEST_PATH_IMAGE032
Belong to Bin[0];
B) if current pixel
Figure 313670DEST_PATH_IMAGE032
The V channel value
Figure 592205DEST_PATH_IMAGE036
, and the S channel value
Figure 287759DEST_PATH_IMAGE038
, current pixel
Figure 702560DEST_PATH_IMAGE032
Belong to Bin[1];
C) if current pixel
Figure 959623DEST_PATH_IMAGE032
The V channel value , and the S channel value
Figure 880491DEST_PATH_IMAGE042
, current pixel Belong to Bin[2];
D) if current pixel
Figure 76297DEST_PATH_IMAGE032
The H channel value , and S, V channel value belong to (0.2,1], current pixel
Figure 537420DEST_PATH_IMAGE032
Belong to Bin[3];
E) if current pixel
Figure 926813DEST_PATH_IMAGE032
The H channel value
Figure 24213DEST_PATH_IMAGE046
, and S, V channel value belong to (0.2,1], current pixel
Figure 499057DEST_PATH_IMAGE032
Belong to Bin[4];
F) if current pixel The H channel value
Figure 751714DEST_PATH_IMAGE048
, and S, V channel value belong to (0.2,1], current pixel
Figure 269283DEST_PATH_IMAGE032
Belong to Bin[5];
G) if current pixel The H channel value
Figure 610583DEST_PATH_IMAGE050
, and S, V channel value belong to (0.2,1], current pixel
Figure 646672DEST_PATH_IMAGE032
Belong to Bin[6];
H) if current pixel The H channel value
Figure 33846DEST_PATH_IMAGE052
, and S, V channel value belong to (0.2,1], current pixel
Figure 951117DEST_PATH_IMAGE032
Belong to Bin[7];
I) if current pixel
Figure 169609DEST_PATH_IMAGE032
The H channel value
Figure 966664DEST_PATH_IMAGE054
, and S, V channel value belong to (0.2,1], current pixel
Figure 890014DEST_PATH_IMAGE032
Belong to Bin[8];
J) if current pixel
Figure 125823DEST_PATH_IMAGE032
The H channel value
Figure 949554DEST_PATH_IMAGE056
, and S, V channel value belong to (0.2,1], current pixel
Figure 979827DEST_PATH_IMAGE032
Belong to Bin[9];
All sub-pieces
Figure 75959DEST_PATH_IMAGE002
Bin[i] [10] totally 150 dimensional features.
(4) calculate the texture histogram feature and comprise, adopt each sub-piece of known sift feature calculation
Figure 833568DEST_PATH_IMAGE002
N key point
Figure 26652DEST_PATH_IMAGE004
128 dimensional features;
(5) characteristic sequence of the current headstock of comparison
Figure 978558DEST_PATH_IMAGE006
Headstock characteristic sequence with corresponding license plate number in the database
Figure 624303DEST_PATH_IMAGE008
Comprise 150 dimension color characteristic Bin[i] [10] and Individual sift feature is combined into the associating feature
Figure 191385DEST_PATH_IMAGE006
In existing property data base, search the headstock feature of this license plate number correspondence , calculate
Figure 447234DEST_PATH_IMAGE006
With
Figure 562958DEST_PATH_IMAGE008
The Mahalanobis distance.If both distances are less than 0.4 then this car does not overlap board, otherwise it is fake-licensed car.

Claims (5)

1. cover board detection method based on vehicle characteristics coupling is characterized in that the concrete steps of this method are as follows:
Car plate width and high computational headstock zone R that step (1) utilizes car plate identification to obtain are divided into 15 sub-pieces with the headstock zone
Figure 2013101757635100001DEST_PATH_IMAGE002
:
Step (2) is carried out the pre-service of normalization, sharpen edges and removal noise to the vehicle body image;
Step (3) is calculated each sub-piece
Figure 963895DEST_PATH_IMAGE002
The hsv color space, the color of each sub-piece is carried out statistics with histogram;
Step (4) is calculated each sub-piece
Figure 257604DEST_PATH_IMAGE002
N key point
Figure 2013101757635100001DEST_PATH_IMAGE004
Textural characteristics;
The characteristic sequence of the current headstock of step (5) comparison Headstock characteristic sequence with corresponding license plate number in the database
Figure 2013101757635100001DEST_PATH_IMAGE008
If both covariance distance is less than 0.4, then this car does not overlap board, otherwise is fake-licensed car.
2. a kind of cover board detection method based on vehicle characteristics coupling according to claim 1, it is characterized in that: headstock zone R is determined by the relative position of headstock in the step (1), specifically is according to the origin coordinates of car plate in the middle of image
Figure 2013101757635100001DEST_PATH_IMAGE010
With the car plate width
Figure 2013101757635100001DEST_PATH_IMAGE012
, can calculate the relative position of headstock;
Figure 2013101757635100001DEST_PATH_IMAGE014
；
Figure 2013101757635100001DEST_PATH_IMAGE016
；
Figure 2013101757635100001DEST_PATH_IMAGE018
；
Figure 2013101757635100001DEST_PATH_IMAGE020
；
Wherein
Figure DEST_PATH_IMAGE022
The origin coordinates in expression vehicle body zone,
Figure DEST_PATH_IMAGE024
The width of expression vehicle body,
Figure DEST_PATH_IMAGE026
The height of expression vehicle body.
3. a kind of cover board detection method based on vehicle characteristics coupling according to claim 1 is characterized in that: step (2) specifically:
1) adopts bilinear interpolation method, with the vehicle body image normalization extremely
Figure DEST_PATH_IMAGE028
2) adopt gaussian filtering, the license plate image after the normalization is transported capable sharpen edges handle;
3) adopt Gauss's low-pass filtering method, to the noise processed of removing of the license plate image behind the sharpen edges.
4. a kind of cover board detection method based on vehicle characteristics coupling according to claim 1 is characterized in that: step (3) specifically:
1) adopt RGB to change the HSV algorithm to each the sub-piece among the R of headstock zone
Figure 363094DEST_PATH_IMAGE002
Do color conversion;
2) to each sub-piece
Figure 552284DEST_PATH_IMAGE002
Carry out statistics with histogram, statistic histogram is divided into 10 class Bin[i] [10], i
Figure DEST_PATH_IMAGE030
[0,14], each pixel wherein
Figure DEST_PATH_IMAGE032
Divide according to following rule:
If a) current pixel
Figure 121937DEST_PATH_IMAGE032
The V channel value
Figure DEST_PATH_IMAGE034
, current pixel
Figure 209716DEST_PATH_IMAGE032
Belong to Bin[0];
B) if current pixel
Figure 68082DEST_PATH_IMAGE032
The V channel value
Figure DEST_PATH_IMAGE036
, and the S channel value
Figure DEST_PATH_IMAGE038
, current pixel
Figure 902439DEST_PATH_IMAGE032
Belong to Bin[1];
C) if current pixel
Figure 451232DEST_PATH_IMAGE032
The V channel value , and the S channel value
Figure DEST_PATH_IMAGE042
, current pixel
Figure 726225DEST_PATH_IMAGE032
Belong to Bin[2];
D) if current pixel
Figure 55575DEST_PATH_IMAGE032
The H channel value
Figure DEST_PATH_IMAGE044
, and S, V channel value belong to (0.2,1], current pixel
Figure 801945DEST_PATH_IMAGE032
Belong to Bin[3];
E) if current pixel The H channel value
Figure DEST_PATH_IMAGE046
, and S, V channel value belong to (0.2,1], current pixel Belong to Bin[4];
F) if current pixel
Figure 464855DEST_PATH_IMAGE032
The H channel value
Figure DEST_PATH_IMAGE048
, and S, V channel value belong to (0.2,1], current pixel
Figure 529763DEST_PATH_IMAGE032
Belong to Bin[5];
G) if current pixel
Figure 364733DEST_PATH_IMAGE032
The H channel value
Figure DEST_PATH_IMAGE050
, and S, V channel value belong to (0.2,1], current pixel
Figure 404364DEST_PATH_IMAGE032
Belong to Bin[6];
H) if current pixel
Figure 708306DEST_PATH_IMAGE032
The H channel value
Figure DEST_PATH_IMAGE052
, and S, V channel value belong to (0.2,1], current pixel
Figure 563523DEST_PATH_IMAGE032
Belong to Bin[7];
I) if current pixel
Figure 3732DEST_PATH_IMAGE032
The H channel value
Figure DEST_PATH_IMAGE054
, and S, V channel value belong to (0.2,1], current pixel
Figure 479844DEST_PATH_IMAGE032
Belong to Bin[8];
J) if current pixel
Figure 254771DEST_PATH_IMAGE032
The H channel value
Figure DEST_PATH_IMAGE056
, and S, V channel value belong to (0.2,1], current pixel
Figure 661481DEST_PATH_IMAGE032
Belong to Bin[9];
All sub-pieces
Figure 972508DEST_PATH_IMAGE002
Bin[i] [10] totally 150 the dimension color characteristics.
5. a kind of cover board detection method based on vehicle characteristics coupling according to claim 1 is characterized in that: step (4) specifically: adopt each sub-piece of sift feature calculation
Figure 540892DEST_PATH_IMAGE002
N key point
Figure 65765DEST_PATH_IMAGE004
128 dimensional features.
CN201310175763.5A 2013-05-10 2013-05-10 A kind of deck detection method based on vehicle characteristics coupling Expired - Fee Related CN103279739B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310175763.5A CN103279739B (en) 2013-05-10 2013-05-10 A kind of deck detection method based on vehicle characteristics coupling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310175763.5A CN103279739B (en) 2013-05-10 2013-05-10 A kind of deck detection method based on vehicle characteristics coupling

Publications (2)

Publication Number Publication Date
CN103279739A true CN103279739A (en) 2013-09-04
CN103279739B CN103279739B (en) 2016-05-11

Family

ID=49062254

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310175763.5A Expired - Fee Related CN103279739B (en) 2013-05-10 2013-05-10 A kind of deck detection method based on vehicle characteristics coupling

Country Status (1)

Country Link
CN (1) CN103279739B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650752A (en) * 2016-12-09 2017-05-10 浙江浩腾电子科技股份有限公司 Vehicle body color recognition method
CN106778777A (en) * 2016-11-30 2017-05-31 成都通甲优博科技有限责任公司 A kind of vehicle match method and system
CN106875693A (en) * 2017-03-29 2017-06-20 广西信路威科技发展有限公司 A kind of method and system of vehicle feature recognition
CN107680385A (en) * 2017-10-27 2018-02-09 泰华智慧产业集团股份有限公司 A kind of method and system for determining fake-licensed car
CN110991255A (en) * 2019-11-11 2020-04-10 智慧互通科技有限公司 Method for detecting fake-licensed vehicle based on deep learning algorithm
CN112200765A (en) * 2020-09-04 2021-01-08 浙江大华技术股份有限公司 Method and device for determining false-detected key points in vehicle
CN117373259A (en) * 2023-12-07 2024-01-09 四川北斗云联科技有限公司 Expressway vehicle fee evasion behavior identification method, device, equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002175549A (en) * 2000-12-07 2002-06-21 Mitsubishi Electric Corp Method and device for toll adjustment
US6449555B1 (en) * 1999-03-05 2002-09-10 Kabushiki Kaisha Toshiba Run time information arithmetic operation apparatus
CN101540105A (en) * 2009-04-15 2009-09-23 四川川大智胜软件股份有限公司 Fake-licensed car detection method based on number-plate identification and gridding supervision
CN102426786A (en) * 2011-11-15 2012-04-25 无锡港湾网络科技有限公司 Intelligent video analyzing system and method for automatically identifying fake plate vehicle
CN102881169A (en) * 2012-09-26 2013-01-16 青岛海信网络科技股份有限公司 Fake-licensed car detection method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6449555B1 (en) * 1999-03-05 2002-09-10 Kabushiki Kaisha Toshiba Run time information arithmetic operation apparatus
JP2002175549A (en) * 2000-12-07 2002-06-21 Mitsubishi Electric Corp Method and device for toll adjustment
CN101540105A (en) * 2009-04-15 2009-09-23 四川川大智胜软件股份有限公司 Fake-licensed car detection method based on number-plate identification and gridding supervision
CN102426786A (en) * 2011-11-15 2012-04-25 无锡港湾网络科技有限公司 Intelligent video analyzing system and method for automatically identifying fake plate vehicle
CN102881169A (en) * 2012-09-26 2013-01-16 青岛海信网络科技股份有限公司 Fake-licensed car detection method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
姚源: "车脸图像的特征提取", 《中国优秀硕士学位论文全文数据库》, 15 January 2009 (2009-01-15) *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106778777A (en) * 2016-11-30 2017-05-31 成都通甲优博科技有限责任公司 A kind of vehicle match method and system
CN106650752A (en) * 2016-12-09 2017-05-10 浙江浩腾电子科技股份有限公司 Vehicle body color recognition method
CN106650752B (en) * 2016-12-09 2019-04-30 浙江浩腾电子科技股份有限公司 A kind of body color recognition methods
CN106875693A (en) * 2017-03-29 2017-06-20 广西信路威科技发展有限公司 A kind of method and system of vehicle feature recognition
CN107680385A (en) * 2017-10-27 2018-02-09 泰华智慧产业集团股份有限公司 A kind of method and system for determining fake-licensed car
CN107680385B (en) * 2017-10-27 2019-12-24 泰华智慧产业集团股份有限公司 Method and system for determining fake-licensed vehicle
CN110991255A (en) * 2019-11-11 2020-04-10 智慧互通科技有限公司 Method for detecting fake-licensed vehicle based on deep learning algorithm
CN110991255B (en) * 2019-11-11 2023-09-08 智慧互通科技股份有限公司 Method for detecting fake-licensed car based on deep learning algorithm
CN112200765A (en) * 2020-09-04 2021-01-08 浙江大华技术股份有限公司 Method and device for determining false-detected key points in vehicle
CN117373259A (en) * 2023-12-07 2024-01-09 四川北斗云联科技有限公司 Expressway vehicle fee evasion behavior identification method, device, equipment and storage medium
CN117373259B (en) * 2023-12-07 2024-03-01 四川北斗云联科技有限公司 Expressway vehicle fee evasion behavior identification method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN103279739B (en) 2016-05-11

Similar Documents

Publication Publication Date Title
CN103279739A (en) Fake license plate detection method based on vehicle characteristic matching
Abolghasemi et al. An edge-based color-aided method for license plate detection
He et al. Color-based road detection in urban traffic scenes
Aldoma et al. OUR-CVFH–oriented, unique and repeatable clustered viewpoint feature histogram for object recognition and 6DOF pose estimation
Yan et al. A method of lane edge detection based on Canny algorithm
CN102799859A (en) Method for identifying traffic sign
CN103136528B (en) A kind of licence plate recognition method based on dual edge detection
CN105740886B (en) A kind of automobile logo identification method based on machine learning
Wang et al. License plate segmentation and recognition of Chinese vehicle based on BPNN
CN108830279B (en) Image feature extraction and matching method
CN104112122A (en) Vehicle logo automatic identification method based on traffic video
CN108021890B (en) High-resolution remote sensing image port detection method based on PLSA and BOW
CN104240231A (en) Multi-source image registration based on local structure binary pattern
CN102521597A (en) Hierarchical strategy-based linear feature matching method for images
CN105139011A (en) Method and apparatus for identifying vehicle based on identification marker image
Hu et al. A non-parametric statistics based method for generic curve partition and classification
Satzoda et al. Robust extraction of lane markings using gradient angle histograms and directional signed edges
Miao License plate character segmentation algorithm based on variable-length template matching
Deb et al. Automatic vehicle identification by plate recognition for intelligent transportation system applications
CN102902962A (en) Front vehicle detection method based on feature vector of scale invariant feature transform (SIFT)
Mills Relative orientation and scale for improved feature matching
Thakur et al. The cooperative approach of genetic algorithm and neural network for the identification of vehicle License Plate number
Tang et al. An improved local feature descriptor via soft binning
Chen et al. Context-aware lane marking detection on urban roads
CN102750550A (en) Multi-target tracking method and device based on video

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C53 Correction of patent of invention or patent application
CB02 Change of applicant information

Address after: Hangzhou City, Zhejiang province Yuhang District 311121 West Street Wuchang No. 998 building 7 East

Applicant after: Zhejiang iCare Vision Technology Co., Ltd.

Address before: 310013, Zhejiang, Xihu District, Hangzhou, Tian Shan Road, No. 398, Kun building, four floor, South Block

Applicant before: Zhejiang iCare Vision Technology Co., Ltd.

C53 Correction of patent of invention or patent application
CB02 Change of applicant information

Address after: Hangzhou City, Zhejiang province Yuhang District 311121 West Street Wuchang No. 998 building 7 East

Applicant after: ZHEJIANG ICARE VISION TECHNOLOGY CO., LTD.

Address before: Hangzhou City, Zhejiang province Yuhang District 311121 West Street Wuchang No. 998 building 7 East

Applicant before: Zhejiang iCare Vision Technology Co., Ltd.

COR Change of bibliographic data

Free format text: CORRECT: APPLICANT; FROM: HANGZHOU ICARE VISION TECHNOLOGY CO., LTD. TO: ZHEJIANG ICARE VISION TECHNOLOGY CO., LTD.

C14 Grant of patent or utility model
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: Fake license plate detection method based on vehicle characteristic matching

Effective date of registration: 20190821

Granted publication date: 20160511

Pledgee: Hangzhou Yuhang Small and Medium-sized Enterprise Transfer Service Co., Ltd.

Pledgor: ZHEJIANG ICARE VISION TECHNOLOGY CO., LTD.

Registration number: Y2019330000020

PE01 Entry into force of the registration of the contract for pledge of patent right
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160511

Termination date: 20210510

CF01 Termination of patent right due to non-payment of annual fee