CN110308091A - A kind of detection method and system of anti-counterfeiting mark - Google Patents
A kind of detection method and system of anti-counterfeiting mark Download PDFInfo
- Publication number
- CN110308091A CN110308091A CN201910625487.5A CN201910625487A CN110308091A CN 110308091 A CN110308091 A CN 110308091A CN 201910625487 A CN201910625487 A CN 201910625487A CN 110308091 A CN110308091 A CN 110308091A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- module
- information
- detectable substance
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 175
- 239000000126 substance Substances 0.000 claims abstract description 63
- 238000007405 data analysis Methods 0.000 claims abstract description 46
- 238000012360 testing method Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 76
- 238000012937 correction Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 238000007790 scraping Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000000151 deposition Methods 0.000 claims 1
- 239000011248 coating agent Substances 0.000 abstract description 12
- 238000000576 coating method Methods 0.000 abstract description 12
- 238000011156 evaluation Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 5
- 230000005484 gravity Effects 0.000 description 18
- 238000007689 inspection Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000000429 assembly Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000002087 whitening effect Effects 0.000 description 2
- 108010025037 T140 peptide Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000004905 finger nail Anatomy 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N19/00—Investigating materials by mechanical methods
- G01N19/04—Measuring adhesive force between materials, e.g. of sealing tape, of coating
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Geophysics And Detection Of Objects (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of detection method of anti-counterfeiting mark and systems, wherein the detection method of anti-counterfeiting mark includes the following steps: to prestore detection pattern and former data corresponding with detection pattern;Detection pattern is selected, and calls former data corresponding with the detection pattern of selection;According to the status data of detection pattern acquisition testing object, and the status data of former data analysis detection object is compared, obtains the detectable substance attribute of the detectable substance.The application has the detection method and evaluation foundation for improving scratch type anti-counterfeiting mark coating, guarantees more objective testing result, specification and clear technical effect.
Description
Technical field
This application involves detection anti-counterfeiting mark technical field more particularly to the detection methods and system of a kind of anti-counterfeiting mark.
Background technique
Currently, people mainly pass through with finger nail or coin scratch scratch type anti-counterfeiting mark, to the scratch type anti-counterfeiting label
The difficulty that scrapes off for knowing coating is judged, and detection method and evaluation result mainly have a deficiency of the following aspects: a,
Detection method can not specific, specification;B, testing result not can be carried out magnitude judge, more to sentence by the subjectivity of reviewer
It is disconnected;C, the standard of evaluation result is difficult to consistent, not unified enough.
Summary of the invention
A kind of detection method and system for being designed to provide anti-counterfeiting mark of the application has and improves scratch type anti-counterfeiting label
Know the detection method and evaluation foundation of coating, guarantees more objective testing result, specification and clear technology effect
Fruit.
In order to achieve the above objectives, this application provides a kind of detection method of anti-counterfeiting mark, include the following steps: to prestore inspection
Survey mode and former data corresponding with detection pattern;Detection pattern is selected, and is called corresponding with the detection pattern of selection
Former data;According to the status data of detection pattern acquisition testing object, and the status data of former data analysis detection object is compared, obtained
The detectable substance attribute of the detectable substance.
Preferably, detection pattern includes at least: scraping difficulty detection off and scrapes information integrity detection off;Detectable substance attribute
It includes at least: difficulty attribute and information integrity attribute.
Preferably, when the detection pattern selected is scrapes difficulty detection off, the specific sub-step of detection is as follows: setting is initial
Pressure value;The scratch status data of detectable substance is obtained to the pressure detection of detectable substance according to initial pressure value;Sentence according to former data
Disconnected scratch status data simultaneously obtains processing information;After receiving processing information, pressure total value is obtained;It should according to pressure total value judgement
The difficulty attribute of detectable substance.
Preferably, difficulty attribute includes being difficult to scrape off and being easy to scrape off.
Preferably, data analysis module judges scratch status data according to former data and obtains the specific sub-step of processing information
Rapid as follows: data processing module handles scratch status data, and forms processing information;Data processing module divides to data
It analyses module and sends processing information.
Preferably, the sub-step handled to scratch status data is as follows: obtaining detection object image;To detection object image
Distortion correction and pretreatment are carried out, the first data set is obtained;Data processing module is trained in advance by the input of the first data set
Deep learning network model carries out feature extraction, obtains first and extracts data;Data processing module receives data analysis module root
The instruction for extracting data feedback according to first, instructing includes that pause is handled and continued with, if received instruction is to continue with,
Judge whether uniformly continuous if scratch state is uniformly continuous forms processing information for the scratch state in scratch region.
Preferably, distortion correction is carried out to detection object image and uses spherical projection model method, wherein imaged according to flake
Spherical coordinate model foundation conventional coordinates in head image-forming principle, adjusts its position and direction, makes the camera of fish-eye camera
Positioned at coordinate axis origin 0, along 0z axis positive direction, the original image after shooting is fallen in 0xy plane shooting direction;Determine correction image
Coordinate conversion relation formula between original image is as follows:In formula, (x, y, z) is original image
3D coordinate points, (a, b) are correction image coordinate points, and r is the spherical radius of the spherical coordinate model in panorama picture of fisheye lens principle.
Preferably, for the detection pattern selected to scrape information integrity detection off, the specific sub-step of detection is as follows: setting the
Two scrape opening force;Opening force is scraped by second back and forth to press to detectable substance detection, obtains information integrity status data;According to former data
Judge information integrity status data and obtains judgement information;According to the information integrity category for judging that information judges the detectable substance
Property.
A kind of detection system of anti-counterfeiting mark, comprising: detection device, data acquisition device and inspection center;In detection
The heart is connect with detection device and data acquisition device respectively;Detection device: the instruction that inspection center sends is received, and according to instruction
Detect detectable substance;Data acquisition device: the data during detectable substance are detected for collecting and detecting device, and data are uploaded and are examined
Measured center;Inspection center: receive and process data acquisition device upload data, to detection device under send instructions, execute it is above-mentioned
Anti-counterfeiting mark detection method.
Preferably, inspection center includes: data processing module, transceiver module, data analysis module, memory module and behaviour
Make module;Data processing module respectively with transceiver module, data analysis module, deposit digital-to-analogue block and connect;Operation module respectively with deposit
Storage module, data processing module, transceiver module are connected with data analysis module;Data processing module: it is received for receiving and processing
Send out the data that module uploads, and will treated that data are sent to data analysis module analyzes;Transceiver module: for receiving
The data of data acquisition device acquisition, send the data to data processing module, receive the instruction that data analysis module issues, and
It is sent to detection device;Memory module: for detection pattern and former data corresponding with detection pattern to be stored in advance;Operation
Module: for detection pattern and former data corresponding with detection pattern to be arranged;Selection detection mould;Show testing result.
What the application realized has the beneficial effect that:
The application has the detection method and evaluation foundation for improving scratch type anti-counterfeiting mark coating, guarantees inspection
Survey more objective result, specification and clear technical effect.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application can also be obtained according to these attached drawings other for those of ordinary skill in the art
Attached drawing.
Fig. 1 is a kind of structural schematic diagram of embodiment of detection system of anti-counterfeiting mark;
Fig. 2 is a kind of flow chart of embodiment of detection method of anti-counterfeiting mark.
Specific embodiment
With reference to the attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on the present invention
In embodiment, those skilled in the art's every other embodiment obtained without making creative work, all
Belong to the scope of protection of the invention.
The application provides the detection method and system of a kind of anti-counterfeiting mark, has and improves scratch type anti-counterfeiting mark coating
Detection method and evaluation foundation guarantee more objective testing result, specification and clear technical effect.
As shown in Figure 1, the application provides a kind of detection system of anti-counterfeiting mark, comprising: detection device 1, data acquisition dress
Set 2 and inspection center 3;Inspection center 3 connect with detection device 1 and data acquisition device 2 respectively;
Detection device 1: the instruction that inspection center 3 sends is received, and according to command detection detectable substance;
Data acquisition device 2: the data during detectable substance are detected for collecting and detecting device 1, and data are uploaded and are examined
Measured center 3;
Inspection center 3: receive and process data acquisition device 2 upload data, to detection device 1 under send instructions, execute
The detection method of following anti-counterfeiting marks.
Further, inspection center 3 include: data processing module, transceiver module, data analysis module, memory module and
Operation module;Data processing module respectively with transceiver module, data analysis module, deposit digital-to-analogue block and connect;Operation module respectively with
Memory module, data processing module, transceiver module are connected with data analysis module;
Data processing module: for receiving and processing the data of transceiver module upload, and by treated, data are sent to
Data analysis module is analyzed;
Transceiver module: the data that acquisition device 2 acquires for receiving data send the data to data processing module, connect
The instruction that data analysis module issues is received, and is sent to detection device 1;
Memory module: for detection pattern and former data corresponding with detection pattern to be stored in advance;
Operation module: for detection pattern and corresponding with detection pattern to be arranged;Select detection module;Display detection
As a result;
Data analysis module: according to the detection pattern of selection to sending instructions under detection device 1, receive data processing module or
The data that transceiver module is sent, and transfer the former data in memory module and are analyzed, according to sending instructions under judging result, and
The detectable substance attribute of the detectable substance out.
Further, as one embodiment, detection device 1 includes pedestal, and pedestal is provided with supporting part and test section;It holds
Load portion includes the station for placing detectable substance, and station is slidably connected by slide assemblies and pedestal;Slide assemblies have first
Control module;First control module receives and executes the instruction that transceiver module issues.Test section includes support rod and balancing pole, branch
Strut one end is flexibly connected with balancing pole, and opposite side is fixedly connected with pedestal;Balancing pole includes that the first balancing pole and second are flat
Weigh bar, and one end of the first balancing pole and one end of the second balancing pole are affixed, the other end of first balancing pole far from the second balancing pole
It is provided with level governor, the second balancing pole is provided with pressurizing device far from one end of the first balancing pole, and pressurizing device includes extremely
The scratch head of a few counterweight, weight brackets and scratch detectable substance;Support rod is set on the second balancing pole close to the first balance
One end of bar, and a part of shaft of the second balancing pole is located above supporting part, scratch head be set to the second balancing pole toward
The downside of supporting part;Weight brackets are set to the upper side on the second balancing pole relative to scratch head position.
Further, data acquisition device 2 includes: sensor and image acquisition device.
Specifically, image acquisition device;Image data for acquisition testing object;The inspection being set to above relative to station
It surveys on device 1.
Sensor includes gravity sensor and sensor for countering, wherein gravity sensor is set to the pressurization of detection device 1
On device, the gravity of the counterweight of addition is acquired, and is uploaded to transceiver module;Sensor for countering is disposed in proximity to the stage body of station
Detection device 1 on, for acquiring the practical reciprocating movement number of station, and be uploaded to transceiver module.
As shown in Fig. 2, the application provides a kind of detection method of anti-counterfeiting mark, include the following steps:
S1: detection pattern and former data corresponding with detection pattern are prestored.
Specifically, detection pattern includes at least: scraping difficulty detection off and scrape information integrity detection off.
Wherein, it scrapes difficulty detection off: so that the station of detection device 1 is completed primary orientation and reciprocatingly slide, and guarantee fund
Rigid head scratches to detectable substance, and test adds one scraping off for uniformly continuous of generation on the coating of detectable substance needed for trace
Add the weight size of counterweight, and completes to scrape anti-counterfeiting mark coating off according to the weight size of the counterweight (i.e. pressure total value)
The value assessment of complexity.
It scrapes information integrity detection off: being the counterweight by the way that fixed weight is arranged, in covering for detectable substance (inspection anti-counterfeiting mark)
The same position of cap rock carries out repeatedly reciprocal test, until destroy covered information, and the number back and forth to scrape is as scraping
Open the value assessment result of information integrity detection.
Further, former data include difficulty original data and integrality original data.
Wherein, difficulty detects former data and includes at least: first scrapes opening force size, the first reciprocating movement number, pre- facility
Press total value, deep learning model and difficulty attribute.
Further, first scrape opening force size include initial pressure value and addition pressure value.
Wherein, initial pressure value: when starting to scrape difficulty detection off, what is applied for the first time in detection device 1 scrapes opening force
Size.
Specifically, the occurrence of initial pressure value can according to the actual situation depending on, the application is preferably the gravity of 50g counterweight
Value.
Further, initial pressure value can be reset.Specifically, resetting initial pressure value by addition addition pressure value.
Wherein, add pressure value: what to scrape off in difficulty detection process, in detection device 1, n-th was added scrapes opening force
Size, N are greater than or equal to 2.
Specifically, the weight of the counterweight of addition pressure value is chosen according to sequence from small to large, and according to practical feelings
Condition is added.
Further, the first reciprocating movement number is fixed value in entire detection process, and specific number can be according to reality
Depending on the situation of border.
Integrity detection original data include at least: second scrapes opening force size, default reciprocating movement number, deep learning model
With information integrity attribute.
Specifically, second scrapes opening force size in entire detection process as fixed value, specific size can be according to practical feelings
Depending on condition.
Further, former data are to preset, and can be updated and/or modify.
S2: selection detection pattern, and call former data corresponding with the detection pattern of selection.
It is set on the station of detection device 1 specifically, will test object, detection pattern is selected by operation module, and
Former data corresponding with the detection pattern of selection are called from memory module, execute S3.
S3: according to the status data of detection pattern acquisition testing object, and comparing the status data of former data analysis detection object,
Obtain the detectable substance attribute of the detectable substance.
Further, status data includes scratch status data and information integrity status data.
Specifically, scratch status data be scrape off difficulty detection in detectable substance mark coating in the detection process by
What is scraped off scrapes level data off.
Information integrity status data is to scrape detectable substance in information integrity detection off to scrape information off in the detection process
Integrity data.
Further, detectable substance attribute includes difficulty attribute and information integrity attribute.
Specifically, difficulty attribute includes: to be difficult to scrape off and be easy to scrape off.Information integrity attribute includes: that integrality is good
It is poor with integrality.
Further, as one embodiment, the detection pattern selected detects to scrape difficulty off, the specific sub-step of detection
It is rapid as follows:
T110: setting initial pressure value.
Specifically, inspection center 3 issues the instruction of setting initial pressure value to detection device 1.Detection device 1 receives finger
After order, the initial pressure value that pressurizing device is arranged in opening force size is scraped according to first.As one embodiment, initial pressure value can be with
For Weight gravity, but it is not limited only to Weight gravity, the application is preferably Weight gravity, and the gravity value of each counterweight is clear, is easy to
It chooses and adds.Wherein, the occurrence of initial pressure value can according to the actual situation depending on, the application is preferably the weight of 50g counterweight
Force value.
Further, initial pressure value can be reset.Specifically, resetting initial pressure value by addition addition pressure value.
Further, the data of the initial pressure value of setting are uploaded to the transmitting-receiving mould of inspection center 3 by gravity sensor
Block.
T120: the scratch status data of detectable substance is obtained to the pressure detection of detectable substance according to initial pressure value.
Specifically, generating the Buddha's warrior attendant head of detection device 1 to the coating of detectable substance
Pressure, data analysis module send move to the first control module according to detection pattern, and the first control module receives movement
Instruction, and execute.Further, move includes the first reciprocating movement number of station, wherein specific first is reciprocal
Mobile number can according to the actual situation depending on, the application preferably moves back and forth primary.Wherein, station stage body is touched to meter
Returning again to after the switch of number sensor in situ is to complete one-shot measurement.After completing one-shot measurement, obtained by image acquisition device
The scratch status data of detectable substance and it is uploaded to transceiver module this moment, wherein the detectable substance after completing one-shot measurement generates scratch
The case where as scratch status data.Execute T130.
Further, in addition to scratch status data, the received data of transceiver module further include the behaviour that sensor for countering obtains
Make the practical mobile number of platform, it is whether identical as move for checking the moving operation number actually executed, to guarantee to grasp
The accuracy of work.
T130: judge scratch status data according to former data and obtain processing information.
Specifically, according to former data judge scratch status data and obtain processing information specific sub-step it is as follows:
D1: handling scratch status data, and forms processing information.
Specifically, the scratch status data received is uploaded to data processing mould by transceiver module as one embodiment
Block is handled by data processing module.
Specifically, the sub-step handled scratch status data is as follows:
D110: data processing module obtains detection object image.
Specifically, data acquisition device 2 carries out Image Acquisition to detectable substance by image acquisition device, and it will test object image
It is sent to transceiver module, data processing module is sent to by transceiver module, executes D120.Wherein, image acquisition device can be photograph
Camera, fish-eye camera etc., the application are preferably fish-eye camera.
D120: data processing module carries out distortion correction and pretreatment to detection object image, obtains the first data set.
Specifically, pretreatment includes to the processing of detectable substance image normalization and whitening pretreatment after completion distortion correction;
Pre-treatment step are as follows: by reducing data redundancy to input data dimensionality reduction, inhibit over-fitting.
Specifically, carrying out distortion correction to detection object image uses spherical projection model method, calculation amount is small and precision is high,
It is specific as follows:
According to the spherical coordinate model foundation conventional coordinates in fish-eye camera image-forming principle, its position and side are adjusted
To making the camera of fish-eye camera be located at coordinate axis origin 0, along 0z axis positive direction, the original image after shooting is fallen in shooting direction
In 0xy plane.
Determine that the coordinate conversion relation formula between correction image and original image is as follows:
In formula, (x, y, z) is original image 3D coordinate points, and (a, b) is correction image coordinate points, and r is that panorama picture of fisheye lens is former
The spherical radius of spherical coordinate model in reason.
D130;First data set is inputted trained deep learning network model in advance by data processing module, is carried out special
Sign is extracted, and is obtained first and is extracted data.
Wherein, the first extraction data include: the initial overlay layer region and/or scratch region of detectable substance.
Specifically, the first extraction data are sent to data analysis module, are held after data processing module completes feature extraction
Row D140.
D140: data processing module receives the instruction that data analysis module extracts data feedback according to first, and instruction includes
Pause is handled and is continued with, if received instruction executes D160 to continue with.
Specifically, data analysis module judges whether initial coverage area has scratch region according to the first extraction data,
If extracting the initial overlay layer region and scratch region that data include detectable substance, it is determined as with scratch region, at data
Reason module issues the instruction continued with, executes D160.
If extracting the initial overlay layer region that data only include detectable substance, it is determined as not having scratch region, to data
Processing module issues the instruction of pause processing, executes D150: issuing the finger retested from data analysis module to detection device 1
It enables.
Specifically, passing through addition pressure value (counterweight) resetting initialization after detection device 1 receives the instruction retested
Pressure value, and the supratectal another region (region that do not scratched) for choosing detectable substance executes T120.
D160: data processing module judge scratch region scratch state whether uniformly continuous, if so, formed processing letter
Breath.
Specifically, scratch state includes: uniformly continuous and non-homogeneous continuous.Data processing module inputs scratch region pre-
First trained deep learning network model, is compared with the sample image in deep learning network, determines scratch region
Scratch state whether uniformly continuous.
Further, if judging scratch state to be non-homogeneous continuous, execution D170: being non-homogeneous continuous by scratch state
Information feeds back to data analysis module, issues the instruction retested from data analysis module to detection device 1.
Specifically, passing through addition pressure value (counterweight) resetting initialization after detection device 1 receives the instruction retested
Pressure value, and the supratectal another region (region that do not scratched) for choosing detectable substance executes T120.
Further, if judging scratch state for uniformly continuous, processing information is formed, executes D2.
D2: processing information is sent to data analysis module.
Specifically, processing information are as follows: detectable substance has scratch region and scratch uniformly continuous.
Further, before being handled (i.e. execution step D1) to scratch status data, execute step D0: transceiver module will
Practical mobile number is uploaded to data analysis module, moves back and forth number analysis according to the first of former data by data analysis module
Whether detection device 1 executes operation correct, if practical mobile number, which is equal to first, moves back and forth number, operates errorless, executes
D1.If practical mobile number moves back and forth number not equal to first, operating trouble is issued by operation module to staff
Alarm and reminding.
T140: after receiving processing information, pressure total value is obtained.
Specifically, sending the instruction for obtaining data, weight to gravity sensor after data analysis module receives processing information
Force snesor according to obtain data instruction acquisition this detection addition counterweight total value (i.e. pressure total value, pressure total value be
This minimum for scraping difficulty performance detection off scrapes value off), and pressure total value is uploaded to inspection center 3.
T150: the difficulty attribute of the detectable substance is judged according to pressure total value.
Specifically, judging inspection according to the default pressure total value in former data after data analysis module receives pressure total value
Survey the difficulty attribute of object.The occurrence of the default pressure total value can according to the actual situation depending on, the application is preferably 500g weight
The gravity value of code.The gravity value G of 500g counterweight are as follows: G=mg=500g/1000*9.8N/kg=4.9N, in formula, G is gravity, single
Position is N;M is quality, unit kg;G is gravity coefficient, usually takes 9.8N/kg.
Wherein, pressure total value is less than or equal to the gravity value of 500g counterweight, then the difficulty attribute of detectable substance is to be easy to scrape
It opens;Judging result is gravity value of the total value greater than 500g counterweight that press, then the difficulty attribute of detectable substance is to be difficult to scrape off.
Further, as one embodiment, the detection pattern selected for scrape off information integrity detection, detection it is specific
Sub-step is as follows:
T210: opening force is scraped in setting second.
Further, inspection center 3 issues the instruction of setting initial pressure value to detection device 1.Detection device 1 receives
After instruction, scrape opening force size setting pressurizing device according to second second scrapes opening force.Second scrapes opening force size detected entirely
Cheng Zhongwei fixed value, specific size can according to the actual situation depending on.The application is preferably the gravity value of 250g counterweight.
T220: scraping opening force by second and back and forth press to detectable substance detection, obtains information integrity status data.
Specifically, the Buddha's warrior attendant head of detection device 1 is made to generate pressure to the coating of detectable substance under the action of second scrapes opening force
Power, data analysis module send move to the first control module according to detection pattern, and the first control module receives movement and refers to
It enables, and executes.Further, move includes the second reciprocating movement number of station, wherein second moves back and forth number
Equal to default reciprocating movement number, after detection device 1 completes default reciprocating movement number, passes through image acquisition device and acquire current inspection
The information integrity status data of object is surveyed, T230 is executed.
T230: judge information integrity status data according to former data and obtain judgement information.
Specifically, judging that information integrity status data and obtaining judges the sub-step of information according to former data are as follows:
F1: handling information integrity status data, and forms judgement information.
Specifically, handling information integrity status data, and is formed and judges that the sub-step of information is as follows:
F110: data processing module obtains detection object image.
Specifically, data acquisition device 2 carries out Image Acquisition to detectable substance by image acquisition device, and it will test object image
It is sent to transceiver module, data processing module is sent to by transceiver module, executes F120.Wherein, image acquisition device can be photograph
Camera, fish-eye camera etc., the application are preferably fish-eye camera.
F120: data processing module carries out distortion correction and pretreatment to detection object image, obtains the second data set.
Specifically, pretreatment includes to the processing of detectable substance image normalization and whitening pretreatment after completion distortion correction;
Pre-treatment step are as follows: by reducing data redundancy to input data dimensionality reduction, inhibit over-fitting.
Specifically, carrying out distortion correction to detection object image uses spherical projection model method, calculation amount is small and precision is high,
It is specific as follows:
According to the spherical coordinate model foundation conventional coordinates in fish-eye camera image-forming principle, its position and side are adjusted
To making the camera of fish-eye camera be located at coordinate axis origin 0, along 0z axis positive direction, the original image after shooting is fallen in shooting direction
In 0xy plane.
Determine the coordinate conversion relation formula between correction image and original image:
In formula, (x, y, z) is original image 3D coordinate points, and (a, b) is correction image coordinate points, and r is that panorama picture of fisheye lens is former
The spherical radius of spherical coordinate model in reason.
F130: the second data set is inputted trained deep learning network model in advance by data processing module, is carried out special
Sign is extracted, and is obtained second and is extracted data.
Wherein, the second extraction data include: the covering layer region of detectable substance and/or scrape information area off.
Specifically, the second extraction data are sent to data analysis module, are held after data processing module completes feature extraction
Row F140.
F140: data processing module receives the instruction that data analysis module extracts data feedback according to second, and instruction includes
Pause is handled and is continued with, if received instruction executes F160 to continue with.
Further, data analysis module judges whether initial coverage area has and scrapes information off according to the second extraction data
Region, if extract data include detectable substance detectable substance covering layer region and scrape information area off, be determined as have scrape off
Information area issues the instruction continued with to data processing module, executes F150.
Further, if extract data only include detectable substance initial overlay layer region, be determined as do not have scrape letter off
Region is ceased, the instruction of pause processing is issued to data processing module, first is formed and judges information, execute F2, wherein the first judgement
Information is that nothing scrapes information off.
F150: judgement scrape off information area whether scrape information off complete, if so, forming second judges information.
Specifically, data processing module, which will scrape information area off, inputs trained deep learning network model in advance, with
Sample image in deep learning network is compared, determine to scrape off information area whether scrape information off complete, if completely, number
Judge that information is uploaded to data analysis module for second according to processing module.Wherein, second judges information to scrape information off and scraping
It is complete to open information, executes F2.
If it is imperfect to scrape information off, forms third and judge information.
Specifically, third is judged that information is uploaded to data analysis module by data processing module.Wherein, third judges information
It is imperfect to scrape information off but scraping information off, execute F2.
F2: information is judged to data analysis module transmission.
Specifically, judging that information judges that information, second judge that information or third judge information for first.
Further, before being handled (i.e. execution step F1) to information integrity status data, step F0 is executed: transmitting-receiving
Practical mobile number is uploaded to data analysis module by module, the default reciprocating movement time by data analysis module according to former data
Whether the number execution operation of analysis and detection device 1 is correct, if practical mobile number, which is equal to preset, moves back and forth number, operates nothing
Accidentally, F1 is executed.If practical mobile number moves back and forth number not equal to default, operating trouble, by operation module to work
Personnel sound an alarm prompting.
Specifically, experiment needs to reset sensor for countering before starting, and the process of 1 movable operating platform of detection device, station
Stage body top touching sensor for countering switch, complete data statistics.
T240: according to the information integrity attribute for judging that information judges the detectable substance.
Specifically, information integrity attribute includes: effective protection coverage information and is difficult to protect coverage information.In detectable substance
The same position of (anti-counterfeiting mark) coating, under the gravity of 250g counterweight, station is moved back and forth 12 times, coverage information
Without any destruction, that is, being considered as it is complete can to scrape rear information off with effective protection coverage information.After moving back and forth 12 times, if judgement letter
Breath is imperfect to scrape information off but scraping information off, then be considered as can not effective protection coverage information, it is imperfect to scrape rear information off, inspection
The information integrity attribute for surveying object is to be difficult to protect coverage information.If judging information for without scraping information area off or scrape off
Information and to scrape information off complete, then being considered as can scrape that rear information is complete off with effective protection coverage information, and the information of detectable substance is complete
Property attribute be effective protection coverage information.
What the application realized has the beneficial effect that:
The application has the detection method and evaluation foundation for improving scratch type anti-counterfeiting mark coating, guarantees inspection
Survey more objective result, specification and clear technical effect.
Although the preferred embodiment of the application has been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.Obviously, those skilled in the art can be to the application
Various modification and variations are carried out without departing from spirit and scope.If in this way, these modifications and variations of the application
Belong within the scope of the claim of this application and its equivalent technologies, then the application is also intended to encompass these modification and variations and exists
It is interior.
Claims (10)
1. a kind of detection method of anti-counterfeiting mark, which comprises the steps of:
Prestore detection pattern and former data corresponding with detection pattern;
Detection pattern is selected, and calls former data corresponding with the detection pattern of selection;
According to the status data of detection pattern acquisition testing object, and the status data of former data analysis detection object is compared, obtains this
The detectable substance attribute of detectable substance.
2. the detection method of anti-counterfeiting mark according to claim 1, which is characterized in that detection pattern includes at least: scraping off
Difficulty detects and scrapes off information integrity detection;Detectable substance attribute includes at least: difficulty attribute and information integrity attribute.
3. the detection method of anti-counterfeiting mark according to claim 2, which is characterized in that when the detection pattern selected is scrapes off
Difficulty detection, the specific sub-step of detection are as follows:
Initial pressure value is set;
The scratch status data of detectable substance is obtained to the pressure detection of detectable substance according to initial pressure value;
Judge scratch status data according to former data and obtain processing information;
After receiving processing information, pressure total value is obtained;
The difficulty attribute of the detectable substance is judged according to pressure total value.
4. the detection method of anti-counterfeiting mark according to claim 3, which is characterized in that difficulty attribute includes being difficult to scrape off
Be easy to scrape off.
5. the detection method of anti-counterfeiting mark according to claim 4, which is characterized in that data analysis module is according to former data
Judge scratch status data and the specific sub-step for obtaining processing information be as follows:
Data processing module handles scratch status data, and forms processing information;
Data processing module sends processing information to data analysis module.
6. the detection method of anti-counterfeiting mark according to claim 5, which is characterized in that handle scratch status data
Sub-step it is as follows:
Obtain detection object image;
Distortion correction and pretreatment are carried out to detection object image, obtain the first data set;
First data set is inputted trained deep learning network model in advance by data processing module, is carried out feature extraction, is obtained
Take the first extraction data;
Data processing module receive data analysis module according to first extract data feedback instruction, instruction include pause processing and
Continue with, if received instruction to continue with, judge scratch region scratch state whether uniformly continuous, if scratch shape
State is uniformly continuous, then forms processing information.
7. the detection method of anti-counterfeiting mark according to claim 6, which is characterized in that carry out distortion school to detection object image
Just use spherical projection model method, wherein sit according to the spherical coordinate model foundation standard in fish-eye camera image-forming principle
Mark system, adjusts its position and direction, and the camera of fish-eye camera is made to be located at coordinate axis origin 0, shooting direction along 0z axis positive direction,
Original image after shooting is fallen in 0xy plane;Determine that the coordinate conversion relation formula between correction image and original image is as follows:
In formula, (x, y, z) is original image 3D coordinate points, and (a, b) is correction image coordinate points, and r is in panorama picture of fisheye lens principle
Spherical coordinate model spherical radius.
8. the detection method of anti-counterfeiting mark according to claim 2, which is characterized in that the detection pattern selected is scrapes letter off
Integrity detection is ceased, the specific sub-step of detection is as follows:
Opening force is scraped in setting second;
Opening force is scraped by second back and forth to press to detectable substance detection, obtains information integrity status data;
Judge information integrity status data according to former data and obtain judgement information;
According to the information integrity attribute for judging that information judges the detectable substance.
9. a kind of detection system of anti-counterfeiting mark characterized by comprising in detection device, data acquisition device and detection
The heart;The inspection center connect with the detection device and the data acquisition device respectively;
The detection device: the instruction that the inspection center sends is received, and detectable substance is detected according to described instruction;
The data acquisition device: the data during detectable substance are detected for collecting and detecting device, and the data are uploaded
The inspection center;
The inspection center: receiving and processing the data that the data acquisition device uploads, to detection device under send instructions, execute
The detection method of anti-counterfeiting mark described in any one of claim 1-8.
10. the detection system of anti-counterfeiting mark according to claim 9, which is characterized in that the inspection center includes: data
Processing module, transceiver module, data analysis module, memory module and operation module;The data processing module respectively with institute
Transceiver module, the data analysis module, the digital-to-analogue block of depositing is stated to connect;The operation module respectively with the memory module,
Data processing module, transceiver module are connected with data analysis module;
The data processing module: the data uploaded for receiving and processing the transceiver module, and data are sent out by treated
It send to the data analysis module and is analyzed;
The transceiver module: the data of acquisition device acquisition for receiving data send the data to the data processing
Module receives the instruction that data analysis module issues, and is sent to the detection device;
The memory module: for detection pattern and former data corresponding with the detection pattern to be stored in advance;
The operation module: for detection pattern and former data corresponding with the detection pattern to be arranged;Selection detection mould;
Show testing result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910625487.5A CN110308091B (en) | 2019-07-11 | 2019-07-11 | Detection method and system for anti-counterfeiting mark |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910625487.5A CN110308091B (en) | 2019-07-11 | 2019-07-11 | Detection method and system for anti-counterfeiting mark |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110308091A true CN110308091A (en) | 2019-10-08 |
CN110308091B CN110308091B (en) | 2024-06-25 |
Family
ID=68080154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910625487.5A Active CN110308091B (en) | 2019-07-11 | 2019-07-11 | Detection method and system for anti-counterfeiting mark |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110308091B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110239748A1 (en) * | 2010-04-05 | 2011-10-06 | Korea Research Institute Of Chemical Technology | Quantitative evaluation of scratch-induced damages on polymeric and coating materials |
KR20110111756A (en) * | 2010-04-05 | 2011-10-12 | 한국화학연구원 | Quantitative determination of scratch visibility for polymeric and coating materials |
TW201224426A (en) * | 2010-12-01 | 2012-06-16 | Univ St Johns | An adhesion testing device of thin films |
CN102564945A (en) * | 2011-12-29 | 2012-07-11 | 联通兴业通信技术有限公司 | Method and device for measuring and evaluating password lamination property of telecommunication card |
CN202372420U (en) * | 2011-12-20 | 2012-08-08 | 神龙汽车有限公司 | Tool used for detecting scratch resistance of paint on surface of plastic piece |
CN102692355A (en) * | 2012-06-15 | 2012-09-26 | 山东泰宝防伪技术产品有限公司 | Method for detecting surface quality of anti-counterfeiting digital label |
US20160334315A1 (en) * | 2015-05-12 | 2016-11-17 | Nanovea, Inc. | Method for automated parameter and selection testing based on known characteristics of the sample being tested |
CN107238528A (en) * | 2017-06-15 | 2017-10-10 | 深圳市旺盈彩盒纸品有限公司 | A kind of printed matter scratch-resistant tester and its method of testing |
CN108021926A (en) * | 2017-09-28 | 2018-05-11 | 东南大学 | A kind of vehicle scratch detection method and system based on panoramic looking-around system |
US20180293726A1 (en) * | 2017-04-05 | 2018-10-11 | Asmec Advanced Surface Mechanics Gmbh | Method for the Analysis of Surface Measurements |
CN208043578U (en) * | 2018-02-10 | 2018-11-02 | 苏州艾驰博特检测科技有限公司 | A kind of plastics scratch-resistant experiment improvement device |
-
2019
- 2019-07-11 CN CN201910625487.5A patent/CN110308091B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110239748A1 (en) * | 2010-04-05 | 2011-10-06 | Korea Research Institute Of Chemical Technology | Quantitative evaluation of scratch-induced damages on polymeric and coating materials |
KR20110111756A (en) * | 2010-04-05 | 2011-10-12 | 한국화학연구원 | Quantitative determination of scratch visibility for polymeric and coating materials |
TW201224426A (en) * | 2010-12-01 | 2012-06-16 | Univ St Johns | An adhesion testing device of thin films |
CN202372420U (en) * | 2011-12-20 | 2012-08-08 | 神龙汽车有限公司 | Tool used for detecting scratch resistance of paint on surface of plastic piece |
CN102564945A (en) * | 2011-12-29 | 2012-07-11 | 联通兴业通信技术有限公司 | Method and device for measuring and evaluating password lamination property of telecommunication card |
CN102692355A (en) * | 2012-06-15 | 2012-09-26 | 山东泰宝防伪技术产品有限公司 | Method for detecting surface quality of anti-counterfeiting digital label |
US20160334315A1 (en) * | 2015-05-12 | 2016-11-17 | Nanovea, Inc. | Method for automated parameter and selection testing based on known characteristics of the sample being tested |
US20180293726A1 (en) * | 2017-04-05 | 2018-10-11 | Asmec Advanced Surface Mechanics Gmbh | Method for the Analysis of Surface Measurements |
CN107238528A (en) * | 2017-06-15 | 2017-10-10 | 深圳市旺盈彩盒纸品有限公司 | A kind of printed matter scratch-resistant tester and its method of testing |
CN108021926A (en) * | 2017-09-28 | 2018-05-11 | 东南大学 | A kind of vehicle scratch detection method and system based on panoramic looking-around system |
CN208043578U (en) * | 2018-02-10 | 2018-11-02 | 苏州艾驰博特检测科技有限公司 | A kind of plastics scratch-resistant experiment improvement device |
Also Published As
Publication number | Publication date |
---|---|
CN110308091B (en) | 2024-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8407625B2 (en) | Behavior recognition system | |
US9043026B2 (en) | Method and device for actuating a key of a keyboard with a tracer finger of a robot | |
CN105069423A (en) | Human body posture detection method and device | |
CN109035204A (en) | A kind of weld seam target real-time detection method | |
CN107832802A (en) | Quality of human face image evaluation method and device based on face alignment | |
CN105959585B (en) | Multistage backlighting detecting and device | |
CN108090896B (en) | Wood board flatness detection and machine learning method and device and electronic equipment | |
CN105975925B (en) | Partial occlusion pedestrian detection method based on joint-detection model | |
CN106909220A (en) | A kind of sight line exchange method suitable for touch-control | |
CN110009614A (en) | Method and apparatus for output information | |
CN109685761A (en) | A kind of power cable defect inspection method and its detection system based on cloud platform | |
CN106126786A (en) | Cockpit display Human Machine Interface ergonomic's quantitative evaluating method | |
CN109359514A (en) | A kind of gesture tracking identification federation policies method towards deskVR | |
KR101282319B1 (en) | Method and apparatus for virtual golf simulation measuring golf ability of the user | |
CN110415238A (en) | Diaphragm spots detection method based on reversed bottleneck structure depth convolutional network | |
Hartl | Computer-vision based pharmaceutical pill recognition on mobile phones | |
CN108090922A (en) | Intelligent Target pursuit path recording method | |
CN102750536A (en) | Image processing apparatus, image processing method, and program | |
CN108229494A (en) | network training method, processing method, device, storage medium and electronic equipment | |
CN116092199A (en) | Employee working state identification method and identification system | |
CN110308091A (en) | A kind of detection method and system of anti-counterfeiting mark | |
CN100580372C (en) | System for testing life buoy for military use on controlling pose of human body in water | |
CN101021948A (en) | Automatic identifying device and method for joint in human body symmetric motion image | |
CN109033999B (en) | Subway charge platform based on face recognition | |
Colvin et al. | Multiple user motion capture and systems engineering |
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 |