CN109142393A - A kind of defect classification method, apparatus and system - Google Patents
A kind of defect classification method, apparatus and system Download PDFInfo
- Publication number
- CN109142393A CN109142393A CN201811018191.9A CN201811018191A CN109142393A CN 109142393 A CN109142393 A CN 109142393A CN 201811018191 A CN201811018191 A CN 201811018191A CN 109142393 A CN109142393 A CN 109142393A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- presetting
- original image
- area
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/952—Inspecting the exterior surface of cylindrical bodies or wires
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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention proposes a kind of defect classification method, apparatus and system, is related to image procossing, analysis and field of machine vision.This method, apparatus and system are by obtaining original image, original image is pre-processed again to obtain the first image, then the round degree of characteristics and area features that the defect that the first image includes is extracted using presetting feature extraction algorithm, finally classify to the defect of original image based on the round degree of characteristics and area features；Due to being pre-processed to original image, the treating capacity of data is greatly reduced, to optimize the arithmetic speed of system, improves the efficiency finally identified；Whole process carries out automatically simultaneously, without artificially being identified, substantially increases the accuracy and precision of identification.
Description
Technical field
The present invention relates to image procossing, analysis and field of machine vision, in particular to a kind of defect classification method,
Apparatus and system.
Background technique
In the production and processing of automobile heterotype element such as engine cam, camshaft is almost required manually both at home and abroad at present
Naked eyes go detection defect, such as metal surface scratch, crackle, arrisdefect, chipping, and engine cam defects detection is for entire vapour
The quality of vehicle product plays the role of critically important.There is large effect for the production cost and production time of enterprise.
As in Camshaft Production detection process in current production, camshaft is examined by test mode is manually visualized
The defect of camshaft is surveyed, the time that such mode detects a product is too long, easily slips, in addition camshaft itself also compares
Weight manually also can be tired under prolonged artificial detection situation, causes the product of mistake to be flowed into next process, sternly
Ghost image rings the safety and quality of vehicle, entire production efficiency can be made low and the increase of error rate.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of defect classification method, apparatus and system, to solve above-mentioned ask
Topic.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of defect classification method, the defect classification method includes:
Obtain original image；
The original image is pre-processed to obtain the first image；
The round degree of characteristics and area of the defect that the first image includes are extracted using presetting feature extraction algorithm
Feature；
Classified based on the round degree of characteristics and the area features to the defect of the original image.
Second aspect, the embodiment of the invention also provides a kind of device for classifying defects, the device for classifying defects includes:
Image acquisition unit, for obtaining original image；
Pretreatment unit, for being pre-processed to the original image to obtain the first image；
Feature extraction unit, for extracting the defect that the first image includes using presetting feature extraction algorithm
The round degree of characteristics and area features；
Defect analysis unit, for the defect based on the round degree of characteristics and the area features to the original image
Classify.
The third aspect, the present invention also provides a kind of defect categorizing system, the defect categorizing system include: memory,
Processor, controller, manipulator, camera, position sensor and device for classifying defects, the memory, the controller point
It is not electrically connected with the processor, the controller is electrically connected with the manipulator, the camera and the position sensor；
The position sensor is used to sense the position coordinates for acquiring the camshaft after camshaft enters predeterminable area,
And the position coordinates are transmitted to the controller；
The controller is run for controlling the manipulator to the position coordinates；
The prompt information is transmitted to institute for generating prompt information after reaching the position coordinates by the manipulator
State controller；
The controller is for responding the prompt information and controlling the camera and shot the camshaft to obtain
Take the original image of presetting quantity；
The controller is also used to the original image being transmitted to the processor；
The processor is used to execute being installed on the memory and is deposited in the form of one or more software function modules
The device for classifying defects of storage is to generate classification results；
Wherein, the device for classifying defects includes:
Image acquisition unit, for obtaining original image；
Pretreatment unit, for being pre-processed to the original image to obtain the first image；
Pretreatment unit, for extracting the circle for the defect that the first image includes using presetting feature extraction algorithm
Spend feature and area features；
Defect analysis unit, for the defect based on the round degree of characteristics and the area features to the original image
Classify；
The controller is used to be put into corresponding camshaft according to the classification results control manipulator corresponding
Discharge port.
Defect classification method provided in an embodiment of the present invention, apparatus and system, by obtaining original image, then to original graph
As being pre-processed to obtain the first image, the defect that the first image includes then is extracted using presetting feature extraction algorithm
The round degree of characteristics and area features, finally classified based on the round degree of characteristics and area features to the defect of original image；
Due to being pre-processed to original image, the treating capacity of data is greatly reduced, to optimize the arithmetic speed of system, is mentioned
The high efficiency of final identification；Whole process carries out automatically simultaneously, without artificially being identified, substantially increases the accurate of identification
Property and precision.
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 the circuit structure block diagram that can be applied to the defect categorizing system of the embodiment of the present invention.
Fig. 2 shows the flow charts of defect classification method provided in an embodiment of the present invention.
Fig. 3 shows the specific flow chart of step S202 in Fig. 2.
Fig. 4 shows the specific flow chart of step S203 in Fig. 2.
Fig. 5 shows the functional block diagram of device for classifying defects provided in an embodiment of the present invention.
Icon: 100- defect categorizing system；110- processor；120- memory；130- controller；140- manipulator；
150- camera；160- position sensor；200- device for classifying defects；210- image acquisition unit；220- pretreatment unit；230-
Feature extraction unit；240- defect analysis unit.
Specific embodiment
Below in conjunction with 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 only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that the relational terms of term " first " and " second " or the like be used merely to an entity or
Operation is distinguished with another entity or operation, and without necessarily requiring or implying between these entities or operation, there are any
This actual relationship or sequence.Moreover, the terms "include", "comprise" or its any other variant be intended to it is non-exclusive
Property include so that include a series of elements process, method, article or equipment not only include those elements, but also
Further include other elements that are not explicitly listed, or further include for this process, method, article or equipment it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described
There is also other identical elements in the process, method, article or equipment of element.
Please refer to Fig. 1, for can be applied to the embodiment of the present invention defect categorizing system 100 circuit structure block diagram.It is described
Defect categorizing system 100 includes device for classifying defects 200, memory 120, processor 110, controller 130, manipulator 140, phase
Machine 150 and position sensor 160.Wherein, memory 120, controller 130 are electrically connected with processor 110 respectively, controller
130 are electrically connected with manipulator 140, camera 150 and position sensor 160.
Position sensor 160, which is used to sense after camshaft enters predeterminable area, acquires the position coordinates of camshaft, and incites somebody to action
Position coordinates are transmitted to controller 130.
Controller 130 is for controlling the operation of manipulator 140 to position coordinates.
Manipulator 140 will be prompted to information and be transmitted to controller 130 for generating prompt information after reaching position coordinates.
It is to be appreciated that being able to achieve camshaft by setting position sensor 160, controller 130 and manipulator 140
It is quick positioning and crawl, saved human cost, whole process is more efficient.
Controller 130 shoots to obtain preset fixed number camshaft for controlling camera 150 in response to prompt information
The original image of amount.
It should be noted that after camshaft enters predeterminable area, camera 150 is to convex in a kind of preferred embodiment
Wheel shaft is shot 19 times, so as to quickly obtain the ideal image in this anisotropic face of camshaft.
Controller 130 is also used to for original image to be transmitted to processor 110.
The memory 120, processor 110 and each element of controller 130 directly or indirectly electrically connect between each other
It connects, to realize the transmission or interaction of data.For example, these elements can pass through one or more communication bus or signal between each other
Line, which is realized, to be electrically connected.The device for classifying defects 200 includes at least one can be in the form of software or firmware (Firmware)
Be stored in the memory 120 or be solidificated in the defect categorizing system 100 operating system (Operating System,
OS the software function module in).
Wherein, the memory 120 may be, but not limited to, random access memory (Random Access
Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable
Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only
Memory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only
Memory, EEPROM) etc..Wherein, memory 120 is for storing program or data.
The processor 110 is for executing the executable module stored in the memory 120, such as defect classification
Software function module included by device 200 and computer program etc., to generate classification results.
Controller 130 is used to that corresponding camshaft to be put into corresponding discharge port according to classification results control manipulator 140.
It should be understood that structure shown in FIG. 1 is only the structural schematic diagram of defect categorizing system 100, the defect point
Class system 100 may also include than shown in Fig. 1 more perhaps less component or with the configuration different from shown in Fig. 1.Figure
Each component shown in 1 can be realized using hardware, software, or its combination.
First embodiment
The embodiment of the invention provides a kind of defect classification methods, for extracting the defects of original image, and to defect
Classify.Referring to Fig. 2, being the flow chart of defect classification method provided in an embodiment of the present invention.The defect classification method packet
It includes:
Step S201: original image is obtained.
It is to be appreciated that the original image be camshaft reach predeterminable area after, camera 150 carry out shooting or figure
Picture.
Step S202: original image is pre-processed to obtain the first image.
Referring to Fig. 3, being the specific flow chart of step S202.Step S202 includes:
Sub-step S2021: gray scale scaling processing is carried out to obtain to original image using presetting gray scale scaling formula
Second image.
In a kind of preferred embodiment, which scales formula are as follows:
Wherein, g2For the second image, g is original image, and GMax is the maximum gradation value of original image, and GMin is original graph
The minimum gradation value of picture.
It is to be appreciated that gray scale scaling processing is carried out to original image by scaling formula using presetting gray scale, from
And the effective coverage in original image is obtained as the second image, the resolution ratio of original image is reduced, to improve subsequent operation
Speed.
Sub-step S2022: closed operation processing is carried out to obtain third image to the second image.
It is to be appreciated that by the second image carry out closed operation processing, can make obtain third image compared to
Second image has higher contrast, is equally convenient for subsequent extracted feature.
In a kind of preferred embodiment, the mask of the closed operation is 5.
Sub-step S2023: threshold process is carried out to obtain the first image to third image using presetting threshold value formula.
In a kind of preferred embodiment, the presetting threshold value formula are as follows:
Wherein, g1For the first image, g3For third image, MinGray is presetting minimal gray threshold value, and ManGray is
Presetting maximum gray threshold.
It is to be appreciated that by for the second image setting gray threshold, so that gray scale is greater than presetting in third image
Minimal gray threshold value is simultaneously less than presetting maximum gray threshold, remains unchanged；And the gray scale outside range is made to become 0, that is, become
Black obtains third image, reduces other complex characteristics and make to feature extraction to remove more complicated feature in the second image
At error and interference.
Step S203: using presetting feature extraction algorithm extract the defect that the first image includes the round degree of characteristics and
Area features.
Referring to Fig. 4, being the specific flow chart of step S203.Step S203 includes:
Sub-step S2031: the contour area for the defect that the first image includes is extracted based on presetting Blob parser.
Sub-step S2032: the round degree of characteristics is extracted based on contour area and the first presetting formula.
In a kind of preferred embodiment, the first presetting formula are as follows:
C=min (1, C ')
Wherein, C is circularity,F is the area of the contour area, and max is the contour area packet
All profile points contained are to the maximum value in profile center.
Sub-step S2033: area features are extracted based on contour area and the second presetting formula.
In a kind of preferred embodiment, the second presetting formula are as follows:
Wherein, A is area, and g (r, c) is third image, and (r, c) is the coordinate of any one pixel in third image.
Step S204: classified based on the round degree of characteristics and area features to the defect of original image.
It should be noted that the round degree of characteristics and area features are the feature of the fault location of camshaft, by by defect
The round degree of characteristics, the area features at place are compared with the design parameter of standard cams axis corresponding position, and just can obtain is at this
No to have feature, if there is feature, then what specific characteristic type is.
For example, when the round degree of characteristics is greater than or equal to presetting area threshold, then it is assumed that the defect belongs to " sand holes ", sand
Eye is a kind of more serious defect in camshaft, if the camshaft for leaving to have sand holes flows into next production link, then very
May cause engine be very easy to damage, it is therefore desirable to selected using manipulator 140, then by by staff into
Row is rejected.
In addition, it should be noted that, extracting the round degree of characteristics and area features simultaneously is advantageous in that, due to assembly line
Light problem, the light that each face of camshaft is subject to are inconsistent, it is also possible to due to the dust interference problem that camshaft shows, meeting
There are shade positions for the original image for taking camera 150, but are not defect, but processor 110 also can at this time
The round degree of characteristics and area features are extracted, but passes through while judging whether the round degree of characteristics and area features meet condition, from
And the influence of the above problem is discharged.
Second embodiment
Referring to Fig. 5, Fig. 5 is a kind of functional block diagram for device for classifying defects 200 that present pre-ferred embodiments provide.
It should be noted that the technical effect of device for classifying defects 200 provided by the present embodiment, basic principle and generation and above-mentioned
Embodiment is identical, and to briefly describe, the present embodiment part does not refer to place, can refer to corresponding contents in the above embodiments.It should
Device for classifying defects 200 includes image acquisition unit 210, pretreatment unit 220, feature extraction unit 230 and defect analysis
Unit 240.
Wherein, image acquisition unit 210 is for obtaining original image.
It is to be appreciated that the image acquisition unit 210 can be used for executing step S201 in a kind of preferred embodiment.
Pretreatment unit 220 is for pre-processing original image to obtain the first image.
Specifically, pretreatment unit 220 is used to carry out gray scale contracting to original image using presetting gray scale scaling formula
Processing is put to obtain the second image, is also used to carry out the second image closed operation processing to obtain third image, is also used to utilize
Presetting threshold value formula carries out threshold process to third image to obtain the first image.
It is to be appreciated that the pretreatment unit 220 can be used for executing step S202, son in a kind of preferred embodiment
Step S2021, sub-step S2022 and sub-step S2023.
Feature extraction unit 230 is used to extract the circle for the defect that the first image includes using presetting feature extraction algorithm
Spend feature and area features.
Specifically, this feature extraction unit 230 is also used to extract the first image packet based on presetting Blob parser
The contour area of the defect contained, and for extracting the round degree of characteristics based on contour area and the first presetting formula, be also used to
Area features are extracted based on contour area and the second presetting formula.
It is to be appreciated that the pretreatment unit 220 can be used for executing step S203, son in a kind of preferred embodiment
Step S2031, sub-step S2032 and sub-step S2033.
Defect analysis unit 240 is for classifying to the defect of original image based on the round degree of characteristics and area features.
It is to be appreciated that the defect analysis unit 240 can be used for executing step S204 in a kind of preferred embodiment.
In conclusion defect classification method provided in an embodiment of the present invention, apparatus and system, by obtaining original image,
Original image is pre-processed again to obtain the first image, then extracts the first image using presetting feature extraction algorithm
The round degree of characteristics and area features for the defect for including, finally based on the round degree of characteristics and area features to the defect of original image
Classify；Due to being pre-processed to original image, the treating capacity of data is greatly reduced, to optimize the fortune of system
Speed is calculated, the efficiency finally identified is improved；Whole process carries out automatically simultaneously, without artificially being identified, substantially increases
The accuracy and precision of identification.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, defect categorizing system or the network equipment etc.) execute all or part of each embodiment the method for the present invention
Step.And storage medium above-mentioned include: USB flash disk, it is mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic or disk
Matter.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of defect classification method, which is characterized in that the defect classification method includes:
Obtain original image；
The original image is pre-processed to obtain the first image；
The round degree of characteristics and area features of the defect that the first image includes are extracted using presetting feature extraction algorithm；
Classified based on the round degree of characteristics and the area features to the defect of the original image.
2. defect classification method according to claim 1, which is characterized in that described to utilize presetting feature extraction algorithm
The step of extracting the round degree of characteristics and area features of the first image defect that includes include:
The contour area for the defect that the first image includes is extracted based on presetting Blob parser；
The round degree of characteristics is extracted based on the contour area and the first presetting formula；
The area features are extracted based on the contour area and the second presetting formula.
3. defect classification method according to claim 2, which is characterized in that the first presetting formula are as follows:
C=min (1, C ')
Wherein, C is circularity,F is the area of the contour area, the institute that max includes for the contour area
There is profile point to the maximum value in profile center.
4. defect classification method according to claim 2, which is characterized in that the second presetting formula are as follows:
Wherein, A is area, and g (r, c) is third image, and (r, c) is the coordinate of any one pixel in third image.
5. defect classification method according to claim 1, which is characterized in that described to be pre-processed to the original image
Include: the step of the first image to obtain
Gray scale scaling processing is carried out to obtain the second image to the original image using presetting gray scale scaling formula；
Closed operation processing is carried out to obtain third image to second image；
Threshold process is carried out to obtain the first image to the third image using presetting threshold value formula.
6. defect classification method according to claim 5, which is characterized in that the presetting gray scale scales formula are as follows:
Wherein, g2For the second image, g is original image, and GMax is the maximum gradation value of original image, and GMin is original image
Minimum gradation value.
7. defect classification method according to claim 5, which is characterized in that the presetting threshold value formula are as follows:
Wherein, g1For the first image, g3For third image, MinGray is presetting minimal gray threshold value, and ManGray is default
Fixed maximum gray threshold.
8. a kind of device for classifying defects, which is characterized in that the device for classifying defects includes:
Image acquisition unit, for obtaining original image；
Pretreatment unit, for being pre-processed to the original image to obtain the first image；
Feature extraction unit, for extracting the circularity for the defect that the first image includes using presetting feature extraction algorithm
Feature and area features；
Defect analysis unit, for being carried out based on the round degree of characteristics and the area features to the defect of the original image
Classification.
9. device for classifying defects according to claim 8, which is characterized in that the pretreatment unit is used for based on presetting
Blob parser extract the contour area of the first image defect that includes；
The pretreatment unit is also used to extract the round degree of characteristics based on the contour area and the first presetting formula；
The pretreatment unit is also used to extract the area features based on the contour area and the second presetting formula.
10. a kind of defect categorizing system, which is characterized in that the defect categorizing system include: memory, processor, controller,
Manipulator, camera, position sensor and device for classifying defects as claimed in claim 8 or 9, the memory, the control
Device processed is electrically connected with the processor respectively, and the controller and the manipulator, the camera and the position sensor are equal
Electrical connection；
The position sensor, which is used to sense after camshaft enters predeterminable area, acquires the position coordinates of the camshaft, and incites somebody to action
The position coordinates are transmitted to the controller；
The controller is run for controlling the manipulator to the position coordinates；
The prompt information is transmitted to the control for generating prompt information after reaching the position coordinates by the manipulator
Device processed；
The controller controls the camera and is shot the camshaft to obtain in advance for responding the prompt information
Set the original image of quantity；
The controller is also used to the original image being transmitted to the processor；
The processor be used for executes be installed on the memory and in the form of one or more software function modules storage
Device for classifying defects is to generate classification results；
The controller, which is used to control the manipulator according to the classification results, is put into corresponding discharging for corresponding camshaft
Mouthful.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811018191.9A CN109142393A (en) | 2018-09-03 | 2018-09-03 | A kind of defect classification method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811018191.9A CN109142393A (en) | 2018-09-03 | 2018-09-03 | A kind of defect classification method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109142393A true CN109142393A (en) | 2019-01-04 |
Family
ID=64826247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811018191.9A Pending CN109142393A (en) | 2018-09-03 | 2018-09-03 | A kind of defect classification method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109142393A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932515A (en) * | 2020-08-10 | 2020-11-13 | 成都数之联科技有限公司 | Short circuit detection method and system for product residual defects and defect classification system |
| CN114119472A (en) * | 2021-10-21 | 2022-03-01 | 东方晶源微电子科技（北京）有限公司 | Defect classification method and device, equipment and storage medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6263292B1 (en) * | 1997-02-28 | 2001-07-17 | Peter J. Fiekowsky | High accuracy particle dimension measurement system |
| JP2006047041A (en) * | 2004-08-03 | 2006-02-16 | Honda Motor Co Ltd | Method of generating data map for determining surface state, and determination method |
| JP2006214890A (en) * | 2005-02-04 | 2006-08-17 | M I L:Kk | Article defect information detector and article defect information detecting/processing program |
| US20080063426A1 (en) * | 2002-12-03 | 2008-03-13 | Tzyy-Shuh Chang | Apparatus and method for detecting surface defects on a workpiece such as a rolled/drawn metal bar |
| CN101620672A (en) * | 2009-08-14 | 2010-01-06 | 华中科技大学 | Method for positioning and identifying three-dimensional buildings on the ground by using three-dimensional landmarks |
| CN101837351A (en) * | 2010-06-02 | 2010-09-22 | 天津大学 | Oil seal spring full-automatic sorting system and method based on image detection method |
| CN102708356A (en) * | 2012-03-09 | 2012-10-03 | 沈阳工业大学 | Automatic license plate positioning and recognition method based on complex background |
| CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN103868935A (en) * | 2014-02-14 | 2014-06-18 | 中国科学院合肥物质科学研究院 | Cigarette appearance quality detection method based on computer vision |
| CN104597057A (en) * | 2015-02-02 | 2015-05-06 | 东华大学 | Columnar diode surface defect detection device based on machine vision |
| CN105044122A (en) * | 2015-08-25 | 2015-11-11 | 安徽工业大学 | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model |
| CN105069460A (en) * | 2015-08-21 | 2015-11-18 | 航天长征火箭技术有限公司 | ISAR image ship target feature extraction method |
| CN106127751A (en) * | 2016-06-20 | 2016-11-16 | 北京小米移动软件有限公司 | image detecting method, device and system |
| CN106409711A (en) * | 2016-09-12 | 2017-02-15 | 佛山市南海区广工大数控装备协同创新研究院 | Solar silicon wafer defect detecting system and method |
| CN106651825A (en) * | 2015-11-03 | 2017-05-10 | 中国科学院沈阳计算技术研究所有限公司 | Workpiece positioning and identification method based on image segmentation |
| CN106990839A (en) * | 2017-03-21 | 2017-07-28 | 张文庆 | A kind of eyeball identification multimedia player and its implementation |
| CN107525808A (en) * | 2017-07-27 | 2017-12-29 | 佛山市南海区广工大数控装备协同创新研究院 | Blister medication classification and the online visible detection method of defect on a kind of production line |
| CN107886493A (en) * | 2016-09-29 | 2018-04-06 | 成都思晗科技股份有限公司 | A kind of wire share split defect inspection method of transmission line of electricity |
-
2018
- 2018-09-03 CN CN201811018191.9A patent/CN109142393A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6263292B1 (en) * | 1997-02-28 | 2001-07-17 | Peter J. Fiekowsky | High accuracy particle dimension measurement system |
| US20080063426A1 (en) * | 2002-12-03 | 2008-03-13 | Tzyy-Shuh Chang | Apparatus and method for detecting surface defects on a workpiece such as a rolled/drawn metal bar |
| JP2006047041A (en) * | 2004-08-03 | 2006-02-16 | Honda Motor Co Ltd | Method of generating data map for determining surface state, and determination method |
| JP2006214890A (en) * | 2005-02-04 | 2006-08-17 | M I L:Kk | Article defect information detector and article defect information detecting/processing program |
| CN101620672A (en) * | 2009-08-14 | 2010-01-06 | 华中科技大学 | Method for positioning and identifying three-dimensional buildings on the ground by using three-dimensional landmarks |
| CN101837351A (en) * | 2010-06-02 | 2010-09-22 | 天津大学 | Oil seal spring full-automatic sorting system and method based on image detection method |
| CN102708356A (en) * | 2012-03-09 | 2012-10-03 | 沈阳工业大学 | Automatic license plate positioning and recognition method based on complex background |
| CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN103868935A (en) * | 2014-02-14 | 2014-06-18 | 中国科学院合肥物质科学研究院 | Cigarette appearance quality detection method based on computer vision |
| CN104597057A (en) * | 2015-02-02 | 2015-05-06 | 东华大学 | Columnar diode surface defect detection device based on machine vision |
| CN105069460A (en) * | 2015-08-21 | 2015-11-18 | 航天长征火箭技术有限公司 | ISAR image ship target feature extraction method |
| CN105044122A (en) * | 2015-08-25 | 2015-11-11 | 安徽工业大学 | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model |
| CN106651825A (en) * | 2015-11-03 | 2017-05-10 | 中国科学院沈阳计算技术研究所有限公司 | Workpiece positioning and identification method based on image segmentation |
| CN106127751A (en) * | 2016-06-20 | 2016-11-16 | 北京小米移动软件有限公司 | image detecting method, device and system |
| CN106409711A (en) * | 2016-09-12 | 2017-02-15 | 佛山市南海区广工大数控装备协同创新研究院 | Solar silicon wafer defect detecting system and method |
| CN107886493A (en) * | 2016-09-29 | 2018-04-06 | 成都思晗科技股份有限公司 | A kind of wire share split defect inspection method of transmission line of electricity |
| CN106990839A (en) * | 2017-03-21 | 2017-07-28 | 张文庆 | A kind of eyeball identification multimedia player and its implementation |
| CN107525808A (en) * | 2017-07-27 | 2017-12-29 | 佛山市南海区广工大数控装备协同创新研究院 | Blister medication classification and the online visible detection method of defect on a kind of production line |
Non-Patent Citations (2)
| Title |
|---|
| 卢荣胜: "自动光学（视觉）检测技术及其在缺陷检测中的", 《光学学报》 * |
| 於文欣: "基于机器视觉的FPC表面缺陷检测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932515A (en) * | 2020-08-10 | 2020-11-13 | 成都数之联科技有限公司 | Short circuit detection method and system for product residual defects and defect classification system |
| CN111932515B (en) * | 2020-08-10 | 2022-04-29 | 成都数之联科技股份有限公司 | Short circuit detection method and system for product residual defects and defect classification system |
| CN114119472A (en) * | 2021-10-21 | 2022-03-01 | 东方晶源微电子科技（北京）有限公司 | Defect classification method and device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11887064B2 (en) | Deep learning-based system and method for automatically determining degree of damage to each area of vehicle | |
| Hussin et al. | Digital image processing techniques for object detection from complex background image | |
| CN109389135B (en) | Image screening method and device | |
| CN108764202A (en) | Airport method for recognizing impurities, device, computer equipment and storage medium | |
| CN109145030B (en) | Abnormal data access detection method and device | |
| US10803116B2 (en) | Logo detection system for automatic image search engines | |
| CN106355367A (en) | Warehouse monitoring management device | |
| CN109815884A (en) | Unsafe driving behavioral value method and device based on deep learning | |
| US9977950B2 (en) | Decoy-based matching system for facial recognition | |
| CN103530648A (en) | Face recognition method based on multi-frame images | |
| CN108960145A (en) | Facial image detection method, device, storage medium and electronic equipment | |
| CN108921840A (en) | Display screen peripheral circuit detection method, device, electronic equipment and storage medium | |
| CN109142393A (en) | A kind of defect classification method, apparatus and system | |
| CN110059666A (en) | A kind of attention detection method and device | |
| CN110321944A (en) | A kind of construction method of the deep neural network model based on contact net image quality evaluation | |
| CN105931259A (en) | High voltage transmission line extraction method based on morphology processing and device | |
| CN104424633B (en) | A kind of video contrast's method for detecting abnormality and device | |
| CN105488486A (en) | Face recognition method and device for preventing photo attack | |
| US10043108B2 (en) | Method and apparatus for detecting and classifying active matrix organic light emitting diode panel | |
| Rodríguez et al. | HD-MR: A new algorithm for number recognition in electrical meters | |
| CN111931721B (en) | Method and device for detecting color and number of annual inspection label and electronic equipment | |
| CN108362227A (en) | Wheel hub detection method, device, system and control device | |
| CN117934897A (en) | Equipment abnormality detection method, device, equipment and storage medium | |
| CN116361695A (en) | Abnormal data detection method and device | |
| CN110287786A (en) | Based on artificial intelligence anti-tampering vehicle information recognition method and device |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190104 |
|
| WD01 | Invention patent application deemed withdrawn after publication |