CN107014830A - ITO electro-conductive glass detection method and detection means - Google Patents
ITO electro-conductive glass detection method and detection means Download PDFInfo
- Publication number
- CN107014830A CN107014830A CN201610135623.9A CN201610135623A CN107014830A CN 107014830 A CN107014830 A CN 107014830A CN 201610135623 A CN201610135623 A CN 201610135623A CN 107014830 A CN107014830 A CN 107014830A
- Authority
- CN
- China
- Prior art keywords
- breakpoint
- conductive glass
- region
- target image
- detected
- 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
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
A kind of ITO electro-conductive glass detection method and detection means, the detection method include：The surface to be detected of ITO electro-conductive glass is continuously shot, all target images of the whole graphics fields in the surface to be detected can be covered by obtaining；Pre-processed to shooting each target image obtained；Breaking point detection is carried out to each target image by pretreatment, the breaking point detection includes：Each pixel on pretreated target image is detected, each pixel is judged whether on the breakpoint in straight line, the breakpoint occurs being mutated for pixel brightness on straight line causes discontinuous pixel region；After by the breaking point detection in all regions for being judged as breakpoint, the region for belonging to normal breakpoint is excluded, and the region of remaining breakpoint is defined as scuffing region.Technical solution of the present invention can simple, efficiently and accurately detect the trickle scuffing situation of conducting wire and short-circuit conditions on ITO electro-conductive glass surface to be detected.
Description
Technical field
The present invention relates to technical field of vision detection, more particularly to a kind of ITO electro-conductive glass detection method and inspection
Survey device.
Background technology
The ITO electro-conductive glass that tin indium oxide (ITO, Indium Tin Oxides) film is manufactured is one
High in technological content extraordinary coated glass is planted, is also the basic material of electronics industry, mainly for the production of liquid
LCD (LCD, Liquid Crystal Display).Because liquid crystal display small volume, it is lightweight,
Thickness of thin, radiationless, voltage are low, energy-conserving and environment-protective, so it is most to be paid attention to and welcome in the world now
Display device, it is in states such as computer, communication, household electrical appliances, instrument and meter, military project, light industry, medical treatment
The every field of people's economy is widely used, be in current electronics industry purposes most extensively, development
Most rapid class product.With the newest replacement developed rapidly with display device of LCD industry,
The market demand of ITO electro-conductive glass will be greater than the growth rate of LCD industry.
Current domestic large batch of ITO conductive glass surfaces quality testing is largely directly to be entered by human eye
Row observation and judgement.Large batch of ITO conductive glass products detection generally requires substantial amounts of employee and carries out height
Repetitive work.This product defects detection mode has many weak points, first, and human eye is for a long time
It is operated under high light source and works, it is easily tired, easily judge by accident and fail to judge；Secondly as everyone is to mark
Accurate awareness is different with the degree of understanding, and the standard of subjective judgement is also different, it is difficult to quantify, therefore
In detection process, ununified examination criteria；Finally, due to which the workload of detection is big, repeatability
Height, the injury to human eye is serious.And sometimes, such as small size accurately will be measured quickly, shape
Shape is matched, colour recognition etc., and people with the naked eye can not continuously and stably be carried out at all, other physical sensings
Device also is difficult to have place to show one's prowess.Not only less efficient, working strength is big, and value-added content of product also compares
It is relatively low.
Developed rapidly with industrial, how quick effectively progress production detection is increasingly taken seriously,
And conventional tactics of human sea is no longer influenced by favor because of surging for cost of labor, therefore emerging detection technique is such as
Mechanical vision inspection technology is then promoted.So-called machine vision, is exactly with generation to machine with visual performance
Measure, analyze and differentiate for human eye, i.e., industrial lens, general point (are included by industrial camera
For two kinds of CMOS and CCD) object to be detected surface information is converted into picture signal, by image procossing
System (being, for example, Industrial PC and its set image pick-up card) is handled, and obtains target subject (quilt
Detection object) shape information, according to the information such as pixel distribution and brightness, color, be transformed into digitlization
These signals are carried out various computings to extract required detection feature such as area, position, length by signal
Degree, angle, quantity, color etc., then compare with default distinguishing rule, so as to export corresponding differentiation
Data or result.The hardware configuration of Machine Vision Inspecting System may be referred to Fig. 1 in the prior art.Machine is regarded
Feel technology has just been used in industrial automatic control since the birth, untouchable, high at a high speed with its
The features such as precision and stability, high flexibility, long-term effect and high performance-price ratio, as a kind of outstanding detection
Technology.
The surface defect problem of the products such as slight crack, cut and discoloration is always frequently encountered in the industrial production,
And these problems are all rich in challenge regardless of for artificial detection or Machine Vision Detection.Its difficulty is this
Class defect shape is irregular, depth contrast is low, and often by the natural texture or figure of product surface
Case is disturbed.Therefore, surface defects detection for correct polishing, camera resolution, be detected part with
The relative position of industrial camera, complicated Machine Vision Detection algorithm etc. require very high.Machine vision is drawn
The fundamental analysis process of trace detection is divided into two steps：First, it is determined that whether detection product surface has cut, its
It is secondary, after it is determined that there is cut on analyzed image, cut is extracted.The detection of cut is general
Scored portion is marked using gray feature or the method for Threshold segmentation based on statistics.
Due to the diversity of the image in industrial detection, for each image, it will integrate by analysis
Consider that various means reach effect to carry out processing.For the machine of ITO conductive glass surface conducting wires
For vision-based detection, due to the scuffing of generation be extremely it is trickle (as shown in the rectangle frame in Fig. 2 and Fig. 3,
White line in relevant drawings is the conducting wire of ITO conductive glass surfaces), drawn by traditional
Trace detection method is difficult to the scuffing situation for simply, efficiently and accurately detecting conducting wire, therefore have must
Take more targeted detection means.
In addition, in general, (being led to the figure of ITO conductive glass surfaces by mechanical vision inspection technology
Electric line) when being detected, the industrial camera that existing ITO electro-conductive glass detection means is used is not
Polaroid, but scan-type, existing industrial camera camera lens is divided into two kinds：One is Linear Array Realtime, one
Secondary is clapped a line so wide image, and the region of linear array is probably 2*0.0001 width, so when shooting
Between long, take, camera lens it is expensive, but quality of taking pictures is higher；Another is planar array type, once claps certain face
Product, such as transparency area is 20*50, face array area domain (the i.e. graph area on ITO electro-conductive glass surface to be detected
Domain) it is it is necessary to clapping 250 times if 2*2.Although the camera lens of planar array type is cheap, imaging efficiency is higher,
It is poor image quality, imaging effect is relatively low, is unfavorable for the lookup of defect, therefore propose for detection algorithm
Higher requirement.
The content of the invention
The problem to be solved in the present invention be machine vision detection device of the prior art be difficult to it is simple, efficient,
The trickle scuffing situation of conducting wire on ITO electro-conductive glass surface to be detected is detected exactly.
To solve the above problems, technical solution of the present invention provides a kind of ITO electro-conductive glass detection method, bag
Include：The surface to be detected of ITO electro-conductive glass is continuously shot, acquisition can cover described to be detected
All target images of surface whole graphics field；Pre-processed to shooting each target image obtained；
Breaking point detection is carried out to each target image by pretreatment, the breaking point detection includes：The pre- place of detection
Each pixel on target image after reason, judges each pixel whether on the breakpoint in straight line, institute
Stating breakpoint and occurring being mutated for pixel brightness on straight line causes discontinuous pixel region；From passing through
It is all after the breaking point detection to be judged as in the region of breakpoint, the region for belonging to normal breakpoint is excluded, and
The region of remaining breakpoint is defined as to scratch region.
Optionally, the ITO electro-conductive glass detection method also includes：It is disconnected on all straight lines are judged
After point, it is determined that being judged as the width of the corresponding region of breakpoint.
Optionally, each pixel on the pretreated target image of detection, judges each pixel
Whether include on the breakpoint in straight line：
Bright line edge is detected, the bright line corresponds to described for the conducting wire on the ITO electro-conductive glass
Bargraphs on target image；
According to the straight parallel lines of the verge searching of the bright line；
Pixel brightness on each bar parallel lines is found out to occur being mutated and cause discontinuous all pixels point.
Optionally, the width in the region for determining to be judged as breakpoint includes：To the discontinuous institute
There is pixel to carry out edge judgement, determine the width of the breakpoint corresponding region.
Optionally, described pair of each target image progress pretreatment for shooting acquisition includes：Obtained to shooting
Each target image carry out dynamic partition, be adapted for the breakpoint to be partitioned into the target image
The region to be detected of detection.
Optionally, there is partly overlapping region between the adjacent target image for shooting acquisition；Described pair of bat
Taking the photograph each target image progress pretreatment of acquisition includes：The target figure obtained after being removed according to shooting order
There is partly overlapping region with the target image that first obtains as among.
Optionally, being continuously shot for surface to be detected to the ITO electro-conductive glass is entered with preset frequency
Capable.
Optionally, the ITO electro-conductive glass is made or suitable for the surface to be detected progress to ITO electro-conductive glass
The industrial camera being continuously shot at the uniform velocity is moved, between the camera lens of the industrial camera and the surface to be detected
Keeping parallelism.
To solve the above problems, technical solution of the present invention also provides a kind of ITO electro-conductive glass detection means,
Including：Image acquisition units, are continuously shot suitable for the surface to be detected to ITO electro-conductive glass, obtain
All target images of the whole graphics fields in the surface to be detected can be covered by obtaining；Pretreatment unit, is fitted
Pre-processed in shooting each target image obtained to described image collecting unit；First detection unit,
Suitable for carrying out breaking point detection to each target image by pretreatment, the breaking point detection includes：Detection
Each pixel on pretreated target image, judges each pixel whether on the breakpoint in straight line,
And the width of the breakpoint is determined, the breakpoint occurs being mutated for pixel brightness on straight line to be caused
Discontinuous pixel region；Second detection unit, is judged suitable for all after by the breaking point detection
For in the region of breakpoint, the region for belonging to normal breakpoint is excluded, and the region of remaining breakpoint is defined as to draw
Hinder region.
Optionally, the ITO electro-conductive glass detection means also include breakpoint width determining unit, suitable for
After judging the breakpoint on all straight lines, it is determined that being judged as the width of the corresponding region of breakpoint.
Compared with prior art, technical scheme at least has advantages below：
The target image for being continuously shot acquisition by the surface to be detected to ITO electro-conductive glass carries out breakpoint inspection
Survey, judge each pixel of target image whether on the breakpoint in straight line, the breakpoint is straight line
Upper pixel brightness occurs being mutated and causes discontinuous pixel region, the institute after by the breaking point detection
Have in the region for being judged as breakpoint, exclude and belong to the region of normal breakpoint, and by the region of remaining breakpoint
It is defined as scratching region, thus, it is possible to simply, efficiently and accurately detect that ITO electro-conductive glass is to be detected
The trickle scuffing situation of conducting wire and short-circuit conditions on surface.
Further, since no matter ITO electro-conductive glass sizes to be detected, are treated as long as ensureing that shooting area is covered
Detection zone just can carry out breaking point detection, and technical solution of the present invention has stronger adaptability.
Brief description of the drawings
Fig. 1 is the hardware architecture diagram of Machine Vision Inspecting System in the prior art；
Fig. 2 and Fig. 3 are that the schematic diagram of trickle scuffing situation occurs for the conducting wire of ITO conductive glass surfaces；
Fig. 4 is the schematic flow sheet for the ITO electro-conductive glass detection methods that technical solution of the present invention is provided；
Fig. 5 is the signal for carrying out vision-based detection in the embodiment of the present invention to ITO electro-conductive glass surface to be detected
Figure；
Fig. 6 is the schematic diagram for the target image for having pending breaking point detection in the embodiment of the present invention；
Fig. 7 is the schematic diagram at detection bright line edge in the embodiment of the present invention；
Fig. 8 is to find straight parallel lines in the embodiment of the present invention and therefrom find out showing for discontinuous pixel
It is intended to；
Fig. 9 is the schematic diagram for carrying out edge judgement in the embodiment of the present invention to discontinuous pixel；
Figure 10 to Figure 12 is the actual effect signal of the ITO electro-conductive glass detection methods of the embodiment of the present invention
Figure；
Figure 13 is that the schematic diagram of short-circuit conditions occurs for the conducting wire of ITO conductive glass surfaces.
Embodiment
In the prior art, using the machine vision detection device of area array cameras to ITO conductive glass surfaces
Conducting wire is detected, because the scuffing produced in the conducting wire is usually extremely trickle, and
In order to which the image quality for improving area array cameras used in detection efficiency is also very limited, then still with traditional
Scratch detection method carries out Machine Vision Detection, certainly will be difficult to it is simple, efficiently and accurately detect conduction
The scuffing situation of circuit.
Therefore, technical solution of the present invention provides a kind of ITO electro-conductive glass detection method, by using at a high speed
Industrial camera, is detected in the way of being continuously shot, i.e.,：One camera is continuous according to certain frequency
Image is gathered, workpiece (ITO electro-conductive glass) to be detected passes through the shooting point of industrial camera with certain speed,
Or mobile industrial camera so shoots to fixed workpiece to be detected and completes a workpiece, will obtain
Region to be detected is completely covered in a series of picture, these pictures；For shooting a series of pictures obtained,
The breakpoint on every pictures is detected in the way of breaking point detection, with this determination ITO conductive glass surfaces
The scuffing situation of conducting wire.
Above-mentioned detection method has following several advantages：
1. simple system, efficiently：Due to being continuously shot using industrial camera, as long as ensureing the scope shot
Cover whole regions to be checked, it is not necessary to simple in construction for specific region etc.；And only
It is continuously shot completion and can be obtained by result, without follow-up splicing etc., efficiency high.
2. strong adaptability：No matter product size to be checked, as long as ensureing that shooting area covers region to be checked just energy work
Make.
3. accuracy is high：Judge no matter each pixel of target image whether on the breakpoint in straight line, leads
How trickle scuffing in electric line is, still is able to detect exactly by way of breaking point detection.
As shown in figure 4, the ITO electro-conductive glass detection method includes：
Step S101, is continuously shot, acquisition can be covered to the surface to be detected of ITO electro-conductive glass
All target images of the whole graphics fields in surface to be detected；
Step S102, is pre-processed to shooting each target image obtained；
Step S103, breaking point detection, the breaking point detection are carried out to each target image by pretreatment
Including：Each pixel on pretreated target image is detected, judges each pixel whether in straight
On the breakpoint of line, the breakpoint occurs being mutated for pixel brightness on straight line causes discontinuous picture
Plain region；
Step S104, after by the breaking point detection in all regions for being judged as breakpoint, excludes category
It is defined as scuffing region in the region of normal breakpoint, and by the region of remaining breakpoint.
It is understandable to enable the above objects, features and advantages of the present invention to become apparent, below in conjunction with the accompanying drawings
The specific embodiment of the present invention is described in detail.
Fig. 5 can be referred to by carrying out vision-based detection in the embodiment of the present invention to ITO electro-conductive glass surface to be detected,
Vision detection system includes ITO electro-conductive glass, conveyer belt, industrial camera and encoder to be detected,
During actual implementation, ITO electro-conductive glass to be detected can be positioned on conveyer belt, ITO electro-conductive glass
Surface to be detected upward, the surface to be detected include whole graphics fields to be detected, it is to be captured
The size of each graphics field determines that area array cameras is then vertically fixed on ITO by the coverage of area array cameras
The relative position on electro-conductive glass surface to be detected, so that the graphics field to surface to be detected is continuously clapped
Take the photograph.
After vision-based detection starts, encoder control conveyer belt motion drives ITO electro-conductive glass by conveyer belt
Arrow direction as shown in Figure 5 is at the uniform velocity moved, and so continuous graphics field will one by one
Sequentially pass through industrial camera camera lens just to position, when there is trigger signal to be transmitted from encoder, industrial phase
Machine receives the trigger signal, just starts and takes pictures, then completes process of taking pictures through overexposure.In the present embodiment,
Industrial camera can be carried out to being continuously shot for surface to be detected of ITO electro-conductive glass with preset frequency.
With continued reference to Fig. 5, in the present embodiment, with the movement of ITO electro-conductive glass, if its surface to be detected
Some graphics field be moved to industrial camera camera lens just to position, camera receives start trigger signal
The graphics field, is now referred to as the graphics field of current shooting by the shooting to the graphics field, and with this
The adjacent region in graphics field is then referred to as next graphics field to be captured.
In the present embodiment, as long as ensureing the whole region to be checked of the scope covering shot, it is not necessary to pin
To specific graphics field, therefore shoot can between two target images that adjacent pattern region is formed respectively
There is partly overlapping region, this can't influence the accuracy of testing result, so for encoder
The required precision that automatically controls for sending trigger signal is not very high, with stronger adaptability.
It should be noted that except fixed industrial camera, and drive in the way of conveyer belt ITO to be detected
The mode that electro-conductive glass is at the uniform velocity moved is carried out outside IMAQ, in other embodiments, can also be provided
ITO electro-conductive glass is fixed, and image is carried out in the way of transmission mechanism drives industrial camera at the uniform velocity to move and is adopted
Collection.Certainly, when the ITO electro-conductive glass or the industrial camera is at the uniform velocity moved, the mirror of the industrial camera
Keeping parallelism between head and the surface to be detected.In the present embodiment, make object to be detected or face battle array phase
Machine is in constant at the uniform velocity moving process, i.e., the IMAQ in detection process is continuous, uninterrupted
Ground is carried out, and can so improve detection efficiency.
It should be noted that in the present embodiment, the industrial camera is specially area array cameras, camera is adopted
Photo-sensitive cell can be Charged Couple (CCD, Charge-Coupled Device) photo-sensitive cell,
Can be complementary metal oxide semiconductor (CMOS, Complementary Metal Oxide
Semiconductor) photo-sensitive cell.
In the present embodiment, the surface to be detected of ITO electro-conductive glass is continuously shot, acquisition can be covered
, can also be to shooting what is obtained after all target images for covering the whole graphics fields in the surface to be detected
Target image is pre-processed.
Specifically, the pretreatment can include：Enter Mobile state point to shooting each target image obtained
Cut, to be partitioned into the region to be detected that the breaking point detection is adapted in the target image.Due to this
Embodiment provide detection method be especially suitable for for specific figure (ITO conductive glass surfaces it is numerous mutually
Parallel conducting wire) detected, then do not fit through breakpoint when existing in the target image of shooting
During the region of detection mode detection, then need therefrom to extract and be adapted for the to be detected of the breaking point detection
Region, it is ensured that the accuracy of detection.
In addition, as it was previously stated, there may be partly overlapping area between shooting the adjacent target image obtained
Domain, then pretreatment can also include：With first obtaining among the target image obtained after being removed according to shooting order
There is partly overlapping region in the target image obtained.It is partly overlapping for existing between adjacent target image
The situation in region, in order to avoid repeating to detect, can remove repeating part, the same area only detects one
It is secondary, it can so greatly improve detection efficiency.
, then can be to by each of pretreatment after being pre-processed to each target image for shooting acquisition
Individual target image carries out breaking point detection.
In the present embodiment, breakpoint refers to that pixel brightness occurs being mutated and caused discontinuous on straight line
Pixel region, Fig. 2 or Fig. 3 can be referred to, the white line in figure is ITO conductive glass surfaces
Conducting wire, the region in figure shown in rectangle frame is the presence of one piece of black region in white line, and this is black
Color region is the breakpoint in the white line of place, and breakpoint can be recognized by the brightness change of pixel,
It will be apparent that occurring the region of pixel intensity change suddenly in white line, i.e., go out suddenly in white line
Existing a bit of discontinuous situation, this block region is considered breakpoint.
It should be noted that breakpoint is not that just can be made up of some pixel, but by more pixel
Point is collectively forming, and the concept of " point " is to correspond to target relative to the conducting wires of ITO conductive glass surfaces
White line figure on image.Certainly, when carrying out image recognition processing by computer, it can recognize
For the corresponding white line of a conducting wire be by sets of parallel that a rule width is a pixel into,
It can be calculated based on each such parallel lines.
In the present embodiment, the breaking point detection can specifically detect each on pretreated target image
Pixel, judge each pixel whether in straight line (may be considered the bright line on target image, it is described
Bright line refers to the bargraphs that conducting wire on ITO electro-conductive glass corresponds on target image) breakpoint
On, can be with and after can drawing the width of breakpoint, the i.e. breakpoint on all straight lines are judged
It is determined that being judged as the width of the corresponding region of breakpoint.
During actual implementation, the algorithm principle of breaking point detection can include following process：
First, detection bright line edge.Comparison diagram 6 and Fig. 7, Fig. 6 are the targets for having pending breaking point detection
Some part of image (target image may be pretreated) or target image, Fig. 7 be then by
Heavy black line in the schematic diagram formed behind bright line edge, Fig. 7 can clearly define each in vain
Color bright line (the actual rule conducting wire of correspondence).
Then, according to the straight parallel lines of bright line verge searching.It is with this that can refer in Fig. 8, the present embodiment
Breakpoint is found based on a little straight parallel lines.
Again, pixel brightness on each bar parallel lines is found out to occur being mutated and cause discontinuous all pixels
Point.Referring still to Fig. 8, the aterrimus region indicated in figure with circle is the discontinuous picture on parallel lines
Vegetarian refreshments, these discontinuous neighbor pixels constitute a breakpoint.
Finally, edge judgement is carried out to the discontinuous all pixels point, determines the breakpoint correspondence area
The width in domain.As shown in figure 9, the distance of every white line in the horizontal direction is the lines in figure
Width, the distance of breakpoint in the horizontal direction in the white line is the width of breakpoint corresponding region.
Certainly, in all breakpoints found out by breaking point detection, some breakpoints are that the original of conducting wire sets
Meter, belongs to normal breakpoint, is not to be caused by the scuffing in production technology, therefore also need to break these
Point is excluded.
Specifically, after by the breaking point detection in all regions for being judged as breakpoint, exclusion belongs to
The region of normal breakpoint, and the region of remaining breakpoint is defined as scuffing region.During actual implementation, only need
The region and the feature of respective regions in former design drawing that will be deemed as breakpoint are compared, and which just can determine that
It is the region of normal breakpoint a bit.
By ITO electro-conductive glass detection method provided in an embodiment of the present invention, can simply, efficiently, it is accurate
The scuffing situation of the conducting wire of ITO conductive glass surfaces really is detected, its actual effect such as Figure 10 is extremely
Shown in Figure 12, the rectangle frame in figure is the region for being judged as breakpoint.
It is pointed out that ITO electro-conductive glass detection method provided in an embodiment of the present invention is not only able to inspection
The common scuffing situation of the conducting wire of ITO conductive glass surfaces is measured, and can also detect that ITO is led
The short-circuit conditions of the conducting wire of electric glass surface.As shown in figure 13, the region that circle is indicated in figure, it is former
It should be grey, and become white now, show that adjacent wire sticks together and formd short
Road.It will be appreciated by those skilled in the art that such case completely can be by provided in an embodiment of the present invention
Similar detection method finds out defect, and here is omitted.
Based on above-mentioned ITO electro-conductive glass detection means, the embodiment of the present invention also provides a kind of conductive glass of ITO
Glass detection means, including：Image acquisition units, suitable for the surface to be detected progress to ITO electro-conductive glass
It is continuously shot, all target images of the whole graphics fields in the surface to be detected can be covered by obtaining；In advance
Processing unit, is pre-processed suitable for shooting each target image obtained to described image collecting unit；
First detection unit, suitable for carrying out breaking point detection, the breakpoint to each target image by pretreatment
Detection includes：Each pixel on pretreated target image is detected, judges whether each pixel is located
In on the breakpoint of straight line, and the width of the breakpoint is determined, the breakpoint is that pixel is lighted on straight line
Degree appearance is mutated and causes discontinuous pixel region；Second detection unit, suitable for from passing through the breakpoint
It is all after detection to be judged as in the region of breakpoint, the region for belonging to normal breakpoint is excluded, and remaining is broken
The region of point is defined as scratching region.
In the present embodiment, the ITO electro-conductive glass detection means also includes breakpoint width determining unit, fits
After the breakpoint on all straight lines are judged, it is determined that being judged as the width of the corresponding region of breakpoint.
The specific implementation of the ITO electro-conductive glass detection means can also be with reference to the inspection of above-mentioned ITO electro-conductive glass
The implementation of survey method, here is omitted.
It will be understood by those skilled in the art that realizing the ITO electro-conductive glass detection means in above-described embodiment
All or part program is can be by instruct the hardware of correlation to complete, described program can deposit
It is stored in computer-readable recording medium, the storage medium can be ROM, RAM, magnetic disc, CD
Deng.
Although the present invention is disclosed as above with preferred embodiment, it is not for limiting the present invention, appointing
What those skilled in the art without departing from the spirit and scope of the present invention, may be by the disclosure above
Methods and techniques content makes possible variation and modification to technical solution of the present invention, therefore, every not take off
From the content of technical solution of the present invention, it is any that the technical spirit according to the present invention is made to above example
Simple modification, equivalent variation and modification, belong to the protection domain of technical solution of the present invention.
Claims (10)
1. a kind of ITO electro-conductive glass detection method, it is characterised in that including：
The surface to be detected of ITO electro-conductive glass is continuously shot, acquisition can cover described to be detected
All target images of surface whole graphics field；
Pre-processed to shooting each target image obtained；
Breaking point detection is carried out to each target image by pretreatment, the breaking point detection includes：Detection
Each pixel on pretreated target image, judges each pixel whether on the breakpoint in straight line,
The breakpoint occurs being mutated for pixel brightness on straight line causes discontinuous pixel region；
After by the breaking point detection in all regions for being judged as breakpoint, exclusion belongs to normal breakpoint
Region, and by the region of remaining breakpoint be defined as scratch region.
2. ITO electro-conductive glass detection method according to claim 1, it is characterised in that also include：
After judging the breakpoint on all straight lines, it is determined that being judged as the width of the corresponding region of breakpoint.
3. ITO electro-conductive glass detection method according to claim 2, it is characterised in that the detection is pre-
Each pixel on target image after processing, judges whether each pixel wraps on the breakpoint in straight line
Include：
Bright line edge is detected, the bright line corresponds to described for the conducting wire on the ITO electro-conductive glass
Bargraphs on target image；
According to the straight parallel lines of the verge searching of the bright line；
Pixel brightness on each bar parallel lines is found out to occur being mutated and cause discontinuous all pixels point.
4. ITO electro-conductive glass detection method according to claim 3, it is characterised in that the determination quilt
Being judged as the width in the region of breakpoint includes：Edge judgement is carried out to the discontinuous all pixels point,
Determine the width of the breakpoint corresponding region.
5. ITO electro-conductive glass detection method according to claim 1, it is characterised in that described pair of shooting
Each target image obtained, which carries out pretreatment, to be included：Enter Mobile state to shooting each target image obtained
Segmentation, to be partitioned into the region to be detected that the breaking point detection is adapted in the target image.
6. ITO electro-conductive glass detection method according to claim 1, it is characterised in that shoot what is obtained
There is partly overlapping region between adjacent target image；Described pair shoots each target image obtained and enters
Row pretreatment includes：Target figure among the target image obtained after being removed according to shooting order with first obtaining
As there is partly overlapping region.
7. ITO electro-conductive glass detection method according to claim 1, it is characterised in that to the ITO
Being continuously shot for the surface to be detected of electro-conductive glass is carried out with preset frequency.
8. ITO electro-conductive glass detection method according to claim 1, it is characterised in that make the ITO
Electro-conductive glass or the industrial camera that is continuously shot suitable for the surface to be detected to ITO electro-conductive glass are at the uniform velocity
It is mobile, keeping parallelism between the camera lens of the industrial camera and the surface to be detected.
9. a kind of ITO electro-conductive glass detection means, it is characterised in that including：
Image acquisition units, are continuously shot suitable for the surface to be detected to ITO electro-conductive glass, obtain
All target images of the whole graphics fields in the surface to be detected can be covered；
Pretreatment unit, is carried out in advance suitable for shooting each target image obtained to described image collecting unit
Processing；
First detection unit, it is described suitable for carrying out breaking point detection to each target image by pretreatment
Breaking point detection includes：Each pixel on pretreated target image is detected, judges that each pixel is
On the no breakpoint in straight line, the breakpoint occurs being mutated for pixel brightness on straight line to be caused not
Continuous pixel region；
Second detection unit, suitable in all regions for being judged as breakpoint after by the breaking point detection,
The region for belonging to normal breakpoint is excluded, and the region of remaining breakpoint is defined as scuffing region.
10. ITO electro-conductive glass detection means according to claim 9, it is characterised in that also including breakpoint
Width determining unit, after the breakpoint on all straight lines are judged, it is determined that being judged as breakpoint
The width of corresponding region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610135623.9A CN107014830A (en) | 2016-03-10 | 2016-03-10 | ITO electro-conductive glass detection method and detection means |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610135623.9A CN107014830A (en) | 2016-03-10 | 2016-03-10 | ITO electro-conductive glass detection method and detection means |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107014830A true CN107014830A (en) | 2017-08-04 |
Family
ID=59439051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610135623.9A Pending CN107014830A (en) | 2016-03-10 | 2016-03-10 | ITO electro-conductive glass detection method and detection means |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107014830A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445022A (en) * | 2018-03-19 | 2018-08-24 | 无锡睿途自控科技有限公司 | A kind of glass is residual just to remove detection mode |
| CN110006915A (en) * | 2018-08-30 | 2019-07-12 | 永康市缘匠贸易有限公司 | Glass blocks bar detection mechanism |
| CN111103309A (en) * | 2018-10-26 | 2020-05-05 | 苏州乐佰图信息技术有限公司 | Method for detecting flaws of transparent material object |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001099789A (en) * | 1999-10-04 | 2001-04-13 | Tosoh Corp | Method of observing sintered compact, ito sintered compact, and manufacturing method of its sputtering target and ito sintered compact |
| JP2003262566A (en) * | 2002-03-07 | 2003-09-19 | Toppan Printing Co Ltd | Defect detection method for transparent conductive film and defect detection device thereof |
| CN101750422A (en) * | 2010-01-07 | 2010-06-23 | 秦皇岛凯维科技有限公司 | On-line automatic detection device for glass defect |
| CN101986143A (en) * | 2010-03-17 | 2011-03-16 | 燕山大学 | Machine vision belt tear detection and protective device |
| CN102270299A (en) * | 2011-08-24 | 2011-12-07 | 复旦大学 | Edge connection algorithm realized in parallel based on breakpoints |
| CN103076345A (en) * | 2013-01-16 | 2013-05-01 | 东莞市三姆森光电科技有限公司 | Detection method and full-automatic optical detection system for ITO conductive glass |
| CN204694646U (en) * | 2015-06-02 | 2015-10-07 | 东莞市三姆森光电科技有限公司 | A kind of structure improved ITO electro-conductive glass pick-up unit |
-
2016
- 2016-03-10 CN CN201610135623.9A patent/CN107014830A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001099789A (en) * | 1999-10-04 | 2001-04-13 | Tosoh Corp | Method of observing sintered compact, ito sintered compact, and manufacturing method of its sputtering target and ito sintered compact |
| JP2003262566A (en) * | 2002-03-07 | 2003-09-19 | Toppan Printing Co Ltd | Defect detection method for transparent conductive film and defect detection device thereof |
| CN101750422A (en) * | 2010-01-07 | 2010-06-23 | 秦皇岛凯维科技有限公司 | On-line automatic detection device for glass defect |
| CN101986143A (en) * | 2010-03-17 | 2011-03-16 | 燕山大学 | Machine vision belt tear detection and protective device |
| CN102270299A (en) * | 2011-08-24 | 2011-12-07 | 复旦大学 | Edge connection algorithm realized in parallel based on breakpoints |
| CN103076345A (en) * | 2013-01-16 | 2013-05-01 | 东莞市三姆森光电科技有限公司 | Detection method and full-automatic optical detection system for ITO conductive glass |
| CN204694646U (en) * | 2015-06-02 | 2015-10-07 | 东莞市三姆森光电科技有限公司 | A kind of structure improved ITO electro-conductive glass pick-up unit |
Non-Patent Citations (3)
| Title |
|---|
| 徐乐云: "S90270缺划不良分析报告", 《百度文库》 * |
| 肖嵩等: "《计算机图形学原理及应用》", 30 June 2014, 西安电子科技大学出版社 * |
| 陈方涵等: "高分辨率ITO导电薄膜透明区域缺陷识别", 《光子学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445022A (en) * | 2018-03-19 | 2018-08-24 | 无锡睿途自控科技有限公司 | A kind of glass is residual just to remove detection mode |
| CN108445022B (en) * | 2018-03-19 | 2020-11-03 | 无锡尚实电子科技有限公司 | Detection mode for removing residual glass |
| CN110006915A (en) * | 2018-08-30 | 2019-07-12 | 永康市缘匠贸易有限公司 | Glass blocks bar detection mechanism |
| CN111103309A (en) * | 2018-10-26 | 2020-05-05 | 苏州乐佰图信息技术有限公司 | Method for detecting flaws of transparent material object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN108355981A (en) | A kind of battery connector quality determining method based on machine vision | |
| Tao et al. | Weak scratch detection and defect classification methods for a large-aperture optical element | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| CN103076345A (en) | Detection method and full-automatic optical detection system for ITO conductive glass | |
| CN103645573A (en) | Liquid crystal display (LCD) detection method and system based on machine vision | |
| CN112819844B (en) | Image edge detection method and device | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN108416766A (en) | Bilateral incidence type light guide plate defective vision detection method | |
| CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
| CN109916910A (en) | Photovoltaic glass edge fault detection system and corresponding method | |
| CN104777172A (en) | Quick and intelligent defective optical lens detection device and method | |
| CN107014830A (en) | ITO electro-conductive glass detection method and detection means | |
| CN110567976A (en) | mobile phone cover plate silk-screen defect detection device and detection method based on machine vision | |
| CN110096980A (en) | Character machining identifying system | |
| CN109507205A (en) | A kind of vision detection system and its detection method | |
| CN110208269A (en) | The method and system that a kind of glass surface foreign matter and internal foreign matter are distinguished | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN113865830A (en) | Display screen defect detection method and system | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN203908956U (en) | System for detecting surface defects of workpiece | |
| CN114820439A (en) | PCB bare board defect detection system and method based on AOI | |
| CN116818785B (en) | Defect detection method, system and medium based on machine vision | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170804 |