CN108776146A - Method and device for detecting silk-screen lines - Google Patents
Method and device for detecting silk-screen lines Download PDFInfo
- Publication number
- CN108776146A CN108776146A CN201810772238.4A CN201810772238A CN108776146A CN 108776146 A CN108776146 A CN 108776146A CN 201810772238 A CN201810772238 A CN 201810772238A CN 108776146 A CN108776146 A CN 108776146A
- Authority
- CN
- China
- Prior art keywords
- silk
- screen lines
- detected
- lines
- screen
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000007797 corrosion Effects 0.000 claims abstract description 111
- 238000005260 corrosion Methods 0.000 claims abstract description 111
- 238000001514 detection method Methods 0.000 claims abstract description 70
- 230000007547 defect Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims description 44
- 230000000877 morphologic effect Effects 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 9
- 230000002950 deficient Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004378 air conditioning Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 8
- 238000013459 approach Methods 0.000 description 7
- 239000004973 liquid crystal related substance Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
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
- G01N21/8851—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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/32—Polishing; Etching
-
- 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
-
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for detecting silk-screen lines. Wherein, the method comprises the following steps: extracting silk-screen lines to be detected from a panel area on a product image; carrying out corrosion treatment on the silk-screen lines to be detected by adopting different corrosion kernel values to obtain the silk-screen lines subjected to corrosion treatment; and determining whether the silk-screen lines to be detected have defects by counting the number of the silk-screen lines subjected to the corrosion treatment, wherein the defects comprise at least one of the following defects: the invention solves the technical problem that in the prior art, the detection result is inaccurate by adopting a method for detecting whether the silk-screen lines are defective by calipers because the silk-screen lines are small in size.
Description
Technical field
The present invention relates to detection technique fields, in particular to a kind of detection method and device of silk-screen lines.
Background technology
At present in detection field, the method for inc lines burr or defect is detected based on visual detection, usual feelings
The detection method that Kuang Xia enterprises use is：(1) extraction line edge region；(2) this one paths of regional planning is given；(3) exist
On this path a point, the measurement point as slide calliper rule are taken every a distance；(4) width of this section of lines is measured with caliper tool
Degree；(5) the bad of lines each section can be measured once week along this path.The method only has 0.2mm below some width
Lines detection is not closed to have the following disadvantages：1. having the risk of erroneous judgement, by taking manual operator panel silk-screen lines as an example, using normal
The industrial camera of 5,000,000 pixels detects, and the width of lines only has two to three pixels, inspection of the slide calliper rule to this baguette
Survey is inaccurate, and there are the risks of bad products flase drop；2. increasing the complexity of detection algorithm, need within one week to avoid around path
The opening of lines increases the calculation amount of algorithm.
In for the above-mentioned prior art, since silk-screen line size is tiny, whether silk-screen lines are detected using slide calliper rule
Defective method can lead to the technical problem of testing result inaccuracy, and currently no effective solution has been proposed.
Invention content
An embodiment of the present invention provides a kind of detection method and device of silk-screen lines, at least to solve in the prior art,
Since silk-screen line size is tiny, the whether defective method of silk-screen lines is detected using slide calliper rule, testing result can be caused
Inaccurate technical problem.
One side according to the ... of the embodiment of the present invention provides a kind of detection method of silk-screen lines, including：From product figure
As upper panel zone extracts silk-screen lines to be detected；Using different corrosion kernel values, to the silk-screen line to be detected
Item carries out corrosion treatment, obtains the silk-screen lines after corrosion treatment；Pass through the number of the silk-screen lines after the statistics corrosion treatment
Amount, to determine that the silk-screen lines to be detected whether there is defect, wherein the defect includes at least one following：Defect
And burr.
Further, in the case where the corrosion treatment is that constriction is handled, the silk-screen lines to be detected are carried out
Corrosion treatment obtains the silk-screen lines after corrosion treatment, including：Using the first corrosion kernel value to the silk-screen line to be detected
Item carries out the constriction processing, obtains the silk-screen lines of constriction line thickness；Wherein, if after detecting the constriction processing
Silk-screen lines be off, determine that there are the defects for the silk-screen lines to be detected.
Further, detect the constriction treated silk-screen lines be off including：If at the constriction
The quantity of silk-screen lines after reason is more than first threshold, determines the constriction treated that silk-screen lines are off.
Further, the constriction processing is carried out to the silk-screen lines to be detected in the horizontal and/or vertical.
Further, the constriction processing is being carried out to the silk-screen lines to be detected using the first corrosion kernel value,
Before obtaining the silk-screen lines of constriction line thickness, the method further includes：
Count the quantity of the silk-screen lines to be detected extracted；If the quantity of the silk-screen lines to be detected
For second threshold, then executes and the step of constriction is handled is carried out to the silk-screen lines to be detected；Otherwise, it determines described wait for
There are defect and/or burrs for the silk-screen lines of detection.
Further, in the case where the corrosion treatment is to corrode the silk-screen lines completely, to described to be detected
Silk-screen lines carry out corrosion treatment, obtain the silk-screen lines after corrosion treatment, including：It is waited for described using the second corrosion kernel value
The silk-screen lines of detection increase corroded area in the horizontal and/or vertical, obtain grayscale morphologic and corrode complete region；Its
In, if the grayscale morphologic, which corrodes complete region, also detects silk-screen lines, it is determined that the silk-screen lines to be detected
There are the burrs.
Further, it detects the grayscale morphologic and corrodes the silk-screen lines in complete region and include：Statistics is located at the ash
Spend the quantity of the silk-screen lines in the complete region of morphological erosion；If quantity is more than second threshold, determine that the grayscale morphologic is rotten
Losing complete region, there is also silk-screen lines.
Further, before silk-screen lines to be detected being extracted in the panel zone from product image, the method is also
Including：Based on image template, the panel zone in the product image is determined；The interference image in the panel zone is searched,
Determine background area to be shielded；By shielding the background area, the region where the silk-screen lines is obtained.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of detection device of silk-screen lines, including：Extraction is single
Member, for extracting silk-screen lines to be detected from the panel zone in product image；Processing unit, for using different corrosion
Kernel value carries out corrosion treatment to the silk-screen lines to be detected, obtains the silk-screen lines after corrosion treatment；Determination unit,
For the quantity by the silk-screen lines after the statistics corrosion treatment, to determine that the silk-screen lines to be detected whether there is
Defect, wherein the defect includes at least one following：Defect and burr.
Further, in the case where the corrosion treatment is that constriction is handled, the processing unit includes：Constriction handles mould
Block obtains constriction line for carrying out the constriction processing to the silk-screen lines to be detected using the first corrosion kernel value
The silk-screen lines of width, wherein if detecting the constriction treated that silk-screen lines are off, determine described in
There are the defects for silk-screen lines to be detected.
Further, the constriction processing module includes：First determination sub-module, if treated for the constriction
The quantity of silk-screen lines is more than first threshold, determines the constriction treated that silk-screen lines are off.
Further, the constriction processing is carried out to the silk-screen lines to be detected in the horizontal and/or vertical.
Further, described device further includes：First statistic unit, for counting the silk-screen to be detected extracted
The quantity of lines；First execution unit, if the quantity for the silk-screen lines to be detected is less than or equal to second threshold,
It executes and the step of constriction is handled is carried out to the silk-screen lines to be detected；Second execution unit, if waited for for described
The quantity of the silk-screen lines of detection is more than second threshold, determines that there are defect and/or burrs for the silk-screen lines to be detected.
Further, in the case where the corrosion treatment is to corrode the silk-screen lines completely, the processing unit packet
It includes：Full corrosion module, for corroding kernel value to the silk-screen lines to be detected in horizontal and/or vertical using second
Upper increase corroded area obtains grayscale morphologic and corrodes complete region；Wherein, if the grayscale morphologic corrodes complete region
Also detect silk-screen lines, it is determined that there are the burrs for the silk-screen lines to be detected.
Further, the full corrosion module includes：Second statistic submodule is located at grayscale morphologic corruption for counting
Lose the quantity of the silk-screen lines in complete region；Third implementation sub-module, if for quantity be more than second threshold, determine described in
Grayscale morphologic corrodes complete region, and there is also silk-screen lines.
Further, described device further includes：Determination unit, for be checked from the panel zone extraction in product image
It is based on image template before the silk-screen lines of survey, determines the panel zone in the product image；Searching unit, for searching
The interference image in panel zone is stated, determines background area to be shielded；Acquiring unit, for by shielding the background area
Domain obtains the region where the silk-screen lines.
In embodiments of the present invention, by the way of carrying out corrosion treatment to silk-screen lines, by from product image
Panel zone extracts silk-screen lines to be detected；Using different corrosion kernel values, the silk-screen lines to be detected are carried out
Corrosion treatment obtains the silk-screen lines after corrosion treatment；By the quantity of the silk-screen lines after the statistics corrosion treatment, come true
The fixed silk-screen lines to be detected whether there is defect, wherein the defect includes at least one following：Defect and burr,
The accuracy for improving detection silk-screen lines is achieved the purpose that, to realize automatic fast and accurately detection silk-screen line defect
Technique effect, and then solve in the prior art, since silk-screen line size is tiny, silk-screen lines detected using slide calliper rule
Whether defective method, the technical problem of testing result inaccuracy can be caused.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of the detection method of silk-screen lines according to the ... of the embodiment of the present invention；
Fig. 2 is the schematic diagram of the detection method of optional silk-screen lines according to embodiments of the present invention；
Fig. 3 is the schematic diagram one in silk-screen lines detection process according to the ... of the embodiment of the present invention；
Fig. 4 is the schematic diagram two in silk-screen lines detection process according to the ... of the embodiment of the present invention；
Fig. 5 is the schematic diagram three in silk-screen lines detection process according to the ... of the embodiment of the present invention；
Fig. 6 is the schematic diagram four in silk-screen lines detection process according to the ... of the embodiment of the present invention；
Fig. 7 is the schematic diagram five in silk-screen lines detection process according to the ... of the embodiment of the present invention；
Fig. 8 is the schematic diagram six in silk-screen lines detection process according to the ... of the embodiment of the present invention；And
Fig. 9 is the schematic diagram of the detection method processing unit of silk-screen lines according to the ... of the embodiment of the present invention.
Specific implementation mode
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model that the present invention protects
It encloses.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
It includes to be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment to cover non-exclusive
Those of clearly list step or unit, but may include not listing clearly or for these processes, method, product
Or the other steps or unit that equipment is intrinsic.
According to embodiments of the present invention, a kind of embodiment of the method for the detection of silk-screen lines is provided, it should be noted that
The step of flow of attached drawing illustrates can execute in the computer system of such as a group of computer-executable instructions, also,
It, in some cases, can be with different from shown in sequence execution herein although logical order is shown in flow charts
The step of going out or describing.
Fig. 1 is the detection method of silk-screen lines according to the ... of the embodiment of the present invention, as shown in Figure 1, this method includes following step
Suddenly：
Step S102 extracts silk-screen lines to be detected from the panel zone in product image.
Above-mentioned product image can be for the image of air-conditioning manual operator, on the control panel in order to detect air-conditioning manual operator
Silk-screen lines whether there is defect, and in the embodiment of the present application, the panel zone extraction from the image of air-conditioning manual operator is to be detected
Silk-screen lines.
Optionally, in the detection method of silk-screen lines provided by the embodiments of the present application, from the panel in product image
Before extracted region silk-screen lines to be detected, method further includes：Based on image template, the panel area in product image is determined
Domain；The interference image in panel zone is searched, determines background area to be shielded；By shielding background area, silk-screen line is obtained
Region where item.
Above-mentioned interference image can be the image of the liquid crystal display on air-conditioning manual operator, by by liquid crystal display
Image is shielded, and the region where silk-screen lines to be detected on air-conditioning manual operator is obtained, in silk-screen lines institute to be detected
Region extract silk-screen lines to be detected, to improve the speed for extracting silk-screen lines to be detected from panel zone
Degree and accuracy.
Above-mentioned interference image may be product logo images on air-conditioning manual operator, by by the image of product logo into
Row shielding, obtains the region where silk-screen lines to be detected on air-conditioning manual operator, the area where silk-screen lines to be detected
Domain extracts silk-screen lines to be detected, to improve the speed and standard of extracting silk-screen lines to be detected from panel zone
Exactness.
For example, the panel zone of manual operator product is found and extracted by image template first, then in this panel zone
It is interior to be carried out searching the background interferences objects such as product surface silk-screen font, liquid crystal display with trained template, it scratches and removes these backgrounds
These background areas are shielded to fill for 255 white with gray scale, by the area in panel zone in addition to the background area of shielding
It is extracted from the region where silk-screen lines as the region where silk-screen lines and needs the color detected is dark not to be closed in domain
Lines, namely extract silk-screen lines to be detected.
Further, above-mentioned product image is not limited only to the image of air-conditioning manual operator, wherein further including for example：TV
Machine, the image of computer monitor, the image etc. of circuit board, as long as needing the production for being designed into the detection of silk-screen lines on Related product
Product may be applicable to the detection method of silk-screen lines provided by the embodiments of the present application.
Step S104 is carried out corrosion treatment to silk-screen lines to be detected, is corroded using different corrosion kernel values
Treated silk-screen lines；
It should be noted that above-mentioned corrosion kernel value can be determined according to the width of silk-screen lines to be detected,
For the silk-screen lines of different in width, corrosion treatment is carried out using different corrosion kernel values, for the silk-screen line of same width
Item also carries out corrosion treatment using different corrosion kernel values.
Namely corrosion treatment is carried out to silk-screen lines to be detected using different corrosion kernel values, obtain different corrosion
Treated as a result, going to judge that silk-screen lines whether there is defect based on different results, to ensure that silk to be detected
Print the accuracy of lines detection.
Step S106, by counting the quantity of the silk-screen lines after corrosion treatment, to determine that silk-screen lines to be detected are
No existing defects, wherein defect includes at least one following：Defect and burr.
S102 to step S106 through the above steps counts the quantity of the silk-screen lines after corrosion treatment, based at corrosion
The quantity of silk-screen lines after reason determines that silk-screen lines to be detected whether there is defect, to avoid artificial visual detection
The defect of silk-screen lines improves the accuracy of detection silk-screen lines.
In the detection method of silk-screen lines provided by the embodiments of the present application, by being carried from the panel zone in product image
Take silk-screen lines to be detected；Using different corrosion kernel values, corrosion treatment is carried out to silk-screen lines to be detected, obtains corruption
Erosion treated silk-screen lines；By the quantity of the silk-screen lines after statistics corrosion treatment, to determine silk-screen lines to be detected
With the presence or absence of defect, wherein defect includes at least one following：Defect and burr have reached the standard for improving detection silk-screen lines
The purpose of exactness to realize the technique effect of automatic fast and accurately detection silk-screen line defect, and then solves existing
In technology, since silk-screen line size is tiny, the whether defective method of silk-screen lines is detected using slide calliper rule, can cause to examine
Survey the technical problem of result inaccuracy.
Optionally, it is constriction processing in corrosion treatment in the detection method of silk-screen lines provided by the embodiments of the present application
In the case of, corrosion treatment is carried out to silk-screen lines to be detected, obtains the silk-screen lines after corrosion treatment, including：Use
One corrosion kernel value carries out constriction processing to silk-screen lines to be detected, obtains the silk-screen lines of constriction line thickness；Wherein,
If detecting constriction treated that silk-screen lines are off, determine that there are defects for silk-screen lines to be detected.
For example, there was only the 0.2mm detections below for not being closed lines to some width, when corrosion treatment is constriction processing
In the case of, constriction processing is carried out to silk-screen lines degree of progress, the corrosion kernel value used is 17X17 (corresponding the first above-mentioned corruption
Lose kernel value), the use of corrosion kernel value is that 17X17 carries out constriction processing to silk-screen lines to be detected, obtains constriction lines
The silk-screen lines of width.If detecting constriction treated that silk-screen lines are off, silk-screen line to be detected is determined
There are defects for item.
Specifically, in the detection method of silk-screen lines provided by the embodiments of the present application, detection constriction treated silk-screen
Lines be off including：If the quantity of constriction treated silk-screen lines is more than first threshold, determine that constriction is handled
Silk-screen lines afterwards are off.
Wherein, when the quantity of constriction treated silk-screen lines is one, it may be determined that silk-screen provided by the embodiments of the present application
Lines do not have defect, whereas if the lines number that silk-screen lines provided by the embodiments of the present application after constriction is handled, obtain
When more than one, it may be determined that the silk-screen lines that application embodiment provides are off.
Optionally, in the detection method of silk-screen lines provided by the embodiments of the present application, in the horizontal and/or vertical
Constriction processing is carried out to silk-screen lines to be detected.
It is handled wherein it is possible to carry out the constriction in horizontal direction to silk-screen lines provided by the embodiments of the present application, it can also
Constriction processing in vertical direction is carried out to silk-screen lines provided by the embodiments of the present application, the embodiment of the present application can also be provided
Silk-screen lines be carried out at the same time the constriction on vertically and horizontally processing.
Optionally, in the detection method of silk-screen lines provided by the embodiments of the present application, the first corrosion kernel value is being used
Constriction processing is carried out to silk-screen lines to be detected, before obtaining the silk-screen lines of constriction line thickness, method further includes：System
Count the quantity of the silk-screen lines to be detected extracted；If the quantity of silk-screen lines to be detected is second threshold, execute
The step of constriction processing is carried out to silk-screen lines to be detected；Otherwise, it determines there are defect and/or hairs for silk-screen lines to be detected
Thorn.
In the above scheme, blob analytic approach may be used and detect whether silk-screen lines to be detected are only one (corresponding
Above-mentioned second threshold), if silk-screen lines to be detected are one, execute and silk-screen lines to be detected are carried out at constriction
Otherwise reason judges that the panel where silk-screen lines have fracture or silk-screen lines has if silk-screen lines to be detected are not one
Impurity.
Optionally, it is corrosion completely in corrosion treatment in the detection method of silk-screen lines provided by the embodiments of the present application
In the case of silk-screen lines, corrosion treatment is carried out to silk-screen lines to be detected, obtains the silk-screen lines after corrosion treatment, is wrapped
It includes：Corroded area is increased in the horizontal and/or vertical to silk-screen lines to be detected using the second corrosion kernel value, is obtained
Grayscale morphologic corrodes complete region；Wherein, if grayscale morphologic, which corrodes complete region, also detects silk-screen lines, it is determined that
There are burrs for silk-screen lines to be detected.
For example, there was only the 0.2mm detections below for not being closed lines to some width, when corrosion treatment is at complete corrosion
In the case of reason, complete corrosion treatment is carried out to silk-screen lines degree of progress, the corrosion kernel value used is that (correspondence is above-mentioned by 25X25
The second corrosion kernel value), the use of corrosion kernel value is that 25X25 carries out complete corrosion treatment to silk-screen lines to be detected, obtains
Corrode complete region to grayscale morphologic, if grayscale morphologic, which corrodes complete region, also detects silk-screen lines, it is determined that wait for
There are burrs for the silk-screen lines of detection.
Optionally, in the detection method of silk-screen lines provided by the embodiments of the present application, detection grayscale morphologic corrosion is complete
The silk-screen lines in region include：Statistics is located at the quantity that grayscale morphologic corrodes the silk-screen lines in complete region；If quantity
More than second threshold, determine that there is also silk-screen lines in grayscale morphologic corrosion complete region.
Corrode the quantity of the silk-screen lines in complete region with blob analytic approach analysis grayscale morphologic, if silk-screen lines
Quantity is 0 (corresponding above-mentioned second threshold), then it is assumed that silk-screen lines do not have defect, if the quantity of silk-screen lines is not 0, recognize
For silk-screen lines, there are burrs namely silk-screen lines existing defects.
Fig. 2 is the schematic diagram of the detection method of optional silk-screen lines according to embodiments of the present invention, as shown in Fig. 2, to clapping
According to good picture by plucking out the jamming patterns such as liquid crystal display and logo, whether only with blob analytic approach detection silk-screen lines
It it is one, otherwise wire fractures or panel have impurity, in the case where silk-screen lines are one, with the corrosion in gray scale morphology
Kernel 17X17 carries out corrosion treatment, and normal line thickness only constriction does not disconnect, is using blob analytic approach detection number
1, otherwise silk-screen lines have defect.With the corrosion kernel 25X25 processing in gray scale morphology, silk-screen lines just disappear, blob
Analytic approach looks for number of lines, and number is zero under normal circumstances, and otherwise lines are jagged.If silk-screen lines have defect or burr to think
Silk-screen lines existing defects.
Detailed process as shown in Figures 3 to 8 takes pictures to manual operator product, and the picture taken pictures first is looked for by template
To and extract the panel zone of manual operator product, obtain image as shown in Figure 3, then with trained in this panel zone
Template carries out searching the background interferences objects such as product surface silk-screen font, liquid crystal display, scratches and removes these jamming patterns and use gray scale
Shield these regions for 255 white to fill, extraction need the color that detects it is dark be not closed lines, as shown in Figure 4.By
Apparent in such product objective lines and background panel difference, the grey scale change between different product is smaller, and it is relatively accurate to find
Target lines and background panel intersection pixel value, therefore can use hard -threshold (fixed threshold) method image segmentation
Target lines and background panel are opened, detects whether existing lines quantity is 1 using blob analyzing detecting methods, if it is
Next step detection is carried out, otherwise shows silk-screen wire fractures or jagged, as shown in Figure 5.Then it executes in gray scale morphology
Corrosion treatment operation finds suitable corrosion kernel value with the presence or absence of incompleteness to detect silk-screen lines with etch, and constriction is whole
The width of silk-screen lines, then lines quantity is analyzed with blob analytic approach, normal silk-screen lines constriction width, quantity
It is still 1, otherwise silk-screen lines exist incomplete bad, as shown in Figure 6.It then continues to execute the etching operation in gray scale morphology
It whether there is burr to detect silk-screen lines, with etch, while increasing in horizontal and vertical corrosion check figure to just completely
Lines are corroded, then blob analytic approach are used to analyze lines quantity, quantity is 0 under normal circumstances, otherwise shows that lines exist
Burr is bad, as shown in Figure 7.For testing result as shown in Fig. 8 object detection results figures, intermediate gap is silk-screen lines defect
Place.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
The embodiment of the present application also provides a kind of detection devices of silk-screen lines, it should be noted that the embodiment of the present application
The detection devices of silk-screen lines can be used for executing the detection method for silk-screen lines that is provided of the embodiment of the present application.With
Under the detection device of silk-screen lines provided by the embodiments of the present application is introduced.
Fig. 9 is the schematic diagram according to the detection device of the silk-screen lines of the embodiment of the present application.As shown in figure 9, the device packet
It includes：Extraction unit 10, processing unit 20 and determination unit 30.
Specifically, extraction unit 10, for extracting silk-screen lines to be detected from the panel zone in product image；
Processing unit 20 carries out corrosion treatment to silk-screen lines to be detected, obtains for using different corrosion kernel values
Silk-screen lines after to corrosion treatment；
Determination unit 30, for the quantity by the silk-screen lines after statistics corrosion treatment, to determine silk-screen to be detected
Lines whether there is defect, wherein defect includes at least one following：Defect and burr.
In the detection method of silk-screen lines provided by the embodiments of the present application, by extraction unit 10 from product image
Panel zone extracts silk-screen lines to be detected；Processing unit 20 uses different corrosion kernel values, to silk-screen line to be detected
Item carries out corrosion treatment, obtains the silk-screen lines after corrosion treatment；Determination unit 30 passes through the silk-screen line after counting corrosion treatment
The quantity of item, to determine that silk-screen lines to be detected whether there is defect, wherein defect includes at least one following：Defect and
Burr has achieved the purpose that the accuracy for improving detection silk-screen lines, to realize automatic fast and accurately detection silk-screen line
The technique effect of strip defect, and then solve in the prior art, since silk-screen line size is tiny, silk is detected using slide calliper rule
The whether defective method of lines is printed, the technical problem of testing result inaccuracy can be caused.
Optionally, it is constriction processing in corrosion treatment in the detection device of silk-screen lines provided by the embodiments of the present application
In the case of, processing unit includes：Constriction processing module, for using first corrosion kernel value to silk-screen lines to be detected into
The processing of row constriction, obtains the silk-screen lines of constriction line thickness, wherein if detecting constriction treated at silk-screen lines
In off-state, determine that there are defects for silk-screen lines to be detected.
Optionally, in the detection device of silk-screen lines provided by the embodiments of the present application, constriction processing module includes：First
Determination sub-module determines constriction treated silk if the quantity for constriction treated silk-screen lines is more than first threshold
Print lines are off.
Optionally, in the detection device of silk-screen lines provided by the embodiments of the present application, in the horizontal and/or vertical
Constriction processing is carried out to silk-screen lines to be detected.
Optionally, in the detection device of silk-screen lines provided by the embodiments of the present application, device further includes：
First statistic unit, the quantity for counting the silk-screen lines to be detected extracted；First execution unit, is used for
If the quantity of silk-screen lines to be detected is less than or equal to second threshold, executes and silk-screen lines to be detected are carried out at constriction
The step of reason；Second execution unit determines to be detected if the quantity for silk-screen lines to be detected is more than second threshold
There are defect and/or burrs for silk-screen lines.
Optionally, it is corrosion completely in corrosion treatment in the detection device of silk-screen lines provided by the embodiments of the present application
In the case of silk-screen lines, processing unit includes：Full corrosion module, for corroding kernel value to silk-screen to be detected using second
Lines increase corroded area in the horizontal and/or vertical, obtain grayscale morphologic and corrode complete region；Wherein, if it is grey
The complete region of degree morphological erosion also detects silk-screen lines, it is determined that there are burrs for silk-screen lines to be detected.
Optionally, in the detection device of silk-screen lines provided by the embodiments of the present application, full module of corroding includes：Second system
Submodule is counted, for counting the quantity for being located at the silk-screen lines that grayscale morphologic corrodes complete region；Third implementation sub-module is used
If being more than second threshold in quantity, determine that there is also silk-screen lines in grayscale morphologic corrosion complete region.
Optionally, in the detection device of silk-screen lines provided by the embodiments of the present application, device further includes：Determination unit,
For being based on image template before extracting silk-screen lines to be detected in the panel zone from product image, product image is determined
On panel zone；Searching unit determines background area to be shielded for searching the interference image in panel zone；It obtains
Unit, for by shielding background area, obtaining the region where silk-screen lines.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
In the above embodiment of the present invention, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, for example, the unit division, Ke Yiwei
A kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
It connects, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
On unit.Some or all of unit therein can be selected according to the actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can to store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (16)
1. a kind of detection method of silk-screen lines, which is characterized in that including：
Silk-screen lines to be detected are extracted from the panel zone in product image；
Corrosion treatment is carried out to the silk-screen lines to be detected using different corrosion kernel values, obtains the silk after corrosion treatment
Print lines；
By the quantity of the silk-screen lines after the statistics corrosion treatment, to determine that the silk-screen lines to be detected whether there is
Defect, wherein the defect includes at least one following：Defect and burr.
2. according to the method described in claim 1, it is characterized in that, the corrosion treatment be constriction handle in the case of, it is right
The silk-screen lines to be detected carry out corrosion treatment, obtain the silk-screen lines after corrosion treatment, including：
The constriction processing is carried out to the silk-screen lines to be detected using the first corrosion kernel value, it is wide to obtain constriction lines
The silk-screen lines of degree；
Wherein, if detecting the constriction treated that silk-screen lines are off, the silk-screen to be detected is determined
There are the defects for lines.
3. according to the method described in claim 2, being disconnected it is characterized in that, detecting the constriction treated silk-screen lines and be in
State includes：
If the quantity of the constriction treated silk-screen lines is more than first threshold, the constriction is determined treated silk-screen line
Item is off.
4. according to the method described in claim 2, it is characterized in that, in the horizontal and/or vertical to described to be detected
Silk-screen lines carry out the constriction processing.
5. according to the method described in claim 2, it is characterized in that, corroding kernel value to the silk to be detected using first
It prints lines and carries out the constriction processing, before obtaining the silk-screen lines of constriction line thickness, the method further includes：
Count the quantity of the silk-screen lines to be detected extracted；
If the quantity of the silk-screen lines to be detected is second threshold, executes and the silk-screen lines to be detected are carried out
The step of constriction processing；
Otherwise, it determines there are defect and/or burrs for the silk-screen lines to be detected.
6. according to the method described in claim 1, it is characterized in that, being to corrode the silk-screen lines completely in the corrosion treatment
In the case of, corrosion treatment is carried out to the silk-screen lines to be detected, obtains the silk-screen lines after corrosion treatment, including：
Erosional surface is increased in the horizontal and/or vertical to the silk-screen lines to be detected using the second corrosion kernel value
Product obtains grayscale morphologic and corrodes complete region；
Wherein, if the grayscale morphologic, which corrodes complete region, also detects silk-screen lines, it is determined that the silk to be detected
Printing lines, there are the burrs.
7. according to the method described in claim 6, it is characterized in that, detecting the silk-screen that the grayscale morphologic corrodes complete region
Lines include：
Statistics is located at the quantity that the grayscale morphologic corrodes the silk-screen lines in complete region；
If quantity is more than second threshold, determine that there is also silk-screen lines in the grayscale morphologic corrosion complete region.
8. method as claimed in any of claims 1 to 7, which is characterized in that from the panel area in product image
Before silk-screen lines to be detected are extracted in domain, the method further includes：
Based on image template, the panel zone in the product image is determined；
The interference image in the panel zone is searched, determines background area to be shielded；
By shielding the background area, the region where the silk-screen lines is obtained.
9. a kind of detection device of silk-screen lines, which is characterized in that including：
Extraction unit, for extracting silk-screen lines to be detected from the panel zone in product image；
Processing unit carries out corrosion treatment to the silk-screen lines to be detected, obtains for using different corrosion kernel values
Silk-screen lines after corrosion treatment；
Determination unit, for the quantity by the silk-screen lines after the statistics corrosion treatment, to determine the silk to be detected
It prints lines and whether there is defect, wherein the defect includes at least one following：Defect and burr.
10. device according to claim 9, which is characterized in that in the case where the corrosion treatment is that constriction is handled, institute
Stating processing unit includes：
Constriction processing module, for being carried out at the constriction to the silk-screen lines to be detected using the first corrosion kernel value
Reason, obtains the silk-screen lines of constriction line thickness,
Wherein, if detecting the constriction treated that silk-screen lines are off, the silk-screen to be detected is determined
There are the defects for lines.
11. device according to claim 10, which is characterized in that the constriction processing module includes：
First determination sub-module determines institute if the quantity for the constriction treated silk-screen lines is more than first threshold
State constriction treated that silk-screen lines are off.
12. device according to claim 10, which is characterized in that in the horizontal and/or vertical to described to be detected
Silk-screen lines carry out the constriction processing.
13. device according to claim 10, which is characterized in that described device further includes：
First statistic unit, the quantity for counting the silk-screen lines to be detected extracted；
First execution unit, if the quantity for the silk-screen lines to be detected is less than or equal to second threshold, execution pair
The silk-screen lines to be detected carry out the step of constriction processing；
Second execution unit determines described to be checked if the quantity for the silk-screen lines to be detected is more than second threshold
There are defect and/or burrs for the silk-screen lines of survey.
14. device according to claim 9, which is characterized in that the corrosion treatment be corrode the silk-screen line completely
In the case of item, the processing unit includes：
Full corrosion module, for corroding kernel value to the silk-screen lines to be detected in horizontal and/or Vertical Square using second
Increase corroded area upwards, obtains grayscale morphologic and corrode complete region；
Wherein, if the grayscale morphologic, which corrodes complete region, also detects silk-screen lines, it is determined that the silk to be detected
Printing lines, there are the burrs.
15. device according to claim 14, which is characterized in that the full corrosion module includes：
Second statistic submodule, for counting the quantity for being located at the silk-screen lines that the grayscale morphologic corrodes complete region；
Third implementation sub-module determines that the grayscale morphologic corrodes complete region also if being more than second threshold for quantity
There are silk-screen lines.
16. the device according to any one of claim 9 to 15, which is characterized in that described device further includes：
Determination unit, for being based on image mould before extracting silk-screen lines to be detected in the panel zone from product image
Plate determines the panel zone in the product image；
Searching unit determines background area to be shielded for searching the interference image in the panel zone；
Acquiring unit, for by shielding the background area, obtaining the region where the silk-screen lines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810772238.4A CN108776146B (en) | 2018-07-13 | 2018-07-13 | Method and device for detecting silk-screen lines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810772238.4A CN108776146B (en) | 2018-07-13 | 2018-07-13 | Method and device for detecting silk-screen lines |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108776146A true CN108776146A (en) | 2018-11-09 |
| CN108776146B CN108776146B (en) | 2021-02-26 |
Family
ID=64029838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810772238.4A Active CN108776146B (en) | 2018-07-13 | 2018-07-13 | Method and device for detecting silk-screen lines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108776146B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110018169A (en) * | 2019-04-10 | 2019-07-16 | 珠海格力智能装备有限公司 | Detection method and device for silk-screen lines, storage medium and processor |
| CN118898781A (en) * | 2024-07-19 | 2024-11-05 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Cable loosening identification method based on data processing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6687396B1 (en) * | 1998-07-29 | 2004-02-03 | Pentax Corporation | Optical member inspection apparatus, image-processing apparatus, image-processing method, and computer readable medium |
| CN103018261A (en) * | 2012-11-29 | 2013-04-03 | 华中科技大学 | Appearance fault detecting system and appearance fault detecting method of RFID (Radio Frequency Identification Device) antenna |
| CN103500459A (en) * | 2013-09-24 | 2014-01-08 | 华南理工大学 | Printed circuit board defect detecting method based on regularization parameters |
| CN104280406A (en) * | 2014-09-16 | 2015-01-14 | 中国科学院广州能源研究所 | Machine vision system for detecting surface defects of copper part |
| CN106296636A (en) * | 2015-06-02 | 2017-01-04 | 征图新视（江苏）科技有限公司 | The detection method of printing image and detection device |
| CN107543828A (en) * | 2017-08-25 | 2018-01-05 | 广东工业大学 | A kind of Surface Flaw Detection method and system |
-
2018
- 2018-07-13 CN CN201810772238.4A patent/CN108776146B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6687396B1 (en) * | 1998-07-29 | 2004-02-03 | Pentax Corporation | Optical member inspection apparatus, image-processing apparatus, image-processing method, and computer readable medium |
| CN103018261A (en) * | 2012-11-29 | 2013-04-03 | 华中科技大学 | Appearance fault detecting system and appearance fault detecting method of RFID (Radio Frequency Identification Device) antenna |
| CN103500459A (en) * | 2013-09-24 | 2014-01-08 | 华南理工大学 | Printed circuit board defect detecting method based on regularization parameters |
| CN104280406A (en) * | 2014-09-16 | 2015-01-14 | 中国科学院广州能源研究所 | Machine vision system for detecting surface defects of copper part |
| CN106296636A (en) * | 2015-06-02 | 2017-01-04 | 征图新视（江苏）科技有限公司 | The detection method of printing image and detection device |
| CN107543828A (en) * | 2017-08-25 | 2018-01-05 | 广东工业大学 | A kind of Surface Flaw Detection method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110018169A (en) * | 2019-04-10 | 2019-07-16 | 珠海格力智能装备有限公司 | Detection method and device for silk-screen lines, storage medium and processor |
| CN110018169B (en) * | 2019-04-10 | 2022-01-28 | 珠海格力智能装备有限公司 | Detection method and device for silk-screen lines, storage medium and processor |
| CN118898781A (en) * | 2024-07-19 | 2024-11-05 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Cable loosening identification method based on data processing |
| CN118898781B (en) * | 2024-07-19 | 2025-02-07 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Cable loosening identification method based on data processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108776146B (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349145B (en) | Defect detection method, defect detection device, electronic equipment and storage medium | |
| JP4095860B2 (en) | Defect inspection method and apparatus | |
| CN111047655B (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
| CN117798087B (en) | Visual sorting system and terminal for lithium battery based on appearance defect detection | |
| CN113850749B (en) | Method for training defect detector | |
| CN113111903B (en) | Intelligent production line monitoring system and monitoring method | |
| CN110533654A (en) | The method for detecting abnormality and device of components | |
| CN109285140A (en) | A kind of printed circuit board image registration evaluation method | |
| CN108802052A (en) | A kind of detecting system and its detection method about slide fastener defect | |
| CN117474924B (en) | Label defect detection method based on machine vision | |
| CN115947066A (en) | Belt tearing detection method, device and system | |
| CN108776146A (en) | Method and device for detecting silk-screen lines | |
| CN113822836B (en) | Method for marking an image | |
| Lin et al. | Defect detection system for optical element surface based on machine vision | |
| CN105448095B (en) | Method and apparatus are surveyed in a kind of yellow mark car test | |
| CN114359115A (en) | Method for improving defect detection accuracy, computer equipment and readable medium | |
| CN111563869B (en) | Stain test method for quality inspection of camera module | |
| Islam et al. | Image processing techniques for quality inspection of gelatin capsules in pharmaceutical applications | |
| CN106204531A (en) | Noise and the method for marginal point in a kind of synchronous detecting coloured image | |
| Niskanen et al. | Experiments with SOM based inspection of wood | |
| CN113361444B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN111935480B (en) | Detection method for image acquisition device and related device | |
| JP7423368B2 (en) | Defect detection device and method | |
| Aydin et al. | A vision based inspection system using gaussian mixture model based interactive segmentation | |
| Jiang et al. | Research on defect detection technology of tablets in aluminum plastic package |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |