CN108564631A - Car light light guide acetes chinensis method, apparatus and computer readable storage medium - Google Patents
Car light light guide acetes chinensis method, apparatus and computer readable storage medium Download PDFInfo
- Publication number
- CN108564631A CN108564631A CN201810288504.6A CN201810288504A CN108564631A CN 108564631 A CN108564631 A CN 108564631A CN 201810288504 A CN201810288504 A CN 201810288504A CN 108564631 A CN108564631 A CN 108564631A
- Authority
- CN
- China
- Prior art keywords
- light guide
- car light
- light
- car
- image
- 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
Links
- 241000114727 Acetes chinensis Species 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 238000013139 quantization Methods 0.000 claims abstract description 11
- 230000004075 alteration Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 7
- 239000003086 colorant Substances 0.000 claims abstract 2
- 230000015654 memory Effects 0.000 claims description 18
- 238000004040 coloring Methods 0.000 claims description 6
- 239000004576 sand Substances 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000013145 classification model Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of car light light guide acetes chinensis method, apparatus and computer readable storage medium, this method includes making training image library and the learning classification model of car light light guide;Car light light guide image to be detected is obtained using colour imagery shot;Image is converted from RGB color to hsv color space, unequal interval quantization is carried out to tri- Color Channels of H, S, V respectively, constitutes color feature vector;The feature vector of extraction is sent into the corresponding sorter model of car light conductivity type selected, calculates the classification results for obtaining light guide to be measured, and judge whether light guide color is qualified.The invention also discloses a kind of car light light guide acetes chinensis device and computer readable storage mediums.The car light light guide acetes chinensis method of the present invention is suitable for the car light light guide of a variety of different colours, different size to the accuracy of judgement of light guide aberration, and relative to current artificial detection method, detection speed and accuracy can be improved, reduce production cost.
Description
Technical field
The present invention relates to automobile on-line checking field more particularly to a kind of car light light guide acetes chinensis method and devices.
Background technology
With the rapid development of auto industry and the continuous application of novel energy, light guide techniques are combined with LED green light sources
Generated optical lighting system is more and more extensive to be applied in the design and manufacture of car light.
In industrial processes, due to the influences such as defect of the error and light guide manufacture craft of light source installation site,
Aberration is generated when car light light guide may be made to light, leads to the reduction of car light product qualified rate, therefore industrially for car light light guide
Acetes chinensis just becomes one of important procedure.Optical illumination technology is not grown in the application time of auto industry at present, to car light
The acetes chinensis led is completed by artificial or complicated measuring instrument mostly, and not only time, human cost are high, but also detection efficiency
It cannot be satisfied the demand of auto manufacturing with accuracy.
The above is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that the above is existing skill
Art.
Invention content
The main purpose of the present invention is to provide a kind of car light light guide acetes chinensis method and devices, to solve the prior art
Deficiency.
To achieve the above object, technical solution provided by the invention is:A kind of car light light guide acetes chinensis method, step
For:First, the car light conductivity type information with detection is obtained, it is right in disaggregated model database to select to preset according to the information of acquisition
The Parameter File answered;Obtain car light light guide image to be detected;The hsv color histogram feature vector of car light light guide is extracted again;So
Afterwards, the feature vector of extraction is sent into the corresponding sorter model of car light conductivity type selected, calculates and obtains light to be measured
The classification results led, and judge whether light guide color is qualified.
Further, described that corresponding Parameter File in disaggregated model database is preset according to acquisition information selection, including:
If the corresponding disaggregated model Parameter File of light guide type to be detected is existing in the present system, select such
Type;
If corresponding Parameter File is not present in default disaggregated model database, need to add new car light light guide class
Type makes corresponding disaggregated model.
Further, described the step of adding new car light conductivity type, includes:Make the image library of new type light guide;Pass through
Colour imagery shot obtains the image of light guide exemplar, and the image in image library includes the light guide of standard color and the vehicle for having various aberration
Light leads the total M classes of image, marks class label respectively and preserves;It is special that M class car light light guide images in image library are subjected to color
Sign vector extraction;To the training set being made of M category feature vector sum class labels, using M two classification of one-against-rest study
Support vector machine classifier, and preserve corresponding classifier parameters model file, be used for subsequent light guide classification and Detection.
Further, the acquisition car light light guide image to be detected, including:Car light is lighted, optronics is made, is taken the photograph using colour
As head obtains optronic image, and by image transmitting to computer.
Further, the color feature vector step of the extraction car light light guide includes:Image is converted from RGB color
To hsv color space;Unequal interval quantization is carried out to H, S, V3 Color Channels respectively, constitutes color feature vector.
Further, the formula that image is converted from RGB color to hsv color space is:
In formula, R, G, B indicate that the initial colouring information of car light light guide image is rgb value, and transformed hsv color space will
The colouring information of car light light guide is divided into three elements:Tone H, saturation degree S and brightness V, wherein H ∈ [0,360], S ∈ [0,1],
V ∈ [0,1].
Further, the method for the hsv color histogram feature vector of the extraction car light light guide is:
Tri- components of HSV are subjected to non-uniform quantizing, the spaces H are divided into 8 grades, and S points are 3 grades, and V points are 3 etc.
Grade:
Structuring one-dimensional feature vector.According to above quantization method, each color component is synthesized one-dimensional characteristic vector G:
G=HQSQV+SQV+V
Wherein QSAnd QVThe respectively quantization series of component S and V, i.e. QS=3, QV=3, then formula be converted into:
G=9H+3S+V
Thus to obtain the 72 handle one dimensional histograms of G, the i.e. color feature vector of car light light guide image.
A kind of car light light guide acetes chinensis device for realizing car light light guide acetes chinensis method, the car light light guide color
Poor detection device includes:Memory, processor and it is stored in the car light that can be run on the memory and on the processor
Light guide acetes chinensis program.
A kind of computer readable storage medium for car light light guide acetes chinensis method, the computer-readable storage medium
It is stored with light in matter and leads acetes chinensis program, the light leads when acetes chinensis program is executed by processor and realizes the light
Lead acetes chinensis method and step.
The beneficial effects of the invention are as follows:
The present invention makes training image library and the learning classification model of car light light guide, carries by obtaining car light light guide image
Car light light guide color feature vector to be detected is taken, feature vector is sent into the corresponding grader of car light conductivity type selected
Carry out classification and Detection in model, obtain the classification results of light guide to be measured, if classification results be standard color when if it is qualified, classification knot
Fruit is that other colour casts are then unqualified.It is achieved in the acetes chinensis of car light light guide, relative to current artificial detection method,
Detection speed and accuracy can be improved in the present invention, and reduces production cost.
Description of the drawings
Fig. 1 is the structural schematic diagram for the affiliated terminal of car light light guide acetes chinensis device that embodiment of the present invention is related to;
Fig. 2 is the flow diagram of car light light guide acetes chinensis method of the present invention.
Specific implementation mode
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.It should
Understand, the specific embodiments described herein are merely illustrative of the present invention, is not intended to limit the present invention.
Terminal of the embodiment of the present invention can be PC.As shown in Figure 1, the terminal may include:Processor 1001, such as CPU,
Utilizing camera interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 for realizing
Connection communication between these components.User interface 1003 may include display screen (Display), input unit such as keyboard
(Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Utilizing camera interface 1004 can
That select may include the serial ports of standard, parallel port, USB, IEEE1394 etc..Memory 1005 can be high-speed RAM memory, also may be used
To be stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be
Independently of the storage device of aforementioned processor 1001.
Optionally, terminal can also include sensor, voltage and current detection circuit, communication module etc..
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, either combines certain components or different components arrangement.
As shown in Figure 1, as may include operation server, image in a kind of memory 1005 of computer storage media
Acquisition module, Subscriber Interface Module SIM and car light light guide acetes chinensis program.
In terminal shown in Fig. 1, utilizing camera interface 1004 is mainly used for connecting colour imagery shot, after acquisition image is used for
Continuous acetes chinensis;User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication;And locate
Reason device 1001 can be used for calling the car light light guide acetes chinensis program stored in memory 1005.
In the present embodiment, car light light guide acetes chinensis device includes:Memory 1005, processor 1001 and it is stored in institute
The car light light guide acetes chinensis program stated on memory 1005 and can run on the processor 1001, wherein processor
When the car light light guide acetes chinensis program stored in 1001 calling memories 1005, following operation is executed:
The car light conductivity type information with detection is obtained, it is right in disaggregated model database to select to preset according to the information of acquisition
The Parameter File answered;
Obtain car light light guide image to be detected;
Extract the hsv color histogram feature vector of car light light guide;
The feature vector of extraction is sent into the corresponding sorter model of car light conductivity type selected, calculating is waited for
The classification results of light guide are surveyed, and judge whether light guide color is qualified.
Further, processor 1001 can call the car light light guide acetes chinensis program stored in memory 1005, also
Execute following operation:
If the corresponding disaggregated model Parameter File of light guide type to be detected is existing in the present system, select such
Type;
If corresponding Parameter File is not present in default disaggregated model database, need to add new car light light guide class
Type makes corresponding disaggregated model.
Further, processor 1001 can call the car light light guide acetes chinensis program stored in memory 1005, also
Execute following operation:
Car light is lighted, optronics is made, obtains optronic image using colour imagery shot, and image transmitting is extremely counted
Calculation machine.
Further, processor 1001 can call the car light light guide acetes chinensis program stored in memory 1005, also
Execute following operation:
Image is converted from RGB color to hsv color space;
Unequal interval quantization is carried out to 3 Color Channels of H, S, V respectively, constitutes color feature vector.
Further, processor 1001 can call the car light light guide acetes chinensis program stored in memory 1005, also
Execute following operation:
The image library of new type light guide is made, the image in image library includes the light guide of standard color and there are various aberration
The step of total M classes of car light light guide image mark class label and preserve respectively, acquisition image is the same as claim 3;
M class car light light guide images in image library are subjected to color feature vector extraction, step is the same as described in claim 4;
To the training set being made of M category feature vector sum class labels, using the branch of one-against-rest M two classification of study
Vector machine (SVM) grader is held, and preserves corresponding classifier parameters model file, is used for subsequent light guide classification and Detection.
The present invention further provides a kind of car light light guide acetes chinensis methods, are car light light guide of the present invention with reference to Fig. 2, Fig. 2
The flow diagram of acetes chinensis method.
In the present embodiment, the aberration of car light light guide is detected using the method for machine vision, detection method includes
Following steps:
Step S10 obtains the car light conductivity type information with detection, is selected to preset disaggregated model number according to the information of acquisition
According to corresponding Parameter File in library;
In the present embodiment, if the corresponding disaggregated model Parameter File of light guide type to be detected has been deposited in the present system
Then selecting this type;If corresponding Parameter File is not present in default disaggregated model database, need to add new car light
Light guide type makes corresponding classification learning model.
When further, adding new car light conductivity type, car light light guide exemplar is obtained by colour imagery shot first
Image, make the image library of new type light guide, the image in image library includes the light guide of standard color and has various aberration
The total M classes of car light light guide image mark class label and preserve respectively;Further, by the M class car light light guide images in image library
It is converted from RGB color to hsv color space, then carries out hsv color characteristic vector pickup;Further, to by M category features
The training set that vector sum class label is constituted, the support vector machines (SVM) using one-against-rest M two classification of study are classified
Device, and corresponding classifier parameters model file is preserved, it is used for subsequent light guide classification and Detection.
Step S20 obtains car light light guide image to be detected;
In the present embodiment, it controls car light by program to light, makes optronics, obtaining light guide using colour imagery shot sends out
The image of light, and by image transmitting to computer.
Step S30 extracts the hsv color histogram feature vector of car light light guide;
In the present embodiment, image is converted from RGB color to hsv color space first, conversion formula is:
In formula, R, G, B indicate that the initial colouring information of car light light guide image is rgb value, and transformed hsv color space will
The colouring information of car light light guide is divided into three elements:Tone H (Hue), saturation degree S (Saturation) and brightness V (Value),
Wherein, [0,360] H ∈, S ∈ [0,1], V ∈ [0,1].
Then unequal interval quantization is carried out to three Color Channels of H, S, V respectively, constitutes the color characteristic of 72 handles
Vector.The method of hsv color histogram feature vector for extracting car light light guide is:
Tri- components of HSV are subjected to non-uniform quantizing by the following method, the spaces H are divided into 8 grades, and S points are 3 grades, V
It is divided into 3 grades:
Structuring one-dimensional feature vector.According to above quantization method, each color component is synthesized one-dimensional characteristic vector:
G=HQSQV+SQv+V
Wherein QSAnd QVThe respectively quantization series of component S and V, i.e. QS=3, QV=3, then formula be converted into:
G=9H+3S+V
Thus to obtain the 72 handle one dimensional histograms of G, the i.e. color feature vector of car light light guide image.
The hsv color feature vector of extraction is sent into the corresponding grader mould of car light conductivity type selected by step S40
In type, the classification results for obtaining light guide to be measured are calculated, and judge whether light guide color is qualified.
In the present embodiment, if classification results be standard color when if it is qualified, classification results be other colour casts be not
Qualification, while the aberration situation of light guide can be obtained according to underproof car light light guide color label and light guide is improved.
Car light light guide acetes chinensis method proposed by the present invention makes car light light guide by obtaining car light light guide image
Training image library and learning classification model, extract car light light guide color feature vector to be detected, and feature vector feeding has been selected
Classification and Detection is carried out in the fixed corresponding sorter model of car light conductivity type, obtains the classification results of light guide to be measured, if classification
Then qualified when being as a result standard color, classification results are that other colour casts are then unqualified.It is achieved in the aberration of car light light guide
Detection, relative to current detection method, detection speed and accuracy can be improved in the present invention, and reduces production cost.
The present invention also provides a kind of computer readable storage mediums, in the present embodiment, on computer readable storage medium
It is stored with light and leads acetes chinensis program, it can be achieved that the step of the acetes chinensis method of above-mentioned car light light guide.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (9)
1. a kind of car light light guide acetes chinensis method, which is characterized in that its step is:First, the car light light guide with detection is obtained
Type information selects to preset corresponding Parameter File in disaggregated model database according to the information of acquisition;Obtain car light to be detected
Light guide image;The hsv color histogram feature vector of car light light guide is extracted again;Then, the feature vector of extraction feeding has been selected
In the fixed corresponding sorter model of car light conductivity type, the classification results for obtaining light guide to be measured are calculated, and judge light guide color
It is whether qualified.
2. car light light guide acetes chinensis method according to claim 1, it is characterised in that:It is described to be selected according to acquisition information
Corresponding Parameter File in default disaggregated model database, including:
If the corresponding disaggregated model Parameter File of light guide type to be detected is existing in the present system, this type is selected;
If corresponding Parameter File is not present in default disaggregated model database, need to add new car light conductivity type, make
Make corresponding disaggregated model.
3. car light light guide acetes chinensis method according to claim 2, which is characterized in that the new car light light guide of the addition
The step of type includes:Make the image library of new type light guide;The image of light guide exemplar, image library are obtained by colour imagery shot
In image include the light guide of standard color and have the total M classes of car light light guide image of various aberration, mark class label is simultaneously respectively
It preserves;M class car light light guide images in image library are subjected to color feature vector extraction;To by M category feature vector sum classification marks
The training set constituted is signed, using the support vector machine classifier of one-against-rest M two classification of study, and preserves corresponding classification
Device parameter model file is used for subsequent light guide classification and Detection.
4. car light light guide acetes chinensis method according to claim 1, it is characterised in that:It is described to obtain car light to be detected
Image is led, including:Car light is lighted, optronics is made, optronic image is obtained using colour imagery shot, and by image transmitting
To computer.
5. car light light guide acetes chinensis method according to claim 1, it is characterised in that:The face of the extraction car light light guide
Color characteristic vector step includes:Image is converted from RGB color to hsv color space;Respectively to three colors of H, S, V
Channel carries out unequal interval quantization, constitutes color feature vector.
6. car light light guide acetes chinensis method according to claim 5, which is characterized in that it is described by image from RGB color
The formula that space is converted to hsv color space is:
In formula, R, G, B indicate that the initial colouring information of car light light guide image is rgb value, and transformed hsv color space is by car light
The colouring information of light guide is divided into three elements:Tone H, saturation degree S and brightness V, wherein H ∈ [0,360], S ∈ [0,1], V ∈
[0,1].
7. car light light guide acetes chinensis method according to claim 5, it is characterised in that:The extraction car light light guide
The method of hsv color histogram feature vector is:
Tri- components of HSV are subjected to non-uniform quantizing, the spaces H are divided into 8 grades, and S points are 3 grades, and V points are 3 grades:
Each color component is synthesized one-dimensional characteristic vector G by structuring one-dimensional feature vector according to above quantization method:
G=HQSQV+SQV+V
Wherein QSAnd QVThe respectively quantization series of component S and V, i.e. QS=3, QV=3, then formula be converted into:
G=9H+3S+V
Thus to obtain the 72 handle one dimensional histograms of G, the i.e. color feature vector of car light light guide image.
8. a kind of car light light guide aberration inspection for the car light light guide acetes chinensis method described in any one of claim 1 to 7
Survey device, it is characterised in that:The car light light guide acetes chinensis device includes:Memory, processor and it is stored in the storage
On device and the car light light guide acetes chinensis program that can run on the processor.
9. a kind of computer-readable storage for the car light light guide acetes chinensis method described in any one of claim 1 to 7
Medium, it is characterised in that:It is stored with light on the computer readable storage medium and leads acetes chinensis program, the light leads color
Difference detection program realizes that the light leads acetes chinensis method and step when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810288504.6A CN108564631B (en) | 2018-04-03 | 2018-04-03 | Method and device for detecting light guide chromatic aberration of car lamp and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810288504.6A CN108564631B (en) | 2018-04-03 | 2018-04-03 | Method and device for detecting light guide chromatic aberration of car lamp and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108564631A true CN108564631A (en) | 2018-09-21 |
CN108564631B CN108564631B (en) | 2021-07-09 |
Family
ID=63533903
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810288504.6A Expired - Fee Related CN108564631B (en) | 2018-04-03 | 2018-04-03 | Method and device for detecting light guide chromatic aberration of car lamp and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108564631B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109521029A (en) * | 2018-11-30 | 2019-03-26 | 湘潭大学 | A kind of detection method of bayonet type automobile lamp lamp cap side open defect |
CN109800693A (en) * | 2019-01-08 | 2019-05-24 | 西安交通大学 | A kind of vehicle detection at night method based on Color Channel composite character |
CN110288634A (en) * | 2019-06-05 | 2019-09-27 | 成都启泰智联信息科技有限公司 | A kind of method for tracking target based on Modified particle swarm optimization algorithm |
CN112317362A (en) * | 2020-09-24 | 2021-02-05 | 赣州好朋友科技有限公司 | Method and device for sorting quartz associated gold ore and readable storage medium |
CN112365484A (en) * | 2020-11-16 | 2021-02-12 | 北京霍里思特科技有限公司 | Classification method, classification system and mineral product classifier |
CN113592787A (en) * | 2021-07-13 | 2021-11-02 | 苏州汇川控制技术有限公司 | Light emitting component detection method, light emitting component detection device, terminal equipment and storage medium |
CN114240929A (en) * | 2021-12-28 | 2022-03-25 | 季华实验室 | Color difference detection method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110064308A1 (en) * | 2009-09-15 | 2011-03-17 | Tandent Vision Science, Inc. | Method and system for learning a same-material constraint in an image |
CN102385753A (en) * | 2011-11-17 | 2012-03-21 | 江苏大学 | Illumination-classification-based adaptive image segmentation method |
CN102915446A (en) * | 2012-09-20 | 2013-02-06 | 复旦大学 | Plant disease and pest detection method based on SVM (support vector machine) learning |
US20130244197A1 (en) * | 2012-03-16 | 2013-09-19 | Soek Gam Tjioe | Dental Shade Matching Device |
CN105809181A (en) * | 2014-12-31 | 2016-07-27 | 阿里巴巴集团控股有限公司 | Logo detection method and device |
CN106709529A (en) * | 2017-01-18 | 2017-05-24 | 河北工业大学 | Visual detection method for color difference classification of photovoltaic cells |
-
2018
- 2018-04-03 CN CN201810288504.6A patent/CN108564631B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110064308A1 (en) * | 2009-09-15 | 2011-03-17 | Tandent Vision Science, Inc. | Method and system for learning a same-material constraint in an image |
CN102385753A (en) * | 2011-11-17 | 2012-03-21 | 江苏大学 | Illumination-classification-based adaptive image segmentation method |
US20130244197A1 (en) * | 2012-03-16 | 2013-09-19 | Soek Gam Tjioe | Dental Shade Matching Device |
CN102915446A (en) * | 2012-09-20 | 2013-02-06 | 复旦大学 | Plant disease and pest detection method based on SVM (support vector machine) learning |
CN105809181A (en) * | 2014-12-31 | 2016-07-27 | 阿里巴巴集团控股有限公司 | Logo detection method and device |
CN106709529A (en) * | 2017-01-18 | 2017-05-24 | 河北工业大学 | Visual detection method for color difference classification of photovoltaic cells |
Non-Patent Citations (1)
Title |
---|
王晨等: "基于计算机视觉的车灯光导色差检测", 《电子测量技术》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109521029A (en) * | 2018-11-30 | 2019-03-26 | 湘潭大学 | A kind of detection method of bayonet type automobile lamp lamp cap side open defect |
CN109521029B (en) * | 2018-11-30 | 2021-07-13 | 湘潭大学 | Method for detecting appearance defects of side surface of lamp holder of bayonet type automobile lamp |
CN109800693A (en) * | 2019-01-08 | 2019-05-24 | 西安交通大学 | A kind of vehicle detection at night method based on Color Channel composite character |
CN109800693B (en) * | 2019-01-08 | 2021-05-28 | 西安交通大学 | Night vehicle detection method based on color channel mixing characteristics |
CN110288634A (en) * | 2019-06-05 | 2019-09-27 | 成都启泰智联信息科技有限公司 | A kind of method for tracking target based on Modified particle swarm optimization algorithm |
CN112317362A (en) * | 2020-09-24 | 2021-02-05 | 赣州好朋友科技有限公司 | Method and device for sorting quartz associated gold ore and readable storage medium |
CN112365484A (en) * | 2020-11-16 | 2021-02-12 | 北京霍里思特科技有限公司 | Classification method, classification system and mineral product classifier |
CN113592787A (en) * | 2021-07-13 | 2021-11-02 | 苏州汇川控制技术有限公司 | Light emitting component detection method, light emitting component detection device, terminal equipment and storage medium |
CN114240929A (en) * | 2021-12-28 | 2022-03-25 | 季华实验室 | Color difference detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108564631B (en) | 2021-07-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108564631A (en) | Car light light guide acetes chinensis method, apparatus and computer readable storage medium | |
CN111612763B (en) | Mobile phone screen defect detection method, device and system, computer equipment and medium | |
CN100568283C (en) | A kind of picture dominant hue analytical approach and device thereof | |
EP3300024B1 (en) | Color identification system, color identification method, and display device | |
CN103389162B (en) | A kind of reflecting object color measurement instrument utilizing color digital camera | |
CN104854620B (en) | Image processing apparatus, image processing system and program | |
CN104636759B (en) | A kind of method and picture filter information recommendation system for obtaining picture and recommending filter information | |
CN106384117B (en) | A kind of vehicle color identification method and device | |
CN103559499B (en) | RGB vector matching rapid-recognition system and method | |
CN108010024A (en) | It is a kind of blind with reference to tone mapping graph image quality evaluation method | |
CN106355607B (en) | A kind of width baseline color image template matching method | |
CN105678318B (en) | The matching process and device of traffic sign | |
CN105223208B (en) | A kind of circuit board detecting template and preparation method thereof, circuit board detecting method | |
CN107506738A (en) | Feature extracting method, image-recognizing method, device and electronic equipment | |
CN110263608B (en) | Automatic electronic component identification method based on image feature space variable threshold measurement | |
CN109920018A (en) | Black-and-white photograph color recovery method, device and storage medium neural network based | |
CN102088539B (en) | Method and system for evaluating pre-shot picture quality | |
CN109408008A (en) | Image identification system and information display method thereof | |
CN113873229B (en) | Image dead pixel detection method, system and device | |
CN114926661B (en) | Textile surface color data processing and identifying method and system | |
CN105509657B (en) | A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter | |
CN107633508A (en) | One kind metering product printed substrate outward appearance verification method and system | |
CN106815598B (en) | 360-degree panoramic picture identification method and device | |
CN113269195A (en) | Reading table image character recognition method and device and readable storage medium | |
CN112364780A (en) | Method for identifying state of indicator lamp |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210709 |