CN108197622A - A kind of detection method of license plate, device and equipment - Google Patents
A kind of detection method of license plate, device and equipment Download PDFInfo
- Publication number
- CN108197622A CN108197622A CN201711430133.2A CN201711430133A CN108197622A CN 108197622 A CN108197622 A CN 108197622A CN 201711430133 A CN201711430133 A CN 201711430133A CN 108197622 A CN108197622 A CN 108197622A
- Authority
- CN
- China
- Prior art keywords
- detected
- feature
- brightness
- described image
- horizontal gradient
- 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
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
This application discloses a kind of detection method of license plate, device and equipment, scheme includes：Image to be detected is obtained, the brightness of image to be detected and horizontal gradient feature is extracted, the brightness and the horizontal gradient feature is polymerize, obtain converging channels feature, according to the converging channels feature, car plate is detected in described image to be detected.Converging channels feature in this solution can reduce interference characteristic, more accurately characterize vehicle license plate characteristic, be conducive to improve car plate detection speed and reliability.
Description
Technical field
This application involves a kind of field of image recognition more particularly to detection method of license plate, device and equipment.
Background technology
License plate recognition technology is usually applied to parking lot and traffic control department, and when Car license recognition wants advanced driving board to examine
It surveys, after the presence of car plate is detected, yet further identifies characters on license plate.
In the prior art, the feature comprising many dimensions is often used to carry out car plate detection, these dimensions such as include
Multiple directions histogram of gradients (Histogram of Oriented Gradient, HOG) direction character, multiple color characteristics,
And HOG amplitude Characteristics etc..
Based on the prior art, the car plate detection scheme that speed is faster more reliable is needed.
Invention content
Some embodiments of the present application provide a kind of detection method of license plate, device and equipment, to solve the prior art
In following technical problem：Need the car plate detection scheme that speed is faster more reliable.
Some embodiments of the present application use following technical proposals：
A kind of detection method of license plate, including：
Obtain image to be detected；
Extract the brightness of described image to be detected and horizontal gradient feature；
The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected.
Optionally, the brightness is represented with a brightness channel；One level of the horizontal gradient feature
Feature channel represents.
Optionally, it is described that the brightness and the horizontal gradient feature are polymerize, converging channels feature is obtained,
It specifically includes：
Scan the multiple regions of described image to be detected；
According to the brightness channel and the horizontal properties channel, the brightness in each region is obtained respectively
With horizontal gradient feature and polymerize, obtain the converging channels feature in each region.
Optionally, it is described according to the converging channels feature, car plate is detected in described image to be detected, is specifically included：
Respectively according to the converging channels feature in each region, detected in each region using sorting algorithm
With the presence or absence of car plate.
Optionally, the brightness of described described image to be detected of extraction, specifically includes：
According to the gray value of the pixel of described image to be detected, the brightness channel of described image to be detected, institute are extracted
It states brightness channel to be made of multiple first matrix elements, each first matrix element is according to described image to be detected
The gray value of the part pixel is worth to.
Optionally, the horizontal gradient feature of described described image to be detected of extraction, specifically includes：
According to horizontal gradient operator and the gray value of the pixel of described image to be detected, the water of described image to be detected is extracted
Flat Gradient Features channel, the horizontal gradient feature channel are made of multiple second matrix elements, each second matrix element
Element is worth to according to the convolution of the horizontal gradient operator and the gray value of the part pixel of described image to be detected.
Optionally, the horizontal gradient operator is sobel operators or Fast Field operator.
A kind of car plate detection device, including：
Acquisition module obtains image to be detected；
Extraction module extracts the brightness of described image to be detected and horizontal gradient feature；
Aggregation module polymerize the brightness and the horizontal gradient feature, obtains converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected for detection module.
Optionally, the brightness is represented with a brightness channel；One level of the horizontal gradient feature
Feature channel represents.
Optionally, the aggregation module polymerize the brightness and the horizontal gradient feature, is polymerize
Channel characteristics specifically include：
The aggregation module scans the multiple regions of described image to be detected；
According to the brightness channel and the horizontal properties channel, the brightness in each region is obtained respectively
With horizontal gradient feature and polymerize, obtain the converging channels feature in each region.
Optionally, the detection module detects car plate in described image to be detected, has according to the converging channels feature
Body includes：
The detection module according to the converging channels feature in each region, is detected every respectively using sorting algorithm
It whether there is car plate in a region.
Optionally, the extraction module extracts the brightness of described image to be detected, specifically includes：
The extraction module extracts the brightness of described image to be detected according to the gray value of the pixel of described image to be detected
Feature channel, the brightness channel are made of multiple first matrix elements, and each first matrix element is according to
The gray value of the part pixel of image to be detected is worth to.
Optionally, the extraction module extracts the horizontal gradient feature of described image to be detected, specifically includes：
The extraction module is treated described in extraction according to horizontal gradient operator and the gray value of the pixel of described image to be detected
The horizontal gradient feature channel of detection image, the horizontal gradient feature channel are made of multiple second matrix elements, Mei Gesuo
The second matrix element is stated according to the horizontal gradient operator and the volume of the gray value of the part pixel of described image to be detected
Product value obtains.
Optionally, the horizontal gradient operator is sobel operators or Fast Field operator.
A kind of car plate detection equipment, including：
At least one processor；And
The memory being connect at least one processor communication；Wherein,
The memory is stored with the instruction that can be performed by least one processor, and described instruction is by described at least one
A processor performs, so that at least one processor can：
Obtain image to be detected；
Extract the brightness of described image to be detected and horizontal gradient feature；
The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected.
Above-mentioned at least one technical solution that some embodiments of the present application use can reach following advantageous effect：It reduces
The intrinsic dimensionality of car plate detection is used for, interference characteristic can be reduced by converging channels feature, it is special more accurately to characterize car plate
Sign is conducive to improve car plate detection speed and reliability.
Description of the drawings
Attached drawing described herein is used for providing further understanding of the present application, forms the part of the application, this Shen
Illustrative embodiments and their description please do not form the improper restriction to the application for explaining the application.In the accompanying drawings：
Fig. 1 is the flow diagram of detection method of license plate that some embodiments of the present application provide；
Fig. 2 is the detailed process schematic diagram of detection method of license plate that some embodiments of the present application provide；
Fig. 3 is the structure diagram of car plate detection equipment that some embodiments of the present application provide；
Fig. 4 is the structure diagram of car plate detection device that some embodiments of the present application provide.
Specific embodiment
Purpose, technical scheme and advantage to make the application are clearer, below in conjunction with the application specific embodiment and
Technical scheme is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the application one
Section Example, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not doing
Go out all other embodiments obtained under the premise of creative work, shall fall in the protection scope of this application.
It has been mentioned hereinbefore that it is more for detecting the intrinsic dimensionality of car plate in the prior art, for example, in a kind of detection algorithm
In, intrinsic dimensionality is for 10 comprising 6 HOG direction characters, 3 color characteristics and 1 HOG amplitude Characteristics.
The application has carried out Feature Dimension Reduction according to the characteristics of car plate, to reduce interference characteristic, improve car plate detection speed and
Reliability.Specifically, it is contemplated that the distribution characteristics of characters on license plate, i.e. characters on license plate are all arranged side by side by horizontal direction, therefore, vehicle
The edge feature of board character is concentrated mainly on vertical direction, then gradient direction is horizontal direction, passes through Luminance Distribution and horizontal ladder
The characteristics of degree information just can represent car plate well based on this, carries out Feature Dimension Reduction, with 1 brightness and 1 horizontal ladder
Degree feature can detect car plate.
Fig. 1 is the flow diagram of detection method of license plate that some embodiments of the present application provide.In the flow, from setting
For standby angle, executive agent can be the vehicle monitoring relevant device of parking lot or traffic department.The equipment can be clothes
Business device or terminal, the application this is not specifically limited.
In addition, for program angle, the executive agent of some steps in the embodiment of the present application can be above equipment
The program of middle installation.The form of the program can be client or page end etc., and the application is not especially limited this.
Flow in Fig. 1 may comprise steps of：
S102：Obtain image to be detected.
In some embodiments of the present application, image to be detected can pass through such as first-class camera shooting of camera, monitoring camera
Equipment acquires.Whether image to be detected may include car plate, detected by subsequent step comprising car plate in image to be detected, if
Comprising, additionally it is possible to determine residing region of the car plate in image to be detected.
S104：Extract the brightness of described image to be detected and horizontal gradient feature.
In some embodiments of the present application, brightness can be represented with a brightness channel, and horizontal gradient is special
Sign can be represented with a horizontal properties channel.Feature channel is matrix form, and matrix element can reflect mapping to be checked
The feature of corresponding region as in.
It should be noted that brightness, horizontal gradient feature can also be represented with more than one feature channel, total spy
Sign dimension, which is less than 10, can realize dimensionality reduction.
S106：The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature.
In some embodiments of the present application, image to be detected is often the road image or parking lot entrance acquired
Image, when taking vehicle, image to be detected can include the car plate of the vehicle.In this case, car plate is in mapping to be checked
Subregion is only occupied as in, usually smaller region, when subsequent detection can preferably be detected with subregion, to improve detection
Accuracy.
For the different zones in image to be detected, can there are oneself corresponding brightness and horizontal gradient spy respectively
Sign, and then can have oneself corresponding converging channels feature by polymerization, it is detected for subregion.
S108：According to the converging channels feature, car plate is detected in described image to be detected.
In some embodiments of the present application, it can be examined in image to be detected using sorting algorithm with converging channels feature
Measuring car board.Specifically, the converging channels feature training grader of license plate image sample can be advanced with, after the completion of training, with
The input data of grader that the converging channels feature of image to be detected is obtained as training, carries out classification processing, is treated with detection
Whether car plate is included in detection image.Sorting algorithm the application for being utilized simultaneously is not specifically limited, for example is Boosting points
Class algorithm etc..
By the method for Fig. 1, the intrinsic dimensionality for car plate detection is reduced, can be reduced by converging channels feature dry
Feature is disturbed, more accurately characterizes vehicle license plate characteristic, is conducive to improve car plate detection speed and reliability.
Method based on Fig. 1, some embodiments of the present application additionally provide this method some specific embodiments and
Expansion scheme is illustrated below.
In some embodiments of the present application, for step S104, the brightness of described described image to be detected of extraction,
Can specifically it include：According to the gray value of the pixel of described image to be detected, the brightness for extracting described image to be detected leads to
Road, the brightness channel are made of multiple first matrix elements, and each first matrix element is according to described to be detected
The gray value of the part pixel of image is worth to.
Each first matrix element corresponds respectively to subregion in image to be detected, and the part pixel preferably should
Pixel in subregion, then the first matrix element can represent the brightness of its corresponding subregion.Need what is illustrated
It is that region when subregion here is detected with subregion can be one-to-one relationship or independently of each other
Difference, for example, can be include or by comprising relationship etc..
In order to make it easy to understand, a kind of example calculation scheme of brightness channel is illustrated below.
It is assumed that image to be detected is made of m row n row pixels, it is denoted as Im×n, I (x, y) represent image to be detected in coordinate be
The gray value of the pixel of (x, y).The brightness channel of image to be detected is denoted as Matrix Cl, it is assumed that ClSize be
Then ClIn the first matrix element Cl(i, j) can be calculated according to equation below：
It can be seen that in this embodiment, the value of each first matrix element is equal to the gray scale of 4 pixels of image to be detected
The mean value of value, this 4 pixels can cross a rectangular area in image to be detected.For example, Cl(0,0) value is coordinate point
Not Wei (0,0), (1,0), (0,1), (1,1) 4 pixels gray value mean value.
Similarly, it is assumed that ClSize beThen the value of each first matrix element can be equal to image to be detected
The mean value of gray value of 16 pixels, etc..
It should be noted that the brightness that is worth to of the gray value based on multiple pixels is also exemplary scheme,
For example, maximum value or minimum that can also be based on the gray value of multiple pixels be worth to brightness.
In some embodiments of the present application, for step S104, the horizontal gradient of described described image to be detected of extraction
Feature can specifically include：According to horizontal gradient operator and the gray value of the pixel of described image to be detected, extraction is described to be checked
The horizontal gradient feature channel of altimetric image, the horizontal gradient feature channel are made of multiple second matrix elements, each described
Second matrix element is according to the convolution of the horizontal gradient operator and the gray value of the part pixel of described image to be detected
It is worth to.
Each second matrix element corresponds respectively to subregion in image to be detected, and the part pixel preferably should
Pixel in subregion, then the second matrix element can represent the horizontal gradient feature of its corresponding subregion.It needs
Bright, region when subregion here is detected with subregion can be one-to-one relationship or independently of each other
Different from, for example, can be include or by comprising relationship etc..
In order to make it easy to understand, using the example above below, a kind of example calculation scheme of horizontal gradient feature channel is carried out
Explanation.
The horizontal gradient feature channel of image to be detected is denoted as Matrix Cg, it is assumed that CgSize beThen CgIn
Second matrix element Cg(i, j) can be calculated according to equation below：
Wherein, gradienthRepresent horizontal gradient operator, * represents convolution algorithm symbol, and horizontal gradient operator such as can be with
It is sobel operatorsOr Fast Field operator (- 101) etc..Similarly, if CgSize change, then count
Calculate CgThe formula of (i, j) can also correspondingly change.
In some embodiments of the present application, car plate can be detected with subregion by being previously mentioned that, accordingly, it is desirable to subregion
Extract to domain converging channels feature.Specifically, it is described to the brightness and the horizontal gradient feature for step S106
It is polymerize, obtains converging channels feature, can be included：Scan the multiple regions of described image to be detected；According to the brightness
Feature channel and the horizontal properties channel obtain each brightness in the region and horizontal gradient feature and carry out respectively
Polymerization, obtains the converging channels feature in each region.The mode of polymerization is such as that matrix element is attached combination, dimension
Number extension etc..
In order to comprehensively scan, the sliding window of specified size can be generally utilized, with specified sliding step and is specified
Glide direction slip scan is traversed in image to be detected, then the region that sliding window stops every time is above-mentioned each institute
State region.
Further, it is described according to the converging channels feature for step S108, it is detected in described image to be detected
Car plate can specifically include：Respectively according to the converging channels feature in each region, detected using sorting algorithm each
It whether there is car plate in the region.If there are car plate, the position of corresponding region can be exported, in order to subsequently carry out such as vehicle
The processing such as board character recognition.
Based on explanation above, some embodiments of the present application additionally provide the detailed process signal of detection method of license plate
Figure, as shown in Figure 2.It should be noted that the detailed process of Fig. 2 is exemplary, not to the restriction of the application, according to above
Scheme be described in detail, detection method of license plate can have more than one detailed process.
Flow in Fig. 2 mainly includes the following steps that：
S202：Obtain image to be detected.
S204：According to formula one and formula two, the brightness channel and horizontal gradient feature for calculating image to be detected lead to
Road.
S206：Using sliding window mode, each region of image to be detected is scanned.
S208：According to the brightness channel of calculating and horizontal gradient feature channel, respectively by the bright of each region of scanning
Degree feature and horizontal gradient feature are polymerize, and obtain the converging channels feature in each region.
S210：Respectively according to the converging channels feature in each region, using sorting algorithm, each region is detected with the presence or absence of vehicle
Board, if in the presence of the position of corresponding region is exported.
Based on same thinking, some embodiments of the present application additionally provide corresponding device, equipment and non-volatile meter
Calculation machine storage medium.
Fig. 3 is the structure diagram of the car plate detection device of some embodiments that the application provides, and described device includes：
Acquisition module 301 obtains image to be detected；
Extraction module 302 extracts the brightness of described image to be detected and horizontal gradient feature；
Aggregation module 303 polymerize the brightness and the horizontal gradient feature, obtains converging channels spy
Sign；
According to the converging channels feature, car plate is detected in described image to be detected for detection module 304.
Optionally, the brightness is represented with a brightness channel；One level of the horizontal gradient feature
Feature channel represents.
Optionally, which is characterized in that the aggregation module 303 carries out the brightness and the horizontal gradient feature
Polymerization, obtains converging channels feature, specifically includes：
The aggregation module 303 scans the multiple regions of described image to be detected；
According to the brightness channel and the horizontal properties channel, the brightness in each region is obtained respectively
With horizontal gradient feature and polymerize, obtain the converging channels feature in each region.
Optionally, the detection module 304 detects vehicle according to the converging channels feature in described image to be detected
Board specifically includes：
The detection module 304 according to the converging channels feature in each region, is examined respectively using sorting algorithm
It surveys in each region and whether there is car plate.
Optionally, the extraction module 302 extracts the brightness of described image to be detected, specifically includes：
The extraction module 302 extracts described image to be detected according to the gray value of the pixel of described image to be detected
Brightness channel, the brightness channel are made of multiple first matrix elements, each first matrix element according to
The gray value of the part pixel of described image to be detected is worth to.
Optionally, the extraction module 302 extracts the horizontal gradient feature of described image to be detected, specifically includes：
The extraction module 302 extracts institute according to horizontal gradient operator and the gray value of the pixel of described image to be detected
The horizontal gradient feature channel of image to be detected is stated, the horizontal gradient feature channel is made of multiple second matrix elements, often
A second matrix element is according to the horizontal gradient operator and the gray value of the part pixel of described image to be detected
Convolution be worth to.
Optionally, the horizontal gradient operator is sobel operators or Fast Field operator.
Fig. 4 is the structure diagram of car plate detection equipment that some embodiments of the present application provide, and the equipment includes：
At least one processor；And
The memory being connect at least one processor communication；Wherein,
The memory is stored with the instruction that can be performed by least one processor, and described instruction is by described at least one
A processor performs, so that at least one processor can：
Obtain image to be detected；
Extract the brightness of described image to be detected and horizontal gradient feature；
The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected.
The car plate detection nonvolatile computer storage media for some embodiments that the application provides, being stored with computer can
Execute instruction, the computer executable instructions are set as：
Obtain image to be detected；
Extract the brightness of described image to be detected and horizontal gradient feature；
The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected.
Each embodiment in the application is described by the way of progressive, identical similar part between each embodiment
Just to refer each other, and the highlights of each of the examples are difference from other examples.Especially for equipment and Jie
For matter embodiment, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to method reality
Apply the part explanation of example.
Equipment provided by the embodiments of the present application and medium are one-to-one with method, and therefore, equipment and medium also have
Advantageous effects as corresponding method class, due to having been carried out specifically to the advantageous effects of method above
It is bright, therefore, the advantageous effects of equipment which is not described herein again and medium.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware can be used in the present invention
Apply the form of example.Moreover, the computer for wherein including computer usable program code in one or more can be used in the present invention
The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
The processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices is generated for real
The device of function specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps are performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or
The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM read-only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, available for storing the information that can be accessed by a computing device.It defines, calculates according to herein
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of elements are not only including those elements, but also wrap
Include other elements that are not explicitly listed or further include for this process, method, commodity or equipment it is intrinsic will
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described
Also there are other identical elements in the process of element, method, commodity or equipment.
The foregoing is merely embodiments herein, are not limited to the application.For those skilled in the art
For, the application can have various modifications and variations.All any modifications made within spirit herein and principle are equal
Replace, improve etc., it should be included within the scope of claims hereof.
Claims (15)
1. a kind of detection method of license plate, which is characterized in that including：
Obtain image to be detected；
Extract the brightness of described image to be detected and horizontal gradient feature；
The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected.
2. the method as described in claim 1, which is characterized in that the brightness is represented with a brightness channel；Institute
Horizontal gradient feature is stated to be represented with a horizontal properties channel.
3. method as claimed in claim 2, which is characterized in that it is described to the brightness and the horizontal gradient feature into
Row polymerization, obtains converging channels feature, specifically includes：
Scan the multiple regions of described image to be detected；
According to the brightness channel and the horizontal properties channel, the brightness and water in each region are obtained respectively
Flat Gradient Features are simultaneously polymerize, and obtain the converging channels feature in each region.
4. method as claimed in claim 3, which is characterized in that it is described according to the converging channels feature, described to be detected
Car plate is detected in image, is specifically included：
Respectively according to the converging channels feature in each region, using sorting algorithm detect in each region whether
There are car plates.
5. method as claimed in claim 2, which is characterized in that the brightness of described described image to be detected of extraction, specifically
Including：
According to the gray value of the pixel of described image to be detected, the brightness channel of described image to be detected is extracted, it is described bright
Degree feature channel is made of multiple first matrix elements, and each first matrix element is according to the part of described image to be detected
The gray value of the pixel is worth to.
6. method as claimed in claim 2, which is characterized in that the horizontal gradient feature of described described image to be detected of extraction,
It specifically includes：
According to horizontal gradient operator and the gray value of the pixel of described image to be detected, the horizontal ladder of described image to be detected is extracted
Feature channel is spent, the horizontal gradient feature channel is made of multiple second matrix elements, each second matrix element root
It is worth to according to the convolution of the horizontal gradient operator and the gray value of the part pixel of described image to be detected.
7. method as claimed in claim 6, which is characterized in that the horizontal gradient operator is sobel operators or quick ladder
Spend operator.
8. a kind of car plate detection device, which is characterized in that including：
Acquisition module obtains image to be detected；
Extraction module extracts the brightness of described image to be detected and horizontal gradient feature；
Aggregation module polymerize the brightness and the horizontal gradient feature, obtains converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected for detection module.
9. device as claimed in claim 8, which is characterized in that the brightness is represented with a brightness channel；Institute
Horizontal gradient feature is stated to be represented with a horizontal properties channel.
10. device as claimed in claim 9, which is characterized in that the aggregation module is to the brightness and the level
Gradient Features are polymerize, and are obtained converging channels feature, are specifically included：
The aggregation module scans the multiple regions of described image to be detected；
According to the brightness channel and the horizontal properties channel, the brightness and water in each region are obtained respectively
Flat Gradient Features are simultaneously polymerize, and obtain the converging channels feature in each region.
11. device as claimed in claim 10, which is characterized in that the detection module according to the converging channels feature,
Car plate is detected in described image to be detected, is specifically included：
According to the converging channels feature in each region, each institute is detected using sorting algorithm respectively for the detection module
It states and whether there is car plate in region.
12. device as claimed in claim 9, which is characterized in that the extraction module extracts the brightness of described image to be detected
Feature specifically includes：
The extraction module extracts the brightness of described image to be detected according to the gray value of the pixel of described image to be detected
Channel, the brightness channel are made of multiple first matrix elements, and each first matrix element is according to described to be checked
The gray value of the part pixel of altimetric image is worth to.
13. device as claimed in claim 9, which is characterized in that the extraction module extracts the level of described image to be detected
Gradient Features specifically include：
The extraction module extracts described to be detected according to horizontal gradient operator and the gray value of the pixel of described image to be detected
The horizontal gradient feature channel of image, the horizontal gradient feature channel are made of multiple second matrix elements, and each described the
Two matrix elements are according to the convolution value of the horizontal gradient operator and the gray value of the part pixel of described image to be detected
It obtains.
14. device as claimed in claim 13, which is characterized in that the horizontal gradient operator is for sobel operators or quickly
Gradient operator.
15. a kind of car plate detection equipment, which is characterized in that including：
At least one processor；And
The memory being connect at least one processor communication；Wherein,
The memory is stored with the instruction that can be performed by least one processor, and described instruction is by least one place
It manages device to perform, so that at least one processor can：
Obtain image to be detected；
Extract the brightness of described image to be detected and horizontal gradient feature；
The brightness and the horizontal gradient feature are polymerize, obtain converging channels feature；
According to the converging channels feature, car plate is detected in described image to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711430133.2A CN108197622A (en) | 2017-12-26 | 2017-12-26 | A kind of detection method of license plate, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711430133.2A CN108197622A (en) | 2017-12-26 | 2017-12-26 | A kind of detection method of license plate, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108197622A true CN108197622A (en) | 2018-06-22 |
Family
ID=62584112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711430133.2A Pending CN108197622A (en) | 2017-12-26 | 2017-12-26 | A kind of detection method of license plate, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197622A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086734A (en) * | 2018-08-16 | 2018-12-25 | 新智数字科技有限公司 | The method and device that pupil image is positioned in a kind of pair of eye image |
| CN109117898A (en) * | 2018-08-16 | 2019-01-01 | 新智数字科技有限公司 | A kind of hand-written character recognition method and system |
| CN111626360A (en) * | 2020-05-28 | 2020-09-04 | 新智数字科技有限公司 | Method, device, equipment and storage medium for detecting fault type of boiler |
| CN111797694A (en) * | 2020-06-09 | 2020-10-20 | 浙江大华技术股份有限公司 | License plate detection method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682304A (en) * | 2012-03-26 | 2012-09-19 | 北京博康智能信息技术有限公司 | Multi-feature integrated passer-by detection method and device |
| CN103514460A (en) * | 2013-07-30 | 2014-01-15 | 深圳市智美达科技有限公司 | Video monitoring multi-view-angle vehicle detecting method and device |
| CN104899881A (en) * | 2015-05-28 | 2015-09-09 | 湖南大学 | Shadow detection method for moving vehicle in video image |
| CN106682600A (en) * | 2016-12-15 | 2017-05-17 | 深圳市华尊科技股份有限公司 | Method and terminal for detecting targets |
-
2017
- 2017-12-26 CN CN201711430133.2A patent/CN108197622A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682304A (en) * | 2012-03-26 | 2012-09-19 | 北京博康智能信息技术有限公司 | Multi-feature integrated passer-by detection method and device |
| CN103514460A (en) * | 2013-07-30 | 2014-01-15 | 深圳市智美达科技有限公司 | Video monitoring multi-view-angle vehicle detecting method and device |
| CN104899881A (en) * | 2015-05-28 | 2015-09-09 | 湖南大学 | Shadow detection method for moving vehicle in video image |
| CN106682600A (en) * | 2016-12-15 | 2017-05-17 | 深圳市华尊科技股份有限公司 | Method and terminal for detecting targets |
Non-Patent Citations (1)
| Title |
|---|
| 李庆武 等: "基于多尺度聚合通道特征的实时行人检测", 《电子测量与仪器学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086734A (en) * | 2018-08-16 | 2018-12-25 | 新智数字科技有限公司 | The method and device that pupil image is positioned in a kind of pair of eye image |
| CN109117898A (en) * | 2018-08-16 | 2019-01-01 | 新智数字科技有限公司 | A kind of hand-written character recognition method and system |
| CN109086734B (en) * | 2018-08-16 | 2021-04-02 | 新智数字科技有限公司 | Method and device for positioning pupil image in human eye image |
| CN111626360A (en) * | 2020-05-28 | 2020-09-04 | 新智数字科技有限公司 | Method, device, equipment and storage medium for detecting fault type of boiler |
| CN111626360B (en) * | 2020-05-28 | 2023-11-17 | 新奥新智科技有限公司 | Method, apparatus, device and storage medium for detecting boiler fault type |
| CN111797694A (en) * | 2020-06-09 | 2020-10-20 | 浙江大华技术股份有限公司 | License plate detection method and device |
| CN111797694B (en) * | 2020-06-09 | 2024-05-28 | 浙江大华技术股份有限公司 | License plate detection method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197622A (en) | A kind of detection method of license plate, device and equipment | |
| Lalimi et al. | A vehicle license plate detection method using region and edge based methods | |
| CN108230357B (en) | Key point detection method and device, storage medium and electronic equipment | |
| US20170103258A1 (en) | Object detection method and object detection apparatus | |
| US9098919B2 (en) | Detecting motion in a high resolution video | |
| CN103456003A (en) | Device and method for tracking object by using characteristic point descriptor, device and method for removing erroneous characteristic | |
| EP3493157A1 (en) | Method and system for visual change detection using multi-scale analysis | |
| CN115861400B (en) | Target object detection method, training device and electronic equipment | |
| CN109858542A (en) | A kind of character identifying method and device | |
| Bulugu | Algorithm for license plate localization and recognition for tanzania car plate numbers | |
| CN108830828A (en) | A kind of method for detecting change of remote sensing image and device | |
| CN113762220B (en) | Object recognition method, electronic device, and computer-readable storage medium | |
| CN113129298B (en) | Method for identifying definition of text image | |
| CN104424475B (en) | The recognition methods of fringe area in image and device | |
| CN113468905B (en) | Graphic code identification method, graphic code identification device, computer equipment and storage medium | |
| CN107316296A (en) | A kind of method for detecting change of remote sensing image and device based on logarithmic transformation | |
| CN112215266B (en) | X-ray image contraband detection method based on small sample learning | |
| CN113508395B (en) | Method and device for detecting objects in an image composed of pixels | |
| CN112395924A (en) | Remote sensing monitoring method and device | |
| CN112101139B (en) | Human shape detection method, device, equipment and storage medium | |
| CN111076817B (en) | Abnormal target detection method based on optical multi-dimensional information integrated perception system | |
| CN111709951A (en) | Target detection network training method and system, network, device and medium | |
| CN117252903B (en) | Motion area extraction method and system based on image processing | |
| CN116883644A (en) | Liquid level recognition method, computer readable storage medium, and computer device | |
| CN104700396B (en) | The method and system of the parameter for estimating the volume of traffic is determined from image |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |