CN103077397B - Vehicle-logo location method and vehicle-logo location system - Google Patents

Vehicle-logo location method and vehicle-logo location system Download PDF

Info

Publication number
CN103077397B
CN103077397B CN201310021485.8A CN201310021485A CN103077397B CN 103077397 B CN103077397 B CN 103077397B CN 201310021485 A CN201310021485 A CN 201310021485A CN 103077397 B CN103077397 B CN 103077397B
Authority
CN
China
Prior art keywords
car mark
candidate region
growing
point
mark candidate
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.)
Expired - Fee Related
Application number
CN201310021485.8A
Other languages
Chinese (zh)
Other versions
CN103077397A (en
Inventor
王海峰
王晓萌
何小波
董博
杨宇
张凯歌
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.)
XINZHENG ELECTRONIC TECHNOLOGY (BEIJING) Co Ltd
Original Assignee
XINZHENG ELECTRONIC TECHNOLOGY (BEIJING) 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 XINZHENG ELECTRONIC TECHNOLOGY (BEIJING) Co Ltd filed Critical XINZHENG ELECTRONIC TECHNOLOGY (BEIJING) Co Ltd
Priority to CN201310021485.8A priority Critical patent/CN103077397B/en
Publication of CN103077397A publication Critical patent/CN103077397A/en
Application granted granted Critical
Publication of CN103077397B publication Critical patent/CN103077397B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Image Analysis (AREA)

Abstract

The present invention relates to image processing field, be specifically related to a kind of vehicle-logo location method and vehicle-logo location system, this vehicle-logo location method comprises: the car mark candidate region determining forward; Morphological scale-space is carried out to described car mark candidate region, determines the more than one growing point of region growing; Carry out region growing with described growing point for starting point, determine more than one growth end point; By the mode connecting two adjacent described growth end point, all described growth end point are joined together to form car mark target area boundaries; By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark.The present invention effectively can determine car target position.

Description

Vehicle-logo location method and vehicle-logo location system
Technical field
The present invention relates to image processing field, be specifically related to a kind of vehicle-logo location method and vehicle-logo location system.
Background technology
Along with socioeconomic development, increasing of vehicle, becomes inevitable by computer information, intelligentized management vehicle.License plate recognition technology is widely used in traffic flow monitoring, and highway bayonet socket is charged, in red light violation vehicle monitoring and community automatic fare collection system.Current treatment technology can only identify, but can not identify concrete vehicle car plate and large-scale, medium-sized, dilly.And the identification of car target can make up this defect.Vehicle-logo recognition is vehicle cab recognition technology important step, and car target location is the key link of vehicle-logo recognition, needs a kind of effective method to carry out locating segmentation accurately to car mark for the problems referred to above.
Summary of the invention
The invention provides a kind of vehicle-logo location method and vehicle-logo location system, effectively can determine car target position.
The invention provides a kind of vehicle-logo location method, comprising:
Determine the car mark candidate region of forward;
Morphological scale-space is carried out to described car mark candidate region, determines the more than one growing point of region growing;
Carry out region growing with described growing point for starting point, determine more than one growth end point;
By the mode connecting two adjacent described growth end point, all described growth end point are joined together to form car mark target area boundaries;
By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark;
Wherein, describedly carry out Morphological scale-space to described car mark candidate region, the more than one growing point determining region growing comprises:
Gray processing process is carried out to described car mark candidate region, forms car mark candidate region gray-scale map;
Choose the more than one pixel that in the gray-scale map of described car mark candidate region, gray-scale value is maximum, this pixel is defined as growing point;
Or,
Describedly carry out Morphological scale-space to described car mark candidate region, the more than one growing point determining region growing comprises:
The optimal segmenting threshold of described car mark candidate region is drawn by the method for maximum between-cluster variance;
According to described optimal segmenting threshold, binary conversion treatment is carried out to described car mark candidate region and form binary picture;
Screen the spaced point of white in described binary picture, any one point in the continuous domain of white in described binary picture is defined as growing point.
Described determine the car mark candidate region of forward before, described vehicle-logo location method preferably comprises further: vehicle image is carried out forward process; According to the vehicle image determination license plate area after forward process; Then,
Describedly determine that the car mark candidate region of forward comprises: according to car plate and car target position relationship, determine described car mark candidate region by described license plate area;
Described car plate and car target position relationship preferably include: described car is marked in the region of 1-3 car plate of the top of described car plate, or described car is marked in the region of 1-6 car plate of the top of described car plate.
Described region growing preferably includes:
Setting growth pattern is: when growing point meets formula | I seed-I| < λ | I max-I min| then grow, wherein, λ is customized parameter, and I represents the gray-scale value of pixel, I seedrepresent the gray-scale value of growing point, I maxwith I minrepresent the maximum gray scale in image and minimum gradation value respectively;
Growing point grows according to described growth pattern.
Described region growing preferably includes:
Setting growth pattern: in binary map, when the value of the pixel adjacent with described growing point is equal with the value of described growing point, grow;
Described growing point grows according to described growth pattern.
The present invention also provides a kind of vehicle-logo location system, comprising:
Car mark candidate region assembly, for determining the car mark candidate region of forward;
Growing point assembly, carries out Morphological scale-space for the described car mark candidate region determined described car mark candidate region assembly, determines the more than one growing point of region growing;
Growth end point assembly, carries out region growing for the described growing point determined with described growing point assembly for starting point, determines more than one growth end point;
Car mark target area boundaries assembly, is joined together to form car mark target area boundaries for the mode by connecting the described growth end point that two adjacent described growth end point assemblies are determined by all described growth end point;
The accurate hyte part of car mark, for being split described car mark target area boundaries by axis, being marked the described car mark target area boundaries being positioned at axis, and being mapped to described car mark candidate region, obtaining the accurate position of car mark;
Wherein, described growing point assembly comprises: gray proces assembly, for carrying out gray processing process to described car mark candidate region, forms car mark candidate region gray-scale map; Pixel chooses assembly, for choosing the more than one pixel that in the gray-scale map of described car mark candidate region, gray-scale value is maximum, and this pixel is defined as growing point; And/or,
Described growing point assembly comprises: optimal segmenting threshold assembly, for being drawn the optimal segmenting threshold of described car mark candidate region by the method for maximum between-cluster variance; Binary picture assembly, forms binary picture for carrying out binary conversion treatment according to described optimal segmenting threshold to described car mark candidate region; Screening assembly, for screening the spaced point in described binary picture, is defined as growing point by any one point in continuous domain in described binary picture.
Vehicle-logo location system preferably comprises license plate area assembly further, for vehicle image is carried out forward process; According to the vehicle image determination license plate area after forward process;
Then, described car mark candidate region assembly is preferred for according to car plate and car target position relationship, by the described car mark candidate region of described license plate area determination forward.
By the invention provides a kind of vehicle-logo location method and vehicle-logo location system, following beneficial effect can be reached:
Vehicle-logo location method provided by the invention comprises: the car mark candidate region determining forward; Morphological scale-space is carried out to described car mark candidate region, determines the more than one growing point of region growing; Carry out region growing with described growing point for starting point, determine more than one growth end point; By the mode connecting two adjacent described growth end point, all described growth end point are joined together to form car mark target area boundaries; By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark.First the car mark candidate region of forward is determined roughly, determine growing point, growing point is by the mode determination car mark target area boundaries of region growing, and the car mark target area boundaries that selection is on axis is also mapped to car mark candidate region, obtains the accurate position of car mark.Thus can accurate positioning car mark, the vehicle-logo location method that is new is provided, facilitates next step vehicle-logo recognition, be of value to the identification and management that are applied to vehicle.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in below describing is only some embodiments of the present invention, for those of ordinary skills, under the prerequisite not paying creative work, other embodiment and accompanying drawing thereof can also be obtained according to these accompanying drawing illustrated embodiments.
Fig. 1 is the concrete steps of vehicle-logo location method during the present invention one specifically implements.
Embodiment
Carry out clear, complete description below with reference to accompanying drawing to the technical scheme of various embodiments of the present invention, obviously, described embodiment is only a part of embodiment of the present invention, instead of whole embodiments.Based on the embodiment in the present invention, other embodiments all that those of ordinary skill in the art obtain under the prerequisite not making creative work, all belong to the scope that the present invention protects.
The invention provides a kind of vehicle-logo location method, comprising:
Determine the car mark candidate region of forward;
Morphological scale-space is carried out to described car mark candidate region, determines the more than one growing point of region growing;
Carry out region growing with described growing point for starting point, determine more than one growth end point;
By the mode connecting two adjacent described growth end point, all described growth end point are joined together to form car mark target area boundaries;
By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark.
First the car mark candidate region of forward is determined roughly, determine growing point, growing point is by the mode determination car mark target area boundaries of region growing, and the car mark target area boundaries that selection is on axis is also mapped to car mark candidate region, obtains the accurate position of car mark.Thus can accurate positioning car mark, the vehicle-logo location method that is new is provided, facilitates next step vehicle-logo recognition, be of value to the identification and management that are applied to vehicle.
The present invention will describe this vehicle-logo location method in detail by a specific embodiment, as Fig. 1, shown in:
Step 101, extracts vehicle image;
Step 102, carries out forward process by vehicle image and obtains forward vehicle image;
The technology that forward carries out to image can adopt existing any one comparatively proven technique operate, perform.
Step 103, extracts license plate area from forward vehicle image;
Utilize the algorithm of the Morphological scale-space such as rim detection or machine learning to carry out extraction license plate area to forward vehicle image, this technology can adopt that existing any one is existing determines that the mature technology of license plate area operates, performs.
Such as: carry out gray processing process to input picture, Sobel Operator (sobel) is used to carry out rim detection to gray level image, then by region larger for marginal density license plate area alternatively.
Step 104, determines the car mark candidate region of forward;
Due to the position relationship that existing car plate and car target are comparatively fixed, such as: dolly (such as car), car is marked in the region of 1-3 car plate of the top of car plate; Cart (such as lorry), car is marked in the region of 1-6 car plate of the top of car plate.
According to car plate and car target correspondence position relation, release car mark region by license plate area.
Step 105, determines growing point;
Determine that the mode of growing point can adopt various ways, carry out pickup growing point from different images.
Such as: in embodiment 1, pick up growing point from gray-scale map, first gray processing process is carried out to car mark candidate regions and form car mark candidate region gray-scale map, supposing that the grey scale change scope of image is 1 to K, is S={1 with set expression, 2,3 ... .K}, gray level is the pixel count of i is n i, then whole pixel counts of image are: N=∑ i ∈ Sn i, each pixels probability: then the more than one pixel that in the gray-scale map of car mark candidate region, gray-scale value is maximum is chosen, this pixel is defined as growing point, be appreciated that the most bright spot in a secondary gray-scale map has a lot, so the maximum pixel of gray-scale value has a lot of, these pixels can be defined as growing point.
Such as: in example 2, the optimal segmenting threshold of car mark candidate region is drawn by the method for maximum between-cluster variance; According to this optimal segmenting threshold, binary conversion treatment is carried out to car mark candidate region and form binary picture; Be appreciated that in binary picture and only comprise " 0 " black and " 1 " white; Choose " 1 " that represents white, because part " 1 " is disperse state, partly " 1 " is collected state formation continuous domain, when ensuing pickup growing point, first " 1 " of disperse state sieve to be taken down, then any one " 1 " in " 1 " of collected state be picked up as growing point.
Step 106, is that starting point carries out region growing with growing point, determines more than one growth end point;
Can analyze from above that to show that growing point can pick up out multiple, each growing point carries out growing at different directions and can obtain a growth end point.Region growing can adopt the technology of the existing various region growing in this area.Such as:
For the growing point that above-described embodiment 1 is determined, when region growing, first set growth pattern: when growing point meets formula | I seed-I| < λ | I max-I min| then grow, wherein, λ is customized parameter, and I represents the gray-scale value of pixel, I seedrepresent the gray-scale value of growing point, I maxwith I minrepresent the maximum gray scale in image and minimum gradation value respectively; Then, growing point grows according to this growth pattern, when growing point grows into respective pixel point, if this pixel meets above-mentioned formula, then growing point grows into this pixel, and carries out next step growth, if this pixel does not meet above-mentioned formula, then growing point no longer continued growth, growing point growth last pixel be growth end point.
Be appreciated that λ is customized parameter, can set arbitrarily according to different needs.
For the growing point that above-described embodiment 2 is determined, when region growing, first, determine growth pattern: in binary map, when the value of the pixel adjacent with described growing point is equal with the value of described growing point, grow; Growing point grows according to this growth pattern, if meet growth pattern, then growing point continued growth, if do not meet growth pattern, then growing point is not in continued growth, and the pixel of the last arrival of growing point is growth end point.
Step 107, is joined together to form car mark target area boundaries by the mode connecting two adjacent described growth end point by all described growth end point;
Connect two adjacent growth end point, thus all growth end point are connected in a formation closed boundary together.
Step 108, determines the accurate position of car mark by axis;
Due to car mark in most instances, be all on axis, so, the position can will being not car mark place by axis, but sieved by the car mark target area boundaries that above steps obtains, be specially:
By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark.
Next, the present invention performs the vehicle-logo location system of the method by providing above-mentioned vehicle-logo location method, it comprises:
License plate area assembly, for carrying out forward process by vehicle image; According to the vehicle image determination license plate area after forward process;
Car mark candidate region assembly, for determining the car mark candidate region of forward, being more specifically: according to car plate and car target position relationship, determining described car mark candidate region by described license plate area.Wherein state before car plate and car target position relationship, no longer repeat herein.
Growing point assembly, Morphological scale-space is carried out in described car mark candidate region for determining described car mark candidate region assembly, determine the more than one growing point of region growing, be more specifically: embodiment one: described growing point assembly comprises: gray proces assembly, for carrying out gray processing process to described car mark candidate region, form car mark candidate region gray-scale map; Pixel chooses assembly, for choosing the more than one pixel that in the gray-scale map of described car mark candidate region, gray-scale value is maximum, and this pixel is defined as growing point; Gray processing process is carried out to described car mark candidate region, forms car mark candidate region gray-scale map; Choose the more than one pixel that in the gray-scale map of described car mark candidate region, gray-scale value is maximum, this pixel is defined as growing point; Or embodiment two: described growing point assembly comprises: optimal segmenting threshold assembly, for drawing the optimal segmenting threshold of described car mark candidate region by the method for maximum between-cluster variance; Binary picture assembly, forms binary picture for carrying out binary conversion treatment according to described optimal segmenting threshold to described car mark candidate region; Screening assembly, for screening the spaced point in described binary picture, is defined as growing point by any one point in continuous domain in described binary picture.The optimal segmenting threshold of described car mark candidate region is drawn by the method for maximum between-cluster variance; According to described optimal segmenting threshold, binary conversion treatment is carried out to described car mark candidate region and form binary picture; Screen the spaced point in described binary picture, any one point in continuous domain in described binary picture is defined as growing point.
Growth end point assembly, carries out region growing for the described growing point determined with described growing point assembly for starting point, determines more than one growth end point; Be specially: grow according to growth pattern, determine more than one growth end point, the defining method of growth pattern is stated above, no longer repeats herein.
Car mark target area boundaries assembly, is joined together to form car mark target area boundaries for the mode by connecting the described growth end point that two adjacent described growth end point assemblies are determined by all described growth end point;
The accurate hyte part of car mark, for being split described car mark target area boundaries by axis, being marked the described car mark target area boundaries being positioned at axis, and being mapped to described car mark candidate region, obtaining the accurate position of car mark.
By the invention provides a kind of vehicle-logo location method and vehicle-logo location system, following beneficial effect can be reached:
Vehicle-logo location method provided by the invention comprises: the car mark candidate region determining forward; Morphological scale-space is carried out to described car mark candidate region, determines the more than one growing point of region growing; Carry out region growing with described growing point for starting point, determine more than one growth end point; By the mode connecting two adjacent described growth end point, all described growth end point are joined together to form car mark target area boundaries; By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark.First determine roughly the car mark candidate region of forward, determine growing point, growing point by the mode determination car mark target area boundaries of region growing, and is mapped to car mark candidate region, obtains the accurate position of car mark.Thus can accurate positioning car mark, the vehicle-logo location method that is new is provided, facilitates next step vehicle-logo recognition, be of value to the identification and management that are applied to vehicle.
Various embodiment provided by the invention can combine as required in any way mutually, the technical scheme obtained by this combination, also within the scope of the invention.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if belong within the scope of the claims in the present invention and equivalent technologies thereof to these amendments of the present invention and modification, then the present invention also comprises these change and modification.

Claims (6)

1. a vehicle-logo location method, is characterized in that, comprising:
Determine the car mark candidate region of forward;
Morphological scale-space is carried out to described car mark candidate region, determines the more than one growing point of region growing;
Carry out region growing with described growing point for starting point, determine more than one growth end point;
By the mode connecting two adjacent described growth end point, all described growth end point are joined together to form car mark target area boundaries;
By axis, described car mark target area boundaries is split, the described car mark target area boundaries being positioned at axis is marked, and is mapped to described car mark candidate region, obtain the accurate position of car mark;
Wherein, describedly carry out Morphological scale-space to described car mark candidate region, the more than one growing point determining region growing comprises:
Gray processing process is carried out to described car mark candidate region, forms car mark candidate region gray-scale map;
Choose the more than one pixel that in the gray-scale map of described car mark candidate region, gray-scale value is maximum, this pixel is defined as growing point;
Or,
Describedly carry out Morphological scale-space to described car mark candidate region, the more than one growing point determining region growing comprises:
The optimal segmenting threshold of described car mark candidate region is drawn by the method for maximum between-cluster variance;
According to described optimal segmenting threshold, binary conversion treatment is carried out to described car mark candidate region and form binary picture;
Screen the spaced point of white in described binary picture, any one point in the continuous domain of white in described binary picture is defined as growing point.
2. vehicle-logo location method as claimed in claim 1, is characterized in that, described determine the car mark candidate region of forward before, described vehicle-logo location method comprises further: vehicle image is carried out forward process; According to the vehicle image determination license plate area after forward process; Then,
Describedly determine that the car mark candidate region of forward comprises: according to car plate and car target position relationship, by the described car mark candidate region of described license plate area determination forward;
Described car plate and car target position relationship comprise: described car is marked in the region of 1-3 car plate of the top of described car plate, or described car is marked in the region of 1-6 car plate of the top of described car plate.
3. vehicle-logo location method as claimed in claim 1, it is characterized in that, described region growing comprises:
Setting growth pattern is: when growing point meets formula | I seed-I| < λ | I max-I min| then grow, wherein, λ is customized parameter, and I represents the gray-scale value of pixel, I seedrepresent the gray-scale value of growing point, I maxwith I minrepresent the maximum gray scale in image and minimum gradation value respectively;
Growing point grows according to described growth pattern.
4. vehicle-logo location method as claimed in claim 1, it is characterized in that, described region growing comprises:
Setting growth pattern: in binary map, when the value of the pixel adjacent with described growing point is equal with the value of described growing point, grow;
Described growing point grows according to described growth pattern.
5. a vehicle-logo location system, is characterized in that, comprising:
Car mark candidate region assembly, for determining the car mark candidate region of forward;
Growing point assembly, carries out Morphological scale-space for the described car mark candidate region determined described car mark candidate region assembly, determines the more than one growing point of region growing;
Growth end point assembly, carries out region growing for the described growing point determined with described growing point assembly for starting point, determines more than one growth end point;
Car mark target area boundaries assembly, is joined together to form car mark target area boundaries for the mode by connecting the described growth end point that two adjacent described growth end point assemblies are determined by all described growth end point;
The accurate hyte part of car mark, for being split described car mark target area boundaries by axis, being marked the described car mark target area boundaries being positioned at axis, and being mapped to described car mark candidate region, obtaining the accurate position of car mark;
Wherein, described growing point assembly comprises: gray proces assembly, for carrying out gray processing process to described car mark candidate region, forms car mark candidate region gray-scale map; Pixel chooses assembly, for choosing the more than one pixel that in the gray-scale map of described car mark candidate region, gray-scale value is maximum, and this pixel is defined as growing point; And/or,
Described growing point assembly comprises: optimal segmenting threshold assembly, for being drawn the optimal segmenting threshold of described car mark candidate region by the method for maximum between-cluster variance; Binary picture assembly, forms binary picture for carrying out binary conversion treatment according to described optimal segmenting threshold to described car mark candidate region; Screening assembly, for screening the spaced point in described binary picture, is defined as growing point by any one point in continuous domain in described binary picture.
6. vehicle-logo location system as claimed in claim 5, is characterized in that, comprise license plate area assembly further, for vehicle image is carried out forward process; According to the vehicle image determination license plate area after forward process;
Then, described car mark candidate region assembly is used for according to car plate and car target position relationship, by the described car mark candidate region of described license plate area determination forward.
CN201310021485.8A 2013-01-21 2013-01-21 Vehicle-logo location method and vehicle-logo location system Expired - Fee Related CN103077397B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310021485.8A CN103077397B (en) 2013-01-21 2013-01-21 Vehicle-logo location method and vehicle-logo location system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310021485.8A CN103077397B (en) 2013-01-21 2013-01-21 Vehicle-logo location method and vehicle-logo location system

Publications (2)

Publication Number Publication Date
CN103077397A CN103077397A (en) 2013-05-01
CN103077397B true CN103077397B (en) 2016-02-24

Family

ID=48153921

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310021485.8A Expired - Fee Related CN103077397B (en) 2013-01-21 2013-01-21 Vehicle-logo location method and vehicle-logo location system

Country Status (1)

Country Link
CN (1) CN103077397B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110544235B (en) * 2019-07-31 2022-12-16 华南理工大学 Flexible circuit board image area identification method based on differential geometry

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101154271A (en) * 2006-09-30 2008-04-02 电子科技大学中山学院 License plate character segmentation method based on fast area labeling algorithm and license plate large-spacing locating method
CN101196979A (en) * 2006-12-22 2008-06-11 四川川大智胜软件股份有限公司 Method for recognizing vehicle type by digital picture processing technology
CN101246551A (en) * 2008-03-07 2008-08-20 北京航空航天大学 Fast license plate locating method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101154271A (en) * 2006-09-30 2008-04-02 电子科技大学中山学院 License plate character segmentation method based on fast area labeling algorithm and license plate large-spacing locating method
CN101196979A (en) * 2006-12-22 2008-06-11 四川川大智胜软件股份有限公司 Method for recognizing vehicle type by digital picture processing technology
CN101246551A (en) * 2008-03-07 2008-08-20 北京航空航天大学 Fast license plate locating method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
浅谈区域生长法在车牌定位中的应用;张甫等;《科技创新与应用》;20120930;第24页左栏第3段至右栏第5段 *

Also Published As

Publication number Publication date
CN103077397A (en) 2013-05-01

Similar Documents

Publication Publication Date Title
CN106651872B (en) Pavement crack identification method and system based on Prewitt operator
CN102364496B (en) Method and system for identifying automobile license plates automatically based on image analysis
CN106845890B (en) Storage monitoring method and device based on video monitoring
CN102375982B (en) Multi-character characteristic fused license plate positioning method
CN109389163B (en) Unmanned aerial vehicle image classification system and method based on topographic map
CN104021574A (en) Method for automatically identifying pavement diseases
CN107506760A (en) Traffic signals detection method and system based on GPS location and visual pattern processing
CN107016362B (en) Vehicle weight recognition method and system based on vehicle front windshield pasted mark
CN101339616A (en) Roads recognition method and apparatus
CN108109133B (en) Silkworm egg automatic counting method based on digital image processing technology
CN105718916A (en) Lane line detection method based on Hough transform
CN106709412B (en) Traffic sign detection method and device
CN109886168B (en) Ground traffic sign identification method based on hierarchy
CN114511770A (en) Road sign plate identification method
CN103177445A (en) Outdoor tomato identification method based on subsection threshold image segmentation and light spot identification
CN105550710A (en) Nonlinear fitting based intelligent detection method for running exception state of contact network
CN113837094A (en) Road condition rapid analysis method based on full-color high-resolution remote sensing image
CN113537037A (en) Pavement disease identification method, system, electronic device and storage medium
CN111191557B (en) Mark identification positioning method, mark identification positioning device and intelligent equipment
CN111652033A (en) Lane line detection method based on OpenCV
Vishwanath et al. Connected component analysis for Indian license plate infra-red and color image character segmentation
CN110633635A (en) ROI-based traffic sign board real-time detection method and system
CN112863194B (en) Image processing method, device, terminal and medium
CN107516315A (en) A kind of development machine based on machine vision is slagged tap monitoring method
CN103077397B (en) Vehicle-logo location method and vehicle-logo location system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160224

Termination date: 20200121

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