CN209624411U - Defects identification equipment - Google Patents
Defects identification equipment Download PDFInfo
- Publication number
- CN209624411U CN209624411U CN201822152325.8U CN201822152325U CN209624411U CN 209624411 U CN209624411 U CN 209624411U CN 201822152325 U CN201822152325 U CN 201822152325U CN 209624411 U CN209624411 U CN 209624411U
- Authority
- CN
- China
- Prior art keywords
- imaging device
- data
- pattern recognition
- test product
- equipment according
- 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.)
- Active
Links
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
This application discloses defects identification equipment, comprising: the first imaging device, the global image being located in detection zone for acquiring test product;Second imaging device, the defect position information collection of the test product for being included according to global image include the topography of fault;And pattern recognition device, for reception and corresponding first data of the global image and the second data corresponding with the topography and defects identification processing is carried out to first data and second data.The scheme of embodiments herein first identifies the global image of test product, is determining there are when surface-defect, then identify to the topography of test product, is effectively increasing the surface-defect recognition speed of the long products in advancing.
Description
Technical field
This application involves identification apparatus fields, in particular to defects identification equipment.
Background technique
On such as production line of the products such as textile, leather, whether the product for needing identification producing or producing
There are surface-defects, for example, whether having spot, spot etc. on product.This kind of product is long products, has certain length,
When identifying to this kind of product, product is presently mainly unfolded to by identification equipment and is continuously sent to detection zone,
The product produced continuously is transmitted region after testing while producing by either production equipment, is then stood by testing staff
The test product observed in identification region otherwise is known by naked eyes before detection device or production equipment, to discover whether
There are fault and recorded.In the case where yield is very big, being identified by testing staff will be had high labor costs, moreover, detection
Personal identification speed is very slow, and fatigue is easy after a period of time that works, to there is a possibility that erroneous detection occurs.Therefore, by
Testing staff is inefficient come the overall defect detection identified and recognition accuracy is not sufficiently stable.
In recent years, develop the defects identification technology based on machine vision gradually to replace artificial detection, adopted using camera
Collect test product image and using pattern recognition device operation defects identification application program and/or recognizer (such as nerve
Network model) image is detected to identify to fault.At present often by a certain range of global figure of acquisition
Picture analyzes global image, but due to fault often very little, carries out analyzing occupied calculating providing to global image
Source is larger, causes defects identification speed slower.
Summary of the invention
In view of problem above, embodiments herein provides defects identification equipment, can improve surface-defect recognition speed
And accuracy.
According to the defects identification equipment of embodiments herein, comprising: the first imaging device, for acquiring test product position
In the global image in detection zone;Second imaging device, the fault position of the test product for being included according to global image
Set the topography that information collection includes fault;And pattern recognition device, for receiving corresponding with the global image the
One data and the second data corresponding with the topography simultaneously carry out fault knowledge to first data and second data
Other places reason.
In one embodiment, described image identification device includes that the first pattern recognition device and the second image recognition fill
It sets, the first image identification device is used to receive first data and carries out defects identification processing to first data,
Second pattern recognition device is for receiving second data and carrying out defects identification processing to second data.
In one embodiment, the first image identification device operation first nerves network model and described the
Two pattern recognition devices run nervus opticus network model.
In one embodiment, the first nerves network model is convolutional neural networks model and described second
Neural network model is the convolutional neural networks model based on region.
In one embodiment, first imaging device includes the fixed camera in one or more positions, Yi Jisuo
Stating the second imaging device includes the adjustable camera in one or more positions.
In one embodiment, the equipment further includes control device, is used to control first imaging device and adopts
Collect global image, and the second imaging device of control acquires topography.
In one embodiment, the equipment further includes labelling apparatus, is used for the control according to the control device
Fault is marked in instruction.
In one embodiment, the equipment further includes conveying device, be used to convey test product continually by
The detection zone.
In one embodiment, the conveying device includes the first live-roller and the second live-roller, the detection zone
It is arranged between first live-roller and second live-roller, is provided with bracket above the detection zone, described first
Imaging device and second imaging device are one in front and one in back arranged on the bracket along transmission direction
It can be seen from the above that the scheme of embodiments herein utilizes nerual network technique, rather than people comes
The test product that identification image is included is with the presence or absence of surface-defect, and compared with people, nerual network technique is not in fatigue
Situation constantly can identify the test product that image is included with the presence or absence of surface defect with higher recognition accuracy
Point is determining that there are surface-defects moreover, the scheme of embodiments herein first identifies the global image of test product
When, then the topography of test product is identified, effectively increase the surface-defect recognition speed of the long products in advancing.
Detailed description of the invention
Fig. 1 is the schematic diagram of the defects identification equipment of the application one embodiment;
Fig. 2 is the schematic diagram of the defects identification equipment of another embodiment of the application.
Fig. 3 is the structural schematic diagram of the defects identification equipment of the application one embodiment.
Specific embodiment
Theme described herein is discussed referring now to example embodiment.It should be understood that discussing these embodiments only
It is in order to enable those skilled in the art can better understand that being not to claim to realize theme described herein
Protection scope, applicability or the exemplary limitation illustrated in book.It can be in the protection scope for not departing from present disclosure
In the case of, the function and arrangement of the element discussed are changed.Each example can according to need, omit, substitute or
Add various processes or component.For example, described method can be executed according to described order in a different order, with
And each step can be added, omits or combine.In addition, feature described in relatively some examples is in other examples
It can be combined.
As used in this article, term " includes " and its modification indicate open term, are meant that " including but not limited to ".
Term "based" indicates " being based at least partially on ".Term " one embodiment " and " embodiment " expression " at least one implementation
Example ".Term " another embodiment " expression " at least one other embodiment ".Term " first ", " second " etc. may refer to not
Same or identical object.Here may include other definition, either specific or implicit.Unless bright in context
It really indicates, otherwise the definition of a term is consistent throughout the specification.
In the description of the present application, the meaning of " plurality " is two or more, unless otherwise specifically defined.
In the description of the present application, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected or can be in communication with each other;It can be directly connected, it can also be by between intermediary
It connects connected, can be the connection inside two elements or the interaction relationship of two elements.For the ordinary skill of this field
For personnel, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
Following disclosure provides many different embodiments or example is used to realize the different structure of the application.In order to
Simplify disclosure herein, hereinafter to the component of specific examples and being set for describing.Certainly, they are merely examples, and
And purpose does not lie in limitation the application.In addition, this application provides various specific techniques and material example, but ability
Domain those of ordinary skill can be appreciated that the application of other techniques and/or the use of other materials.
Scheme provided by the embodiments of the present application is located at complete in detection zone using the first imaging device acquisition test product
Office's image, the defect position information collection for the test product for being included according to global image using the second imaging device include fault
Topography, and utilize corresponding second number of corresponding to global image the first data of pattern recognition device and topography
According to defects identification processing is carried out, therefore, nerual network technique is utilized with the scheme of prior art embodiments herein, rather than
People, to identify that the test product that image is included whether there is surface-defect, compared with people, nerual network technique is not in tired
The case where labor, constantly can identify the test product that image is included with the presence or absence of surface with higher recognition accuracy
Fault is determining that there are tables moreover, the scheme of embodiments herein first carries out defects identification to the global image of test product
When the fault of face, then defects identification is carried out to the topography of test product, effectively increases the surface defect of the long products in advancing
Point recognition speed.
Long products described in the embodiment of the present application refer to the product such as textile, leather with certain length, are using
When imaging device carries out Image Acquisition to product, need to complete the surface image acquisition of entire product by multi collect.
By taking textile as an example, with certain code length, usually stored in coiled mode.Length in traveling described in the embodiment of the present application
Product can refer to that long products continuously transmit region after testing by transmission equipment, so that the surface to long products connects
Continuous Image Acquisition and detection.The detection zone can be the monitor station of product detection device, be also possible to Production equipment
Product output region, such as can be the cloth inspection table of cloth inspecting machine or the weaving region of loom.
In order to keep the technical solution of the application clearer, below in conjunction with concrete scene to provided by the embodiments of the present application
Defects identification equipment is introduced.
As shown in Figure 1, in one embodiment, defects identification equipment may include the first imaging device 102, second imaging dress
Set 104, pattern recognition device 106 and conveying device 108.First imaging device 102 and the second imaging device 104 respectively with figure
As identification device 106 connects.
Wherein, the first imaging device 102 can for example use CCD or CMOS camera, above-mentioned CCD (Charge
Coupled Device, photosensitive coupling component) it is the semiconductor subassembly changed in digital camera for recording light, it is above-mentioned
CMOS (Complementary Metal Oxide Semiconductor, complementary metal oxide semiconductor) is a kind of usual
The sensor of 10 times of sensitivity lower than ccd sensor.
Second imaging device 104 can for example use CCD or CMOS camera, above-mentioned CCD (Charge Coupled
Device, photosensitive coupling component) it is in digital camera for recording the semiconductor subassembly of light variation, above-mentioned CMOS
(Complementary Metal Oxide Semiconductor, complementary metal oxide semiconductor) is that one kind usually compares CCD
The sensor of the low 10 times of sensitivity of sensor.
Pattern recognition device 106 for example can be the computer for being equipped with picture recognition module or other with computing capability
Electronic equipment, picture recognition module for example can be the CPU processor, FPGA processor or GPU of operation image recognizer
Processor.
Conveying device 108 can be for example made of drive rotor, live-roller or folding and unfolding wound module, and conveying device 108 can be with
Test product is driven to advance with certain speed.It specifically, can be in the conveyor zones (area of A to B as shown in figure 1 of conveying device 108
Domain) in select a region as detection zone.In this way, can make long products in traveling continually by the detection zone.
In the embodiment of the present application, the first imaging device 102 is for acquiring the overall situation that test product is located in detection zone
Image.First imaging device 102 can be fixed to the top of detection zone, by adjusting the coke of the first imaging device 102
Away from the global image of the test product in detection zone can be taken.When it is implemented, the first imaging device 102 can wrap
One or more cameras are included, such as a camera can not collect the global image of the test product in detection zone, can be by more
A camera acquires a part therein respectively, by the image mosaic of multiple portions at global image.
In the embodiment of the present application, the second imaging device 104 is used for the defect for the test product for being included according to global image
Dot position information acquisition includes the topography of fault.Therefore, the second imaging device 104 is passive acquisition, only when the first one-tenth
As device 104 acquire global image included test product there are when fault, the second imaging device 104 just can be according to fault
Location information acquisition fault position topography, otherwise the second imaging device 104 will not acquire.Due to can not be prior
Learn the position where fault, therefore the second imaging device 104 may include one or more cameras of adjustable position, specifically
, the second imaging device 104 can carry out including front and rear, left and right, at least one position adjustment mode moved up and down.Second imaging
Device 104 can be moved to above fault position by adjusting position, carry out closely or focal length furthers and shoots comprising fault
Topography.If global image includes multiple faults, multiple cameras can be used to shoot corresponding different faults respectively.A kind of reality
It applies in mode, since test product is advanced under the drive of conveying device 108, the second imaging device 102 can be arranged
The front upper place of detection zone direction of travel, the test product that area to be tested is included march to 102 lower section of the second imaging device
When, the second imaging device 102 acquires topography.
In the embodiment of the present application, the global image and the second imaging device 104 of the first imaging device 102 acquisition acquire
Topography carries out defects identification processing by pattern recognition device 106.It is corresponding that pattern recognition device 106 receives global image
Then corresponding second data of first data and topography carry out defects identification processing to the first data and the second data.Figure
It whether there is fault in global image as identification device 106 can identify, the location information of fault determined if there are fault.Figure
As identification device 106 can identify the type for the fault for including in topography, and export fault type information.Image recognition dress
Setting 106 for example can carry out identifying processing to the first data and the second data by neural network model, naturally it is also possible to use
Other kinds of image recognition algorithm.
In one embodiment, pattern recognition device 106 may include the first pattern recognition device and the second image recognition dress
It sets, wherein the first pattern recognition device is for receiving corresponding first data of global image and carrying out at identification to the first data
Reason, the second pattern recognition device is for receiving corresponding second data of topography and carrying out identifying processing to the second data.Phase
It answers, the first pattern recognition device can run first nerves network model and carry out identifying processing and second to the first data
Pattern recognition device can run nervus opticus network model and carry out identifying processing to the second data, wherein first nerves network
Model can be convolutional neural networks (CNN:Convolutional Neural Network) model and nervus opticus network
Model can be convolutional neural networks (the RCNN:Region Based Convolutional Neural based on region
Network) model.
Other modifications: although it will be understood by those skilled in the art that in the above embodiments, defects identification equipment includes defeated
Device 108 is sent, however, the present invention is not limited thereto.In the other embodiments of the application, such as, but not limited to, right
It can not also include conveying device 108 in the limited situation of test product size.
As shown in Fig. 2, in another embodiment, defects identification equipment may include the imaging of the first imaging device 102, second
Device 104, pattern recognition device 106, control device 110 and labelling apparatus 112.Wherein, the first imaging device 102 and second
Imaging device 104 is connect with pattern recognition device 106 respectively, and pattern recognition device 106 is connect with control device 110, control dress
110 are set to connect with the second imaging device 104 and labelling apparatus 112 respectively.
In the embodiment of the present application, the first imaging device 102 and the second imaging device 104 can pass through the network switch or nothing
Line communication link is connect with pattern recognition device 106.Certainly, it should be noted that above-mentioned connection type is only intended to illustrate
It is bright, when it is implemented, can be as the case may be using other connection types in addition to above-mentioned connection type, in this regard, this is practical
It is novel to be not construed as limiting.Pattern recognition device 106 receives corresponding first data of global image of the first imaging device 102 acquisition,
And receive corresponding second data of topography of the second imaging device 104 acquisition.
In the embodiment of the present application, control device 110 includes that (Programmable Logic Controller, can by PLC
Programmed logic controller) control cabinet or signal input/output unit (I/O), control device 110 can pass through the side that serial ports connects
Formula is connect with pattern recognition device 106, and pattern recognition device 106 can send control signal (including fault position to control device 110
Confidence breath), received control signal is sent to the second imaging device 104 and labelling apparatus connected to it by control device 110
112.In the embodiment of the present application, control device 110 can be with the position adjust drivers and camera imaging of the second imaging device 104
Processing controller connection controls the second imaging device adjustment position and progress according to the control signal of image recognition position 106
Image Acquisition.In the embodiment of the present application, for the fault identified to be marked, labelling apparatus 112 wraps labelling apparatus 112
Include ink spraying marking device or label labelling apparatus.
Other modifications, although it will be understood by those skilled in the art that in the above embodiments, defects identification equipment includes mark
Device 112 is remembered, however, the present invention is not limited thereto.In the other embodiments of the application, such as, but not limited to, at this
It can not also include labelling apparatus 112 in the other embodiments of application.
As shown in figure 3, in one embodiment, defects identification equipment may include the first imaging device 102, second imaging dress
Set 104, pattern recognition device 106, conveying device 108, bracket 114 and rack 116.
In the embodiment of the present application, conveying device 108 includes the first live-roller 1082 and the second live-roller 1084, and first passes
The synchronous rotation of dynamic roller 1082 and the second live-roller 1084 can drive test product to advance with certain speed along transmission direction.To quilt
The detection zone that product is detected is surveyed to be arranged between the first live-roller 1082 and the second live-roller 1084.
In the embodiment of the present application, bracket 114 is arranged above detection zone, the first imaging device 102 and the second imaging
Device 104 is one in front and one in back arranged on bracket 114 along transmission direction.In a kind of embodiment, bracket 114 may include first support
1142 and second support 1144, wherein the first imaging device 102 is arranged in first support 1142, and the first imaging device 104 is set
It sets in second support 1144.In the embodiment of the present application, the first imaging device 102 includes two cameras, the first imaging device 102
It is fixed setting in first support 1142, the second imaging device 104 includes a camera, settable cunning in second support 1144
Rail, the second imaging device 104 can be slided along sliding rail.
In the embodiment of the present application, the first imaging device 102, the second imaging device 104, conveying device 108 and bracket 114
It is mounted in rack 116.Global image in first imaging device 102 acquisition monitoring region, is then issued to pattern recognition device
106 are identified, defect position information are given to the control device being arranged in second support 1144 if identifying fault, by controlling
Device processed controls the second imaging device 104 and slides into above fault position, and the acquisition of the second imaging device 104 includes fault
Topography is then forwarded to pattern recognition device 106 and carries out fault type identification.
The specific embodiment illustrated above in conjunction with attached drawing describes exemplary embodiment, it is not intended that may be implemented
Or fall into all embodiments of the protection scope of claims." exemplary " meaning of the term used in entire this specification
Taste " be used as example, example or illustration ", be not meant to than other embodiments " preferably " or " there is advantage ".For offer pair
The purpose of the understanding of described technology, specific embodiment include detail.However, it is possible in these no details
In the case of implement these technologies.In some instances, public in order to avoid the concept to described embodiment causes indigestion
The construction and device known is shown in block diagram form.
The foregoing description of present disclosure is provided so that any those of ordinary skill in this field can be realized or make
Use present disclosure.To those skilled in the art, the various modifications carried out to present disclosure are apparent
, also, can also answer generic principles defined herein in the case where not departing from the protection scope of present disclosure
For other modifications.Therefore, present disclosure is not limited to examples described herein and design, but disclosed herein with meeting
Principle and novel features widest scope it is consistent.
Claims (9)
1. defects identification equipment, characterized in that include:
First imaging device, the global image being located in detection zone for acquiring test product;
Second imaging device, the defect position information collection of the test product for being included according to global image include fault
Topography;And
Pattern recognition device, for receiving and corresponding first data of the global image and corresponding with the topography the
Two data simultaneously carry out defects identification processing to first data and second data.
2. equipment according to claim 1, wherein described image identification device includes the first pattern recognition device and second
Pattern recognition device, the first image identification device is for receiving first data and carrying out fault to first data
Identifying processing, second pattern recognition device is for receiving second data and carrying out defects identification to second data
Processing.
3. equipment according to claim 2, wherein the first image identification device runs first nerves network model,
And second pattern recognition device runs nervus opticus network model.
4. equipment according to claim 3, wherein the first nerves network model is convolutional neural networks model, with
And the nervus opticus network model is the convolutional neural networks model based on region.
5. equipment according to claim 1, wherein first imaging device includes the fixed phase in one or more positions
Machine and second imaging device include the adjustable camera in one or more positions.
6. equipment according to claim 5, wherein the equipment further includes control device, is used to control described second
Imaging device.
7. equipment according to claim 6, wherein the equipment further includes labelling apparatus, is used for according to the control
Fault is marked in the control instruction of device.
8. equipment according to claim 1, wherein the equipment further includes conveying device, is used to convey test product
Continually by the detection zone.
9. equipment according to claim 8, wherein the conveying device includes the first live-roller and the second live-roller, institute
It states detection zone to be arranged between first live-roller and second live-roller, is provided with branch above the detection zone
Frame, first imaging device and second imaging device are one in front and one in back arranged on the bracket along transmission direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201822152325.8U CN209624411U (en) | 2018-12-20 | 2018-12-20 | Defects identification equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201822152325.8U CN209624411U (en) | 2018-12-20 | 2018-12-20 | Defects identification equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN209624411U true CN209624411U (en) | 2019-11-12 |
Family
ID=68446361
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201822152325.8U Active CN209624411U (en) | 2018-12-20 | 2018-12-20 | Defects identification equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN209624411U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109580645A (en) * | 2018-12-20 | 2019-04-05 | 深圳灵图慧视科技有限公司 | Defects identification equipment |
-
2018
- 2018-12-20 CN CN201822152325.8U patent/CN209624411U/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109580645A (en) * | 2018-12-20 | 2019-04-05 | 深圳灵图慧视科技有限公司 | Defects identification equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109580645A (en) | Defects identification equipment | |
CN103901040B (en) | Three-dimensional online network defect detection system based on machine vision | |
WO2020146785A1 (en) | Wearable visualization system and method | |
CN103170459A (en) | Spectacle lens flaw detection system | |
CN109297969A (en) | A kind of tobacco leaf assembly line method for detecting impurities and system | |
CN101482518A (en) | On-line quality detection system for movable band-shaped material | |
CN109089013A (en) | A kind of multiple light courcess detection image acquisition methods and Machine Vision Inspecting System | |
CN104299284B (en) | Indoor substation track inspection system, host and method for automatically positioning and capturing equipment image | |
CN104475350B (en) | Bearing holder false welding visual inspection method | |
CN106767423A (en) | Automatic Visual Inspection instrument | |
CN106327483A (en) | Method, system and device for attaching logo of detection equipment | |
CN106896110A (en) | Product quality detection means and method based on monocular camera machine vision | |
CN106018430A (en) | Six-surface vision detecting device and control method thereof | |
CN102879404B (en) | System for automatically detecting medical capsule defects in industrial structure scene | |
CN209624411U (en) | Defects identification equipment | |
CN109507205A (en) | A kind of vision detection system and its detection method | |
CN108037132A (en) | A kind of visual sensor system and method for the detection of dry cell pulp layer paper winding defect | |
CN104931502A (en) | Multidimensional detection robot and detection method | |
CN110044921A (en) | Lithium battery open defect detection system and method | |
CN105784720A (en) | Cloth defect detection method and system thereof | |
CN108855992A (en) | A kind of detection of glass and defective products rejecting mechanism | |
CN109719056A (en) | A kind of camera module focusing assembly line and its method based on machine vision | |
CN108195847A (en) | A kind of relief pattern Online Video detection device and its detection method | |
CN201503261U (en) | Automatic detecting device for infusion needles | |
CN103913467B (en) | Quilting line breakage detection method based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |