CN109406533A - A kind of detection system and method for surface defects of products - Google Patents
A kind of detection system and method for surface defects of products Download PDFInfo
- Publication number
- CN109406533A CN109406533A CN201811253443.6A CN201811253443A CN109406533A CN 109406533 A CN109406533 A CN 109406533A CN 201811253443 A CN201811253443 A CN 201811253443A CN 109406533 A CN109406533 A CN 109406533A
- Authority
- CN
- China
- Prior art keywords
- product
- camera
- image
- control module
- light source
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
Abstract
The present invention provides a kind of detection system of surface defects of products and methods.System includes: catching robot, inspecting manipuator, control module and defect detecting device, and the defect detecting device includes: first camera and second camera；The image of the first camera upper surface of shooting detected product, second camera are used to shoot the image of the lower surface of the detected product；The image of the upper surface of the collected product is sent to control module by first camera；Control module whether there is defect according to the upper surface of the image detection product of the upper surface of product, and export the first testing result；The image of the lower surface of the collected product is sent to the control module by second camera；The upper surface of control module product according to the image detection of the lower surface of the product whether there is defect, and export the second testing result.In this way, the automatic detection to surface defects of products may be implemented.
Description
Technical field
The present invention relates to technical field of vision detection, a kind of detection system in particular to surface defects of products and
Method.
Background technique
Since the surface defect of hard alloy cutter determines the precision of its service life and processing, with to cutter quality
Requirement it is higher and higher, realize to the defects detection of hard alloy cutter it is the key that improve hard alloy cutter quality and yield
One ring.
Since hard alloy mechanical process tool has ten several series, size, shape, Facing material varies in color, and allows
Flaw size be lower than human eye span of discrimination.Detection method in the prior art be inspector under the microscope, pass through naked eyes
Identify defect, this method speed is relatively slow, can not determine accurate product defects size, and human eye fatigue is be easy to cause to be formed
Missing inspection, since product category is more, more people, which divide the work, to be detected, it is difficult to form effective product information statistics.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of detection system of surface defects of products and method, to improve
To the efficiency of the defects detection on the surface of the products such as cutter.
In a first aspect, the embodiment of the invention provides a kind of detection systems of surface defects of products, comprising:
Catching robot, inspecting manipuator, control module and defect detecting device, the catching robot, detection are mechanical
Hand is connected with the control module；
The defect detecting device includes: first camera and second camera；The first camera is set to detection platform
Top, the second camera are set to the lower section of detection platform；The upper surface of first camera shooting detected product
Image, the second camera are used to shoot the image of the lower surface of the detected product；
The catching robot is used under the control of the control module meet preset production from material platform to be detected crawl
The product to be detected of product type information, and the product to be detected is put to the lower section of the first camera of detection platform, it touches
Send out the first camera described and acquire the image of the upper surface of the product；
The image of the upper surface of the collected product is sent to the control module by the first camera；The control
The upper surface of product described in image detection of the molding root tuber according to the upper surface of the product whether there is defect, and export the first inspection
Survey result；
The inspecting manipuator, for grabbing the product to second after the first camera Image Acquisition finishes
Camera detection zone after, trigger the image that the second camera acquires the lower surface of the product；
The image of the lower surface of the collected product is sent to the control module by the second camera；The control
The upper surface of product described in image detection of the molding root tuber according to the lower surface of the product whether there is defect, and export the second inspection
Survey result.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein institute
State system, further includes:
Light source controller, first light source and second light source, the first light source and the second light source with the light source
Controller is connected；The light source controller is connected with the control module；
The first light source is set to the lower section of the first camera, and the second light source is set to the second camera
Top；The first light source is respectively used to adopt in the first camera and second camera progress image with the second light source
Light filling when collection.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides second of first aspect
Possible embodiment, wherein be provided with third camera above the catching robot, the catching robot is also used to transporting
After moving to material platform to be detected position, triggers the third camera and be acquired the image comprising material platform to be detected, and will be described
Image is sent to control module, and the control module determines that meeting of being included on the material platform to be detected is pre- according to described image
If product type information product to be detected location information, the location information is sent to the catching robot, institute
Catching robot is stated for grabbing the product to be detected according to the position letter information.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein institute
It states control module to be also used to, the quality etc. of the product is determined according to first testing result and second testing result
Grade, according to the quality grade of the product determine the product belonging to material storage dish, and by material storage dish belonging to the product believe
Breath is sent to inspecting manipuator, and the inspecting manipuator is used for according to the material storage dish information, and the product is placed the storage
In charging tray.
In conjunction with one side, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein institute
Control module is stated, specifically for carrying out the upper of the product according to the image detection of the upper surface of the product in the following manner
Surface whether there is defect:
The control module receives the image of the upper surface of the product, and calling pre-establishes and trained neural network
Model calculate by the neural network model according to test parameter set by user, defect threshold value and described image
To defects detection result；Wherein, the test parameter includes: batch size numerical value and image cutting numerical value.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein institute
It states the first testing result and second testing result includes the following information content: the position of defect, the size of defect and defect
Shape, and the class information of the product according to determined by the shape of the position of the defect, the size of defect and defect.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides the 6th kind of first aspect
Possible embodiment, wherein the control module is also used to the product type information according to the product to be detected and presets
Product type information and light source luminance information mapping relations, determine the corresponding light source of the product to be detected brightness letter
The luminance information of the light source is sent to light source controller by breath, and the light source controller is used to be believed according to the light-source brightness
The brightness of breath adjustment first light source and second light source.
With reference to first aspect, the embodiment of the invention provides the 7th kind of possible embodiments of first aspect, wherein institute
Control module is stated to be also used to according to the product type information of the product to be detected and preset product type information and camera
The mapping relations of depth of exposure determine the depth of exposure of the corresponding camera of the product to be detected, by the exposure journey of the camera
Degree is sent to the first camera and the second camera, so that the first camera and the second camera are according to described to be checked
The depth of exposure for surveying the corresponding camera of product adjusts exposure.
With reference to first aspect, the embodiment of the invention provides the 8th kind of possible embodiments of first aspect, wherein institute
State system, further includes: alarming device, the alarming device are connected with the control module；
The control module is also used to count the quantity for having defective product within a preset period of time, super in the quantity
The alarming device is triggered when crossing preset value to alarm.
Second aspect, the embodiment of the invention also provides a kind of detection methods of surface defects of products, which is characterized in that packet
It includes:
Catching robot meets preset product type information from material platform to be detected crawl under the control of control module
Product to be detected is put to the lower section of the first camera of detection platform；
The image of the upper surface of the collected product is sent to control module by the first camera；
The upper surface of control module product according to the image detection of the upper surface of the product is with the presence or absence of scarce
It falls into, and exports the first testing result；
Inspecting manipuator grabs corresponding to the product to second camera after the first camera Image Acquisition finishes
Detection zone after, trigger the image that the second camera acquires the lower surface of the product；
The image of the lower surface of the collected product is sent to the control module by the second camera；
The upper surface of control module product according to the image detection of the lower surface of the product is with the presence or absence of scarce
It falls into, and exports the second testing result.
The detection system and method for a kind of surface defects of products provided in an embodiment of the present invention, are carried out by catching robot
Product to be detected is grabbed, and acquires by first camera the image of the upper surface of product to be detected, the image of the upper surface is sent out
It send to control module, judge whether the upper surface of the product deposits according to the image of the upper surface of the product by the control module
In defect；After the image of the upper surface of the product of first camera acquisition, product to be detected is placed second by inspecting manipuator
The shooting area of camera, and then second camera is acquired the image of the lower surface of the product to be detected, by control module according to
The image of the lower surface of the product to be detected judge the lower surface of the product to be detected with the presence or absence of defect, and exports detection
As a result, can complete in turn to the automatic carry out defect of product detection have precise and high efficiency good effect.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of structural schematic diagram of the detection system of surface defects of products provided by the embodiment of the present invention；
Fig. 2 shows a kind of flow diagrams of the detection method of surface defects of products provided by the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
Middle attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the range of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on the embodiment of the present invention, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall within the protection scope of the present invention.
Fig. 1 is a kind of structural schematic diagram of the detection system of surface defects of products provided by the embodiments of the present application.Referring to Fig.1
It is shown, the detection system of one of the present embodiment surface defects of products, comprising:
Catching robot 101, inspecting manipuator 103, control module 104 and defect detecting device 102, catching robot
101, inspecting manipuator 103 is connected with control module 104.
Above-mentioned defect detecting device 102 includes: first camera 1201 and second camera 1202；First camera 1201 is arranged
In the top of detection platform, the detection platform is for carrying product to be detected；The product to be detected can be the machinery such as blade and add
Work product or Ceramic manufacturing product.Second camera 1202 is set to the lower section of detection platform；The shooting of first camera 1201
The image of the upper surface of detected product, second camera 1202 are used to shoot the image of the lower surface of detected product.
Catching robot 101 is used under the control of control module 104 meet preset product from material platform to be detected crawl
The product to be detected of type information, and the product to be detected is put to the image acquisition areas of the first camera 1201 of detection platform
Behind domain, the image of the upper surface of triggering the first camera 1201 acquisition product.
The image of the upper surface of collected product is sent to control module 104 by first camera 1201；Control module 104
It whether there is defect according to the upper surface of the image detection product of the upper surface of the product, and export the first testing result.This is defeated
The mode of the first testing result, which can be, out will test result and carries out showing to user in front-end interface.
Above-mentioned inspecting manipuator 103, for after 1201 Image Acquisition of first camera finishes, grabbing the product to
The image acquisition region of two cameras 1202, triggering second camera 1202 acquire the image of the lower surface of product.
The image of the lower surface of collected product is sent to control module 104 by second camera 1202；Control module 104
It whether there is defect according to the upper surface of the image detection product of the lower surface of product, and export the second testing result.
In the possible embodiment of the application one, above-mentioned system, further includes: light source controller, first light source and the second light
Source, first light source are connected with light source controller with second light source；Light source controller is connected with control module.
In the present embodiment, above-mentioned first light source is set to the lower section of first camera, and second light source is set to second camera
Top；First light source and second light source are respectively used to the light filling when first camera and second camera carry out Image Acquisition.
In one embodiment of the application, above-mentioned control module be also used to according to the product type information of the product to be detected and
The mapping relations of the luminance information of preset product type information and light source determine the bright of the corresponding light source of the product to be detected
Information is spent, the luminance information of the light source is sent to light source controller, light source controller is used for according to the light-source brightness information
Adjust the brightness of first light source and second light source.
Control module 104 is also used to product type information and preset product type information according to the product to be detected
With the mapping relations of the depth of exposure of camera, the depth of exposure of the corresponding camera of product to be detected is determined, by the exposure of the camera
Light path degree is sent to the first camera and the second camera, so that the first camera and the second camera are according to
The depth of exposure of the corresponding camera of product to be detected adjusts exposure.
In the possible embodiment of the application one, third camera, catching robot are provided with above above-mentioned catching robot
It is also used to after moving at material platform to be detected position, triggering third camera is acquired comprising all productions on material platform to be detected
The image of product, and the image is sent to control module, control module determines the symbol for being included on material platform to be detected according to image
The location information is sent to catching robot by the location information for closing the product to be detected of preset product type information, crawl
Manipulator is used to grab product to be detected according to the location information.
In one possible embodiment, specifically, above-mentioned control module issues the first instruction to catching robot first, grab
It carries out being moved to material platform to be detected after taking manipulator to receive first control instruction, is placed with production to be detected on material platform to be detected
Product can be on the material platform to be detected and be placed with all types of products；Catching robot receive this first instruction after,
Material platform to be detected is moved to, triggering third camera is taken pictures, the image of third camera acquisition testing material platform, is wrapped in the image
Acquired image is sent to by the image containing the product consistent with the type information of above-mentioned product to be detected, third camera
Control module.User passes through the type information for the product for selecting setting to be detected on the display interface of front end, control
Module identifies that the product consistent with the type information of preset product to be detected, the product are product to be detected first, control
After molding block identifies the product to be detected, the location information of the product in the picture is further determined that, then turned by coordinate
It changes, determines that this meets the actual position information of the product to be detected of preset product type information, by the reality of the product to be detected
Border location information is sent to catching robot, and then catching robot grabs the production to be detected according to the physical location letter information
Product are placed in the image acquisition region of first camera.
In above-described embodiment, product to be detected is divided previously according to surface brightness, the type for the defect that may have etc.
Class, the different type information determine the exposure in the brightness and camera for carrying out light source when taking pictures in detection process to the product
Luminosity.
In the possible embodiment of the application one, above-mentioned control module is also used to, and is examined according to the first testing result and second
Survey result and determine the quality grade of product, according to the quality grade of product determine product belonging to material storage dish, and will be belonging to product
Material storage dish information be sent to inspecting manipuator, the inspecting manipuator is used for according to the material storage dish information, by the product
It places in the material storage dish.
In the embodiment of the present application, control module is previously stored with product hierarchy and stores the corresponding relationship of charging tray information,
Determine that the product hierarchy of product later can be according to pair of the product hierarchy and above-mentioned product hierarchy and storage charging tray information
It should be related to, determine charging tray information belonging to the product, and then the product can be piled up to corresponding storage charging tray, be realized
The automatic classification of product.
In one embodiment of the application, above-mentioned control module, specifically for being carried out in the following manner according to the product
The upper surface of product described in the image detection of upper surface whether there is defect:
Control module receives the image of the upper surface of the product, and calling pre-establishes and trained neural network mould
Type, according to the image of the upper surface of test parameter set by user, defect threshold value and the product, by neural network model into
Defects detection result is calculated in row；Wherein, the test parameter includes: batch size numerical value and image cutting numerical value.
In the present embodiment, defect whether there is according to the upper surface of product described in the image detection of the upper surface of the product
Process it is same as described above.
Above-mentioned first testing result and second testing result include the following information content: the position of defect, defect
The shape of size and defect, and the product according to determined by the shape of the position of the defect, the size of defect and defect
Class information.
In one embodiment of the application, above system further include: alarming device, the alarming device and the control module phase
Connection；
The control module is also used to count the quantity for having defective product within a preset period of time, super in the quantity
The alarming device is triggered when crossing preset value to alarm.
The type information of the product detected can be stored into system in the present embodiment, be existed in staff in advance
When needing to detect certain type of product, product type selection is carried out first on interface, in the production for selecting pending detection
After the type information of product, the type information for the product that control module is selected according to user generates the first above-mentioned control instruction.
In the possible embodiment of the application one, above-mentioned control module can be including industrial personal computer and carry out image procossing
Processor.The processor is specifically used for being detected according to the image of upper surface and the image of product lower surface of above-mentioned product
The upper and lower surfaces of the product whether there is defect, which includes: crackle, notch, burr etc..
Fig. 2 is a kind of flow diagram of method for detecting surface defects of products provided by the embodiments of the present application.Referring to Fig. 2 institute
Show, this method includes the following steps S201-S206:
Step S201, catching robot meets preset product class from material platform to be detected crawl under the control of control module
The product to be detected of type information is put to the lower section of the first camera of detection platform.
Step S202, the image of the upper surface of the collected product is sent to control module by the described first camera.
Step S203, the upper surface of described control module product according to the image detection of the upper surface of the product is
No existing defects, and export the first testing result.
Step S204, inspecting manipuator grabs the product to second after the first camera Image Acquisition finishes
After detection zone corresponding to camera, the image that the second camera acquires the lower surface of the product is triggered.
Step S205, the image of the lower surface of the collected product is sent to the control mould by the described second camera
Block.
Step S206, the upper surface of described control module product according to the image detection of the lower surface of the product is
No existing defects, and export the second testing result.
In one optional embodiment of the application, the above method, further includes:
Control module is also according to the product type information of the product to be detected and preset product type information and light source
Luminance information mapping relations, the luminance information of the corresponding light source of the product to be detected is determined, by the brightness of the light source
Information is sent to light source controller, and light source controller adjusts the bright of first light source and second light source according to the light-source brightness information
Degree.So that first light source and second light source according to the luminance information to first camera and second camera the light filling in Image Acquisition.
In one optional embodiment of the application, the above method, further includes:
Control module 104 is according to the product type information of the product to be detected and preset product type information and camera
Depth of exposure mapping relations, the depth of exposure of the corresponding camera of product to be detected is determined, by the depth of exposure of the camera
It is sent to the first camera and the second camera, the first camera and the second camera are according to the product to be detected
The depth of exposure of corresponding camera adjusts exposure.
In one optional embodiment of the application, the above method, further includes:
After moving at material platform to be detected position, triggering third camera is acquired comprising material to be detected catching robot
The image of all products on platform, and the image is sent to control module；
Control module determines that included on material platform to be detected meets the to be checked of preset product type information according to image
The location information is sent to catching robot by the location information for surveying product, and catching robot is grabbed according to the position letter information
Product to be detected to detection platform is detected.
In one optional embodiment of the application, the above method, further includes:
Above-mentioned control module determines the quality grade of product according to the first testing result and the second testing result, according to production
The quality grade of product determines material storage dish belonging to product, and material storage dish information belonging to product is sent to inspecting manipuator, institute
Inspecting manipuator is stated for according to the material storage dish information, the product to be placed in the material storage dish.
In one optional embodiment of the application, the above method, further includes:
Control module receives the image of the upper surface of the product, and calling pre-establishes and trained neural network mould
Type, according to the image of the upper surface of test parameter set by user, defect threshold value and the product, by neural network model into
Defects detection result is calculated in row；Wherein, the test parameter includes: batch size numerical value and image cutting numerical value.
In one optional embodiment of the application, the above method, further includes:
The control module is also used to count the quantity for having defective product within a preset period of time, super in the quantity
The alarming device is triggered when crossing preset value to alarm.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" is to be based on the orientation or positional relationship shown in the drawings, or be somebody's turn to do
Invention product using when the orientation or positional relationship usually put, be merely for convenience of description of the present invention and simplification of the description, without
It is that the device of indication or suggestion meaning or element must have a particular orientation, be constructed and operated in a specific orientation, therefore not
It can be interpreted as limitation of the present invention.In addition, term " first ", " second ", " third " etc. are only used for distinguishing description, and cannot manage
Solution is indication or suggestion relative importance.
In the description of the present invention, it is also necessary to which explanation is unless specifically defined or limited otherwise, term " setting ",
" installation ", " connected ", " connection " shall be understood in a broad sense, for example, it may be fixedly connected, may be a detachable connection or one
Connect to body；It can be mechanical connection, be also possible to be electrically connected；It can be directly connected, it can also be indirect by intermediary
It is connected, can be the connection inside two elements.For the ordinary skill in the art, on being understood with concrete condition
State the concrete meaning of term in the present invention.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of detection system of surface defects of products characterized by comprising
Catching robot, inspecting manipuator, control module and defect detecting device, the catching robot, inspecting manipuator are equal
It is connected with the control module；
The defect detecting device includes: first camera and second camera；The first camera is set to the top of detection platform,
The second camera is set to the lower section of detection platform；The image of the first camera upper surface of shooting detected product,
The second camera is used to shoot the image of the lower surface of the detected product；
The catching robot is used under the control of the control module meet preset product class from material platform to be detected crawl
The product to be detected of type information, and the product to be detected is put to the lower section of the first camera of detection platform, trigger institute
State the image that the first camera acquires the upper surface of the product；
The image of the upper surface of the collected product is sent to the control module by the first camera；The control mould
The upper surface of product described in image detection of the root tuber according to the upper surface of the product whether there is defect, and export the first detection knot
Fruit；
The inspecting manipuator, for grabbing the product to second camera after the first camera Image Acquisition finishes
After the detection zone at place, the image that the second camera acquires the lower surface of the product is triggered；
The image of the lower surface of the collected product is sent to the control module by the second camera；The control mould
The upper surface of product described in image detection of the root tuber according to the lower surface of the product whether there is defect, and export the second detection knot
Fruit.
2. system according to claim 1, which is characterized in that further include: light source controller, first light source and the second light
Source, the first light source are connected with the light source controller with the second light source；The light source controller and the control
Molding block is connected；
The first light source is set to the lower section of the first camera, and the second light source is set to the upper of the second camera
Side；The first light source and the second light source are respectively used to carry out Image Acquisition in the first camera and the second camera
When light filling.
3. system according to claim 2, which is characterized in that be provided with third camera above the catching robot, institute
It states catching robot to be also used to after moving at material platform to be detected position, triggers the third camera and be acquired comprising to be checked
The image of material platform is surveyed, and described image is sent to control module, the control module determines described to be checked according to described image
The location information for surveying the product to be detected for meeting preset product type information for being included on material platform, the location information is sent out
It send to the catching robot, the catching robot is used to grab the product to be detected according to the position letter information.
4. system according to claim 1, which is characterized in that the control module is also used to, according to first detection
As a result the quality grade that the product is determined with second testing result, determines the production according to the quality grade of the product
Material storage dish belonging to product, and material storage dish information belonging to the product is sent to inspecting manipuator, the inspecting manipuator is used
According to the material storage dish information, the product is placed in the material storage dish.
5. the system according to 1, which is characterized in that the control module, specifically for being carried out in the following manner according to institute
The upper surface of product described in the image detection of the upper surface of product is stated with the presence or absence of defect:
The control module receives the image of the upper surface of the product, and calling pre-establishes and trained neural network mould
Type is calculated according to test parameter set by user, defect threshold value and described image by the neural network model
Defects detection result；Wherein, the test parameter includes: batch size numerical value and image cutting numerical value.
6. system according to claim 1, which is characterized in that first testing result and the second testing result packet
Containing the following information content: the position of defect, the size of defect and defect shape, and the position according to the defect, defect
Size and defect shape determined by product class information.
7. system according to claim 2, which is characterized in that the control module is also used to according to the product to be detected
Product type information and preset product type information and light source luminance information mapping relations, determine the production to be detected
The luminance information of the light source is sent to light source controller by the luminance information of the corresponding light source of product, and the light source controller is used
In the brightness for adjusting first light source and second light source according to the light-source brightness information.
8. system according to claim 1, which is characterized in that the control module is also used to according to the product to be detected
Product type information and preset product type information and camera depth of exposure mapping relations, determine the production to be detected
The depth of exposure of the camera is sent to the first camera and the second camera by the depth of exposure of the corresponding camera of product,
So that the first camera and the second camera adjust exposure according to the depth of exposure of the corresponding camera of the product to be detected.
9. system according to claim 1, which is characterized in that further include: alarming device, the alarming device and the control
Molding block is connected；
The control module is also used to count the quantity for having defective product within a preset period of time, is more than pre- in the quantity
If triggering the alarming device when value to alarm.
10. a kind of detection method of surface defects of products characterized by comprising
Catching robot meets the to be checked of preset product type information from material platform to be detected crawl under the control of control module
Product is surveyed to put to the lower section of the first camera of detection platform；
The image of the upper surface of the collected product is sent to control module by the first camera；
The upper surface of control module product according to the image detection of the upper surface of the product whether there is defect, and
Export the first testing result；
Inspecting manipuator grabs inspection corresponding to the product to second camera after the first camera Image Acquisition finishes
After surveying region, the image that the second camera acquires the lower surface of the product is triggered；
The image of the lower surface of the collected product is sent to the control module by the second camera；
The upper surface of control module product according to the image detection of the lower surface of the product whether there is defect, and
Export the second testing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811253443.6A CN109406533A (en) | 2018-10-25 | 2018-10-25 | A kind of detection system and method for surface defects of products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811253443.6A CN109406533A (en) | 2018-10-25 | 2018-10-25 | A kind of detection system and method for surface defects of products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109406533A true CN109406533A (en) | 2019-03-01 |
Family
ID=65470129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811253443.6A Pending CN109406533A (en) | 2018-10-25 | 2018-10-25 | A kind of detection system and method for surface defects of products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109406533A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110102511A (en) * | 2019-05-23 | 2019-08-09 | 北京阿丘机器人科技有限公司 | A kind of vision detection system and method for product appearance |
| CN110142230A (en) * | 2019-05-23 | 2019-08-20 | 北京阿丘机器人科技有限公司 | A kind of method and device detecting open defect |
| CN110186938A (en) * | 2019-06-28 | 2019-08-30 | 笪萨科技(上海)有限公司 | Two-sided defect analysis equipment and defects detection and analysis system |
| CN110501347A (en) * | 2019-07-03 | 2019-11-26 | 深圳市一纳科技有限公司 | A kind of rapid automatized Systems for optical inspection and method |
| CN110673319A (en) * | 2019-09-29 | 2020-01-10 | 江苏才道精密仪器有限公司 | Microscope laser repair system and device capable of automatically adjusting light source |
| CN111311542A (en) * | 2020-01-15 | 2020-06-19 | 歌尔股份有限公司 | Product quality detection method and device |
| CN111598152A (en) * | 2020-05-12 | 2020-08-28 | 北京阿丘机器人科技有限公司 | Visual system reproduction method, apparatus and computer-readable storage medium |
| CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
| CN112730421A (en) * | 2019-10-14 | 2021-04-30 | 富泰华工业（深圳）有限公司 | Appearance flaw detection device |
| CN112730419A (en) * | 2019-10-14 | 2021-04-30 | 富泰华工业（深圳）有限公司 | Appearance flaw detection device |
| CN112730420A (en) * | 2019-10-14 | 2021-04-30 | 富泰华工业（深圳）有限公司 | Appearance flaw detection station |
| CN113177925A (en) * | 2021-05-11 | 2021-07-27 | 昆明理工大学 | Method for nondestructive detection of fruit surface defects |
| CN113189009A (en) * | 2021-05-17 | 2021-07-30 | 石家庄格力电器小家电有限公司 | System for detecting surface treatment quality of smoke collecting hood |
| CN113409308A (en) * | 2021-07-16 | 2021-09-17 | 李华洲 | Circuit board fault defect detection method, device, detection equipment and system |
| CN113567443A (en) * | 2021-06-22 | 2021-10-29 | 浙江大豪科技有限公司 | Control method and device of fabric flaw detection system |
| CN113744247A (en) * | 2021-09-03 | 2021-12-03 | 西安建筑科技大学 | PCB welding spot defect identification method and system |
| CN115744254A (en) * | 2022-11-24 | 2023-03-07 | 臻越自动化技术（上海）有限公司 | Door plant automated inspection conveyor |
| CN116609345A (en) * | 2023-07-19 | 2023-08-18 | 北京阿丘机器人科技有限公司 | Battery cover plate defect detection method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07311160A (en) * | 1994-05-19 | 1995-11-28 | Nitto Denko Corp | Method and device for preforming visual inspection |
| CN1501434A (en) * | 2002-11-14 | 2004-06-02 | 旺宏电子股份有限公司 | Quick warning system and method for continuous abnormal faults |
| DE102004015110A1 (en) * | 2004-03-27 | 2005-10-13 | Texmag Gmbh Vertriebsgesellschaft | Detection apparatus for detecting defects in joints of sheet pieces, has source(s) of electromagnetic non-unidirectional radiations, and one or more sensors that make two-dimensional detection of reflected or refracted radiation |
| CN102033068A (en) * | 2009-09-24 | 2011-04-27 | 苏州维世迅机器视觉技术有限公司 | Product on-line detector |
| CN202694534U (en) * | 2012-08-02 | 2013-01-23 | 东莞利扬微电子有限公司 | Yield warning device |
| CN203526088U (en) * | 2013-11-07 | 2014-04-09 | 珠海格力电器股份有限公司 | Detection device for electronic components |
| CN104516305A (en) * | 2013-10-08 | 2015-04-15 | 繁昌县倍思创业服务有限公司 | Method for detecting weights of products and treating sub-quality products |
| CN104624523A (en) * | 2013-11-07 | 2015-05-20 | 珠海格力电器股份有限公司 | Electronic component detection device and electronic component automatic detection method |
| CN105606625A (en) * | 2016-02-03 | 2016-05-25 | 宁波韵升智能技术有限公司 | Appearance defect detection equipment for flake strip-shaped products |
| CN206155906U (en) * | 2016-10-10 | 2017-05-10 | 广州敏达包装设备有限公司 | Non -contact beats equipment of examining in vacuum |
| CN107271447A (en) * | 2017-07-27 | 2017-10-20 | 江南大学 | A kind of PLC outward appearances and LED status detection means based on machine vision |
| CN108038853A (en) * | 2017-12-18 | 2018-05-15 | 浙江工业大学 | A kind of ceramic tile surface defect identification method based on convolutional neural networks and Active Learning |
| CN108188043A (en) * | 2017-12-25 | 2018-06-22 | 中国科学院自动化研究所 | The appearance detecting device and appearance detecting method of lithium battery electric core |
| CN108631727A (en) * | 2018-03-26 | 2018-10-09 | 河北工业大学 | A kind of solar panel defect identification method based on convolutional neural networks |
-
2018
- 2018-10-25 CN CN201811253443.6A patent/CN109406533A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07311160A (en) * | 1994-05-19 | 1995-11-28 | Nitto Denko Corp | Method and device for preforming visual inspection |
| CN1501434A (en) * | 2002-11-14 | 2004-06-02 | 旺宏电子股份有限公司 | Quick warning system and method for continuous abnormal faults |
| DE102004015110A1 (en) * | 2004-03-27 | 2005-10-13 | Texmag Gmbh Vertriebsgesellschaft | Detection apparatus for detecting defects in joints of sheet pieces, has source(s) of electromagnetic non-unidirectional radiations, and one or more sensors that make two-dimensional detection of reflected or refracted radiation |
| CN102033068A (en) * | 2009-09-24 | 2011-04-27 | 苏州维世迅机器视觉技术有限公司 | Product on-line detector |
| CN202694534U (en) * | 2012-08-02 | 2013-01-23 | 东莞利扬微电子有限公司 | Yield warning device |
| CN104516305A (en) * | 2013-10-08 | 2015-04-15 | 繁昌县倍思创业服务有限公司 | Method for detecting weights of products and treating sub-quality products |
| CN203526088U (en) * | 2013-11-07 | 2014-04-09 | 珠海格力电器股份有限公司 | Detection device for electronic components |
| CN104624523A (en) * | 2013-11-07 | 2015-05-20 | 珠海格力电器股份有限公司 | Electronic component detection device and electronic component automatic detection method |
| CN105606625A (en) * | 2016-02-03 | 2016-05-25 | 宁波韵升智能技术有限公司 | Appearance defect detection equipment for flake strip-shaped products |
| CN206155906U (en) * | 2016-10-10 | 2017-05-10 | 广州敏达包装设备有限公司 | Non -contact beats equipment of examining in vacuum |
| CN107271447A (en) * | 2017-07-27 | 2017-10-20 | 江南大学 | A kind of PLC outward appearances and LED status detection means based on machine vision |
| CN108038853A (en) * | 2017-12-18 | 2018-05-15 | 浙江工业大学 | A kind of ceramic tile surface defect identification method based on convolutional neural networks and Active Learning |
| CN108188043A (en) * | 2017-12-25 | 2018-06-22 | 中国科学院自动化研究所 | The appearance detecting device and appearance detecting method of lithium battery electric core |
| CN108631727A (en) * | 2018-03-26 | 2018-10-09 | 河北工业大学 | A kind of solar panel defect identification method based on convolutional neural networks |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110102511A (en) * | 2019-05-23 | 2019-08-09 | 北京阿丘机器人科技有限公司 | A kind of vision detection system and method for product appearance |
| CN110142230A (en) * | 2019-05-23 | 2019-08-20 | 北京阿丘机器人科技有限公司 | A kind of method and device detecting open defect |
| CN110186938A (en) * | 2019-06-28 | 2019-08-30 | 笪萨科技(上海)有限公司 | Two-sided defect analysis equipment and defects detection and analysis system |
| CN110501347A (en) * | 2019-07-03 | 2019-11-26 | 深圳市一纳科技有限公司 | A kind of rapid automatized Systems for optical inspection and method |
| CN110673319A (en) * | 2019-09-29 | 2020-01-10 | 江苏才道精密仪器有限公司 | Microscope laser repair system and device capable of automatically adjusting light source |
| US11645742B2 (en) | 2019-10-14 | 2023-05-09 | Fu Tai Hua Industry (Shenzhen) Co., Ltd. | Electronic device for optically detecting appearance of product for defects |
| CN112730420B (en) * | 2019-10-14 | 2024-02-20 | 富泰华工业（深圳）有限公司 | Appearance flaw detection workstation |
| CN112730421A (en) * | 2019-10-14 | 2021-04-30 | 富泰华工业（深圳）有限公司 | Appearance flaw detection device |
| CN112730419A (en) * | 2019-10-14 | 2021-04-30 | 富泰华工业（深圳）有限公司 | Appearance flaw detection device |
| CN112730420A (en) * | 2019-10-14 | 2021-04-30 | 富泰华工业（深圳）有限公司 | Appearance flaw detection station |
| CN112730419B (en) * | 2019-10-14 | 2024-01-09 | 富泰华工业（深圳）有限公司 | Appearance flaw detection device |
| CN112730421B (en) * | 2019-10-14 | 2024-01-09 | 富泰华工业（深圳）有限公司 | Appearance flaw detection device |
| CN111311542A (en) * | 2020-01-15 | 2020-06-19 | 歌尔股份有限公司 | Product quality detection method and device |
| CN111311542B (en) * | 2020-01-15 | 2023-09-19 | 歌尔股份有限公司 | Product quality detection method and device |
| CN111598152A (en) * | 2020-05-12 | 2020-08-28 | 北京阿丘机器人科技有限公司 | Visual system reproduction method, apparatus and computer-readable storage medium |
| CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
| CN113177925B (en) * | 2021-05-11 | 2022-11-11 | 昆明理工大学 | Method for nondestructive detection of fruit surface defects |
| CN113177925A (en) * | 2021-05-11 | 2021-07-27 | 昆明理工大学 | Method for nondestructive detection of fruit surface defects |
| CN113189009A (en) * | 2021-05-17 | 2021-07-30 | 石家庄格力电器小家电有限公司 | System for detecting surface treatment quality of smoke collecting hood |
| CN113567443A (en) * | 2021-06-22 | 2021-10-29 | 浙江大豪科技有限公司 | Control method and device of fabric flaw detection system |
| CN113409308A (en) * | 2021-07-16 | 2021-09-17 | 李华洲 | Circuit board fault defect detection method, device, detection equipment and system |
| CN113744247A (en) * | 2021-09-03 | 2021-12-03 | 西安建筑科技大学 | PCB welding spot defect identification method and system |
| CN115744254A (en) * | 2022-11-24 | 2023-03-07 | 臻越自动化技术（上海）有限公司 | Door plant automated inspection conveyor |
| CN115744254B (en) * | 2022-11-24 | 2023-12-26 | 臻越自动化技术（上海）有限公司 | Automatic door plate detection and conveying device |
| CN116609345A (en) * | 2023-07-19 | 2023-08-18 | 北京阿丘机器人科技有限公司 | Battery cover plate defect detection method, device, equipment and storage medium |
| CN116609345B (en) * | 2023-07-19 | 2023-10-17 | 北京阿丘机器人科技有限公司 | Battery cover plate defect detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109406533A (en) | A kind of detection system and method for surface defects of products | |
| CN110383038B (en) | System and method for automated analysis of air samples | |
| JP6705777B2 (en) | Machine learning device, inspection device and machine learning method | |
| CN100520377C (en) | Multi vision hollow bottle detection robot | |
| JP5707399B2 (en) | Microorganism detection method, microorganism detection apparatus, and program | |
| CN204479490U (en) | A kind of laser marking On-line Product testing and analysis system | |
| CN108846841A (en) | Display screen quality determining method, device, electronic equipment and storage medium | |
| CN108982514A (en) | A kind of bionical vision detection system of casting surface defect | |
| CN102529019B (en) | Method for mould detection and protection as well as part detection and picking | |
| AU689547B2 (en) | Apparatus and method for inspecting hot glass containers | |
| CN102967586B (en) | Device for online automatically classifying pearl color and gloss based on monocular multi-view machine vision | |
| WO2005124316A2 (en) | Method and apparatus for configuring and testing a machine vision detector | |
| CN111862083A (en) | Comprehensive monitoring system and method for steel wire rope state based on vision-electromagnetic detection | |
| CN103307989A (en) | Device and method for measuring internal and external diameters of transparent glass bottleneck based on machine vision | |
| CN108993917A (en) | A kind of quality detecting system of microsprings, method and device | |
| JP2022507678A (en) | Optimization of setup stage in automated visual inspection process | |
| CN106706656A (en) | Machine vision-based zipper detection device and method | |
| CN105891228A (en) | Optical fiber appearance defect detecting and outer diameter measuring device based on machine vision | |
| CN108038510A (en) | A kind of detection method based on doubtful flame region feature | |
| CN101696943A (en) | On-line detection method of machine vision system to medical surgical knife flaws | |
| Chao et al. | Design of a dual-camera system for poultry carcasses inspection | |
| CN104766310B (en) | light source detection system and detection method | |
| CN101696877A (en) | On-line detection method of machine vision system to spring verticality | |
| CN116441190A (en) | Longan detection system, method, equipment and storage medium | |
| CN111524136A (en) | Boxing abnormality detection system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |
|
| RJ01 | Rejection of invention patent application after publication |