CN110148141B - Silk-screen optical filter small piece detection counting method and device - Google Patents
Silk-screen optical filter small piece detection counting method and device Download PDFInfo
- Publication number
- CN110148141B CN110148141B CN201910424843.7A CN201910424843A CN110148141B CN 110148141 B CN110148141 B CN 110148141B CN 201910424843 A CN201910424843 A CN 201910424843A CN 110148141 B CN110148141 B CN 110148141B
- Authority
- CN
- China
- Prior art keywords
- region
- screen
- silk
- counting
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 59
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000010191 image analysis Methods 0.000 claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 238000007650 screen-printing Methods 0.000 claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims abstract description 20
- 238000012634 optical imaging Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 241001270131 Agaricus moelleri Species 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000003628 erosive effect Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a detection and counting method and equipment for a silk-screen optical filter small piece, wherein the method comprises the steps of placing an optical filter to be detected on a tray of an object carrying device; the backlight device emits a beam of combined light beam to the optical filter; adjusting the focal length of the optical imaging device and the brightness of the backlight source device until the screen printing contour is clear and the edge is clear in a real-time optical filter picture presented in the image analysis and calculation system; and the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the screen printing outline, so that the number of good product chips in the optical filter is counted. Compared with counting equipment made by other factories in the industry, the method and the equipment for detecting and counting the silk-screen filter chips can automatically identify and count the number of the silk-screen filter chips on the tray without inputting the row and column numbers of the cutting chips in advance, and have the characteristics of stable and accurate counting, low error and high efficiency.
Description
Technical Field
The embodiment of the invention relates to the technical field of silk-screen filter small-chip counting, in particular to a silk-screen filter small-chip detection counting method and device.
Background
The optical filter (the IR/AR sheet covered on the surface of the sensor) in the mobile phone lens is usually cut by a whole optical filter middle sheet, the optical filter small sheet which can be cut by one middle sheet can reach tens to hundreds of sheets due to different sizes, then the four middle sheets are usually arranged into a ring after cracking and film expansion, then the small sheets of defective products can be marked in the form of manual coating points after inspection, and the number of good product sheets in the ring needs to be counted before shipment or transportation to the next process. The traditional manual detection scheme is used, so that the counting is slow and the constant is wrong, and therefore, an efficient and convenient optical filter chip counting scheme is necessary.
Disclosure of Invention
The invention provides a method and equipment for detecting and counting a silk-screen filter small piece, which are used for solving the defects in the prior art.
In order to achieve the above object, the present invention provides the following technical solutions:
in a first aspect, an embodiment of the present invention provides a method for detecting and counting a silk-screen filter patch, where the method is implemented by a silk-screen filter patch detecting and counting device, where the silk-screen filter patch detecting and counting device includes a carrying device, a backlight device, an optical image capturing device, and an image analysis and calculation system, where the backlight device is disposed below the carrying device, and the optical image capturing device is disposed above the carrying device and is disposed on the same vertical plane with the backlight device, and the method includes:
placing an optical filter to be detected on a tray of the carrying device;
the backlight device emits a beam of combined light beam to the optical filter;
adjusting the focal length of the optical imaging device and the brightness of the backlight source device until the screen printing contour is clear and the edge is clear in a real-time optical filter picture presented in the image analysis and calculation system;
and the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the screen printing outline, so that the number of good product chips in the optical filter is counted.
Further, in the method for detecting and counting the silk-screen filter chips, the combined light beam is formed by combining infrared light and white light;
the size and definition of the silk-screen outline are divided into the following three types:
firstly, the silk screen contour is moderate in size and clear in contour;
secondly, the screen printing contour is extra large or extra small but the internal contour is clear;
third, the screen printing has unclear inner and outer contours.
Further, in the method for detecting and counting the small pieces of the silk-screen optical filter, when the size condition and the definition degree of the silk-screen outline are the first, the image analysis and calculation system correspondingly selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the silk-screen outline, so that the step of counting the number of the small pieces of good products in the optical filter comprises the following steps:
the image analysis and calculation system extracts target area regions to be detected based on gray level and shape information, and opens a single thread for each target area Region to be detected;
calculating the average gray value Mean and variance detection of the G channel image in each Region of the target Region to be detected;
dividing each silk-screen Region Valid Region by dynamic threshold segmentation and morphological screening based on average gray value Mean and variance detection;
filling a silk-screen Region Valid Region, corroding a silk-screen part at the edge to obtain a corroded Region Erosion, calculating an average gray value Valid Mean for the corroded Region Erosion, filling all regions except the corroded Region Erosion with the average gray value Valid Mean, and highlighting all Mark points of the whole picture to obtain a Mark Region Mark;
traversing all silk-screen Region Valid regions, and marking the Region which does not intersect with Mark regions as an OK Region; one OK area corresponds to one good chip;
and counting the number of OK areas of all threads, thereby obtaining the number of good chips.
Further, in the method for detecting and counting the small pieces of the silk-screen optical filter, when the size condition and the definition degree of the silk-screen outline are the second type, the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the silk-screen outline, so that the step of counting the number of the small pieces of good products in the optical filter comprises the following steps:
the image analysis and calculation system extracts target area regions to be detected based on gray level and shape information, and opens a single thread for each target area Region to be detected;
carrying out sub-pixel segmentation and edge fitting on the G channel image in each target Region to be detected by using a Canny operator, and screening out Valid regions of the silk-screen Region;
filling a silk-screen Region Valid Region, corroding a silk-screen part at the edge to obtain a corroded Region Erosion, calculating an average gray value Valid Mean for the corroded Region Erosion, filling all regions except the corroded Region Erosion with the average gray value Valid Mean, and highlighting all Mark points of the whole picture to obtain a Mark Region Mark;
traversing all silk-screen Region Valid regions, and marking the Region which does not intersect with Mark regions as an OK Region; one OK area corresponds to one good chip;
and counting the number of OK areas of all threads, thereby obtaining the number of good chips.
Further, in the method for detecting and counting the small pieces of the silk-screen optical filter, when the size condition and the definition degree of the silk-screen outline are third, the corresponding image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the silk-screen outline, so that the step of counting the number of the small pieces of good products in the optical filter comprises the following steps:
the image analysis and calculation system extracts target area regions to be detected based on gray level and shape information, and opens a single thread for each target area Region to be detected;
performing Blob analysis on each Region of the target Region to be detected, performing sub-pixel segmentation and affine transformation, and primarily horizontally aligning an Image Trans to be processed;
extracting the upper, lower, left and right edges of the Image Trans by using a Canny operator, performing Projection transformation on polygons fitted by the four edges and orthogonal rectangles, and further obtaining an image_project for eliminating deformation;
carrying out Projection analysis in horizontal and vertical directions on gray scales in the image_project to obtain horizontal Projection Hor project and vertical Projection Vert project;
solving the most intense change position in the horizontal Projection Hor project and the vertical Projection Vert project, carrying out iterative measurement by using the position, eliminating the point with overlarge difference and keeping the point with uniform position;
fitting points with uniform positions into straight lines by using morphology and Blob analysis, cutting the image by using the fitted straight lines to obtain a plurality of rectangular areas, solving an Area average value Area Mean of the rectangular areas, and filtering out small and large areas by using the Area average value Area Mean to obtain real areas Valid regions of all the small pieces on the picture;
calculating an average gray value Valid Mean of the filter image in the real Region Valid Region, filling all incomplete or blank regions with the average gray value Valid Mean, and completely highlighting Mark points and silk-screen regions;
the screen printing area is corroded by using a circle with 4 pixels, then Gap areas Gap regions of all Mark points are found out by using blob analysis, each area in the real area Valid regions is traversed, and the area intersected with the Gap areas Gap regions and blank areas are removed, so that OK areas are obtained; one OK area corresponds to one good chip;
and counting the number of OK areas of all threads, thereby obtaining the number of good chips.
In a second aspect, an embodiment of the present invention provides a device for detecting and counting a silk-screen filter patch, which is configured to perform the method for detecting and counting a silk-screen filter patch according to the first aspect, where the device includes an object carrying device, a backlight device, an optical image capturing device, and an image analysis computing system; wherein,,
the object carrying device is used for carrying the optical filter to be detected;
the backlight source device is arranged below the object carrying device and is used for emitting a combined light beam to the optical filter;
the optical image capturing device is arranged above the object carrying device and is arranged on the same vertical plane with the backlight source device, and is used for capturing an image of the optical filter on the object carrying device and outputting a real-time optical filter picture to the image analysis and calculation system;
the image analysis and calculation system is used for receiving and processing the real-time optical filter pictures output by the optical imaging device and counting the number of good product chips in the optical filter.
Further, in the silk screen filter small chip detection counting device, the carrying device comprises a tray and a tray moving mechanism for realizing the pushing in or pulling out of the tray.
Further, in the silk screen filter small chip detection counting device, the backlight device comprises a light source formed by combining infrared light and white light, a control unit and a shell:
the light sources are coupled with the control unit and are all accommodated in the shell.
Further, in the silk-screen filter small-piece detection counting device, the optical imaging device comprises a CMOS industrial camera and a zoom lens matched with the CMOS industrial camera;
the CMOS industrial camera is electrically connected with the image analysis and calculation system;
the object distance of the zoom lens is larger than 10cm.
Further, in the silk screen filter small chip detection counting device, the image analysis and calculation system comprises image analysis and counting software and a display.
Compared with counting equipment made by other factories in the industry, the method and the equipment for detecting and counting the silk-screen filter chips can automatically identify and count the number of the silk-screen filter chips on the tray without inputting the row and column numbers of the cutting chips in advance, and have the characteristics of stable and accurate counting, low error and high efficiency.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for detecting and counting a silk-screen filter patch according to a first embodiment of the present invention;
fig. 2 is a flow chart of a method for detecting and counting a silk-screen filter patch according to a first embodiment of the present invention;
fig. 3 is a flow chart of a method for detecting and counting a silk-screen filter patch according to a first embodiment of the present invention;
fig. 4 is a flowchart of a method for detecting and counting a silk-screen filter die according to a first embodiment of the present invention;
FIG. 5 is a diagram showing the result of the screen printing according to the first embodiment of the invention;
FIG. 6 is a diagram showing the result of the second screen printing according to the first embodiment of the invention;
FIG. 7 is a diagram showing the result of counting when the size and definition of the screen printing profile are the third type in the first embodiment of the invention;
fig. 8 is a schematic structural diagram of a device for detecting and counting a silk-screen filter die according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Referring to fig. 1, a flow chart of a method for detecting and counting a silk screen filter patch according to a first embodiment of the present invention is provided, wherein the method is implemented by a device for detecting and counting a silk screen filter patch, the device for detecting and counting a silk screen filter patch comprises a carrying device, a backlight device, an optical imaging device and an image analysis and calculation system, the backlight device is disposed below the carrying device, and the optical imaging device is disposed above the carrying device and is disposed on the same vertical plane with the backlight device. The method specifically comprises the following steps:
s101, placing an optical filter to be detected on a tray of the carrying device;
s102, the backlight device emits a beam of combined light beam to the optical filter;
s103, adjusting the focal length of the optical imaging device and the brightness of the backlight source device until the screen printing contour is clear and the edge is clear in a real-time optical filter picture presented in the image analysis and calculation system;
s104, the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the screen printing outline, so that the number of good product chips in the optical filter is counted.
It should be noted that the segmentation detection algorithm is divided into three parts: dividing the optical filter, detecting Mark points and counting the number.
In this embodiment, the combined beam is formed by combining infrared light and white light; the size and definition of the silk-screen outline are divided into the following three types:
firstly, the silk screen contour is moderate in size and clear in contour; secondly, the screen printing contour is extra large or extra small but the internal contour is clear; third, the screen printing has unclear inner and outer contours.
As shown in fig. 2, preferably, when the size and definition of the screen print contour are the first, the step S104 further includes:
s201, the image analysis and calculation system extracts target area regions to be detected based on gray level and shape information, and opens a single thread for each target area Region to be detected;
s202, calculating an average gray value Mean and variance detection of the G channel image in each Region of the target Region to be detected;
s203, dividing each silk-screen Region Valid Region through dynamic threshold segmentation and morphological screening based on average gray value Mean and variance devision;
s204, filling a silk-screen Region Valid Region, corroding a silk-screen part at the edge to obtain a corroded Region Erosion, calculating an average gray value Valid Mean for the corroded Region Erosion, filling all regions except the corroded Region Erosion with the average gray value Valid Mean, and highlighting all Mark points of the whole picture to obtain a Mark Region Mark Region;
s205, traversing all screen printing area Valid regions, and marking the area which does not intersect with the Mark Region as an OK area; one OK area corresponds to one good chip;
s206, counting the number of OK areas of all threads, and thus obtaining the number of good chips.
As shown in fig. 3, preferably, when the size and definition of the screen print contour is the second type, the step S104 further includes:
s301, extracting target area regions to be detected based on gray level and shape information by the image analysis and calculation system, and opening a single thread for each target area Region to be detected;
s302, sub-pixel segmentation and edge fitting are carried out on the G channel image in each Region of the target Region to be detected by using a Canny operator (edge detection operator), and silk-screen Region Valid regions are screened out according to morphological characteristics such as certain rectangle degree, concave-convex degree and the like;
s303, filling a silk-screen Region Valid Region, corroding a silk-screen part at the edge to obtain a corroded Region Erosion, calculating an average gray value Valid Mean for the corroded Region Erosion, filling all regions except the corroded Region Erosion with the average gray value Valid Mean, and highlighting all Mark points of the whole picture to obtain a Mark Region Mark Region;
s304, traversing all screen printing area Valid regions, and marking the area which does not intersect with the Mark Region as an OK area; one OK area corresponds to one good chip;
s305, counting the number of OK areas of all threads, and thus obtaining the number of good chips.
As shown in fig. 4, preferably, when the size condition and the sharpness of the screen print contour are the third type, the step S104 further includes:
s401, extracting target area regions to be detected based on gray level and shape information by the image analysis and calculation system, and opening a single thread for each target area Region to be detected;
s402, performing Blob (connected domain) analysis on each Region of the target Region to be detected, performing sub-pixel segmentation and affine transformation, and primarily horizontally aligning an Image Trans to be processed;
s403, extracting four edges of an Image Trans, namely an upper edge, a lower edge, a left edge and a right edge by using a Canny operator, performing Projection transformation on a polygon fitted by the four edges and an orthogonal rectangle, and further obtaining an image_project for eliminating deformation;
s404, carrying out Projection analysis in horizontal and vertical directions on gray scales in the image_project to obtain horizontal Projection Hor project and vertical Projection Vert project;
s405, calculating the most intense change position in horizontal Projection Hor project and vertical Projection Vert project by utilizing mathematical means such as first derivative, second derivative and the like, and carrying out iterative measurement by using the position to exclude the point with overlarge difference and keep the point with uniform position;
s406, using morphology and Blob analysis to fit points with uniform positions into straight lines, then using the fitted straight line to cut images to obtain a plurality of rectangular areas, then solving the Area average value Area Mean of the rectangular areas, and using the Area average value Area Mean to filter out small and large areas to obtain real areas Valid regions of all the small pieces on the picture;
s407, calculating an average gray value Valid Mean of the filter image in the Valid Region of the real Region, filling all incomplete or blank regions with the average gray value Valid Mean, and completely highlighting black regions such as Mark points, silk-screen regions and the like;
s408, corroding the silk-screen Region by using a circle with 4 pixels, then using blob analysis to find out Gap regions of all Mark points, traversing each Region in the real Region Valid regions, and removing the Region intersected with the Gap regions and blank regions to obtain OK regions; one OK area corresponds to one good chip;
s409, counting the number of OK areas of all threads, thereby obtaining the number of good chips.
Compared with counting equipment made by other factories in the industry, the detection counting method for the silk-screen filter chips provided by the embodiment of the invention can automatically identify and count the number of the silk-screen filter chips on the tray without inputting the row and column numbers of the cutting chips in advance, and has the characteristics of stable and accurate counting, low error and high efficiency.
Example two
As shown in fig. 8, a second embodiment of the present invention provides a device for detecting and counting a silk-screen filter patch, which is used for executing the method for detecting and counting a silk-screen filter patch in the first embodiment, and the device includes a carrying device 10, a backlight device 20, an optical image capturing device 30 and an image analysis and calculation system 40; wherein,,
the carrying device 10 is used for carrying an optical filter to be detected;
the backlight device 20 is disposed below the carrying device 10, and is configured to emit a combined light beam to the optical filter;
the optical image capturing device 30 is disposed above the object carrying device 10 and is disposed on the same vertical plane as the backlight device 20, and is configured to capture an image of the optical filter on the object carrying device 10 and output a real-time optical filter frame to the image analysis computing system 40;
the image analysis and calculation system 40 is configured to receive and process the real-time filter frame output by the optical imaging device 30, and count the number of good chips in the filter.
Preferably, the carrying device 10 includes a tray and a tray moving mechanism for realizing the pushing in or pulling out of the tray.
Preferably, the backlight device 20 includes a light source composed of infrared light and white light, a control unit, and a housing:
the light sources are coupled with the control unit and are all accommodated in the shell.
Preferably, the optical image capturing device 30 includes a CMOS industrial camera with 1200 ten thousand pixels and a zoom lens matched with the CMOS industrial camera;
the CMOS industrial camera is electrically connected with the image analysis and calculation system 40;
the object distance of the zoom lens is larger than 10cm.
Preferably, the image analysis computing system 40 includes image analysis counting software and a display.
Preferably, the carrying device 10, the backlight device 20, the optical imaging device 30 and the image analysis and calculation system 40 are all arranged on a workbench;
the workbench comprises a base, a backlight source device supporting frame, a carrying device supporting frame and an optical image capturing device supporting frame;
the image analysis computing system 40 is embedded in the base;
the backlight source device support frame, the object carrying device support frame and the optical image capturing device support frame are sequentially fixed on the base from bottom to top.
In the concrete implementation, a CMOS industrial camera is installed, and the focal length of the zoom lens is directly adjusted to a positive infinity position, so that the longest depth of field and the best definition of a photo can be ensured; then a product is placed on the tray, the height of the camera is adjusted according to the size of the visual field, and the product is positioned at the center of the visual field of the camera and has proper size; after the camera position is fixed, taking out the product on the tray, and adjusting the lower combined light source in a proper mode to ensure that the lower combined light source and the CMOS industrial camera are completely in the same vertical plane, so as to ensure uniform brightness in the field of view of the CMOS industrial camera;
after the position of the combined light source is fixed, the brightness of the combined light source is regulated, the brightness of the combined light is regulated according to the actual condition of the site, generally, the gray scale value of white light of the combined light is about 210, and infrared light is additionally regulated according to the actual product, so that the small pieces on the optical filter can be uniformly separated by the infrared light;
after the brightness of the combined light source is regulated, a filter to be detected is placed on the tray, image analysis and counting software is opened, a real-time filter picture is entered, then the tray is pushed in lightly, the counting condition is observed, and the stable and accurate counting in the real-time filter picture is ensured.
Compared with counting equipment made by other factories in the industry, the silk-screen filter small-chip detection counting equipment provided by the embodiment of the invention can automatically identify and count the number of the silk-screen filter small chips on the tray without inputting the row and column numbers of the cutting chips in advance, and has the characteristics of stable and accurate counting, low error and high efficiency.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The method is characterized by being realized by a silk-screen filter small-chip detection counting device, the silk-screen filter small-chip detection counting device comprises a carrying device, a backlight device, an optical imaging device and an image analysis and calculation system, the backlight device is arranged below the carrying device, the optical imaging device is arranged above the carrying device and is arranged on the same vertical plane with the backlight device, and the method comprises the following steps:
placing an optical filter to be detected on a tray of the carrying device;
the backlight device emits a beam of combined light beam to the optical filter;
adjusting the focal length of the optical imaging device and the brightness of the backlight source device until the screen printing contour is clear and the edge is clear in a real-time optical filter picture presented in the image analysis and calculation system;
the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the screen printing outline, so that the number of good product chips in the optical filter is counted;
the combined beam is formed by combining infrared light and white light;
the size and definition of the screen printing outline are divided into the following three types:
firstly, the silk screen contour is moderate in size and clear in contour;
secondly, the screen printing contour is extra large or extra small but the internal contour is clear;
thirdly, the inner and outer contours of the silk screen printing are not clear;
when the size condition and the definition degree of the screen printing outline are the first, the corresponding image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size condition and the definition degree of the screen printing outline, so that the step of counting the number of good chips in the optical filter comprises the following steps:
the image analysis and calculation system extracts target areas to be detected region_1 based on gray level and shape information, and opens a single thread for each target area to be detected region_1;
calculating the average gray value Mean and variance detection of the G channel image in each target Region region_1 to be detected;
dividing each silk-screen Region Valid region_1 through dynamic threshold segmentation and morphological screening based on average gray value Mean and variance detection;
filling a silk-screen Region Valid region_1, corroding silk-screen parts at the edges to obtain a corroded Region Erosion_1, calculating an average gray value Valid mean_1 for the corroded Region Erosion_1, filling all regions except the corroded Region Erosion_1 with the average gray value Valid mean_1, and highlighting all Mark points of the whole picture to obtain a Mark Region Mark region_1;
traversing all screen printing areas Valid region_1, and marking the area which does not intersect with the Mark Region region_1 as an OK area; one OK area corresponds to one good chip;
and counting the number of OK areas of all threads, thereby obtaining the number of good chips.
2. The method of claim 1, wherein when the size and the definition of the screen outline are the second type, the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size and the definition of the screen outline, so as to count the number of good chips in the filter, the method comprises:
the image analysis and calculation system extracts target areas to be detected region_2 based on gray level and shape information, and opens a single thread for each target area to be detected region_2;
carrying out sub-pixel segmentation and edge fitting on the G channel image in each target Region region_2 to be detected by using a Canny operator, and screening out a screen printing Region Valid region_2;
filling a silk-screen Region Valid region_2, corroding silk-screen parts at the edges to obtain a corroded Region Erosion_2, calculating an average gray value Valid mean_2 for the corroded Region Erosion_2, filling all regions except the corroded Region Erosion_2 with the average gray value Valid mean_2, and highlighting all Mark points of the whole picture to obtain a Mark Region Mark region_2;
traversing all screen printing areas Valid region_2, and marking the area which does not intersect with the Mark Region region_2 as an OK area; one OK area corresponds to one good chip;
and counting the number of OK areas of all threads, thereby obtaining the number of good chips.
3. The method of claim 1, wherein when the size and the definition of the screen outline are third, the image analysis and calculation system selects a corresponding segmentation detection algorithm according to the size and the definition of the screen outline, so as to count the number of good chips in the filter, the method comprises:
the image analysis and calculation system extracts target areas to be detected region_3 based on gray level and shape information, and opens a single thread for each target area to be detected region_3;
performing Blob analysis on each Region region_3 of the target Region to be detected, performing sub-pixel segmentation and affine transformation, and primarily horizontally aligning an Image Trans to be processed;
extracting the upper, lower, left and right edges of the Image Trans by using a Canny operator, performing Projection transformation on polygons fitted by the four edges and orthogonal rectangles, and further obtaining an image_project for eliminating deformation;
carrying out Projection analysis in horizontal and vertical directions on gray scales in the image_project to obtain horizontal Projection Hor project and vertical Projection Vert project;
solving the most intense change position in the horizontal Projection Hor project and the vertical Projection Vert project, carrying out iterative measurement by using the position, eliminating the point with overlarge difference and keeping the point with uniform position;
fitting points with uniform positions into straight lines by using morphology and Blob analysis, cutting the image by using the fitted straight lines to obtain a plurality of rectangular areas, solving an Area average value Area Mean of the rectangular areas, and filtering out small and large areas by using the Area average value Area Mean to obtain a real Area Valid region_3 of all the small pieces on the picture;
calculating an average gray value Valid mean_3 of the filter image in the real Region Valid region_3, filling all incomplete or blank regions with the average gray value Valid mean_3, and completely highlighting Mark points and screen printing regions;
the screen printing area is corroded by using a circle with 4 pixels, then the Gap Region of all Mark points is found out by using blob analysis, each area in the real area Valid region_3 is traversed, and the area intersected with the Gap Region and the blank area are removed, so that an OK area is obtained; one OK area corresponds to one good chip;
and counting the number of OK areas of all threads, thereby obtaining the number of good chips.
4. A silk-screen filter small-chip detection counting device for executing the silk-screen filter small-chip detection counting method according to any one of claims 1-3, wherein the device comprises a carrying device, a backlight source device, an optical image capturing device and an image analysis computing system; wherein,,
the object carrying device is used for carrying the optical filter to be detected;
the backlight source device is arranged below the object carrying device and is used for emitting a combined light beam to the optical filter;
the optical image capturing device is arranged above the object carrying device and is arranged on the same vertical plane with the backlight source device, and is used for capturing an image of the optical filter on the object carrying device and outputting a real-time optical filter picture to the image analysis and calculation system;
the image analysis and calculation system is used for receiving and processing the real-time optical filter pictures output by the optical imaging device and counting the number of good product chips in the optical filter.
5. The silk screen filter die detection and counting apparatus of claim 4, wherein the carrier device comprises a tray and a tray moving mechanism for effecting the pushing in or out of the tray.
6. The silk screen filter die detection counting apparatus of claim 4, wherein the backlight device comprises a light source composed of infrared light and white light, a control unit, and a housing:
the light sources are coupled with the control unit and are all accommodated in the shell.
7. The silk-screen filter small piece detection counting device according to claim 4, wherein the optical imaging device comprises a CMOS industrial camera and a zoom lens matched with the CMOS industrial camera;
the CMOS industrial camera is electrically connected with the image analysis and calculation system;
the object distance of the zoom lens is larger than 10cm.
8. The silk screened filter die detection counting device of claim 4, wherein the image analysis computing system comprises image analysis counting software and a display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910424843.7A CN110148141B (en) | 2019-05-21 | 2019-05-21 | Silk-screen optical filter small piece detection counting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910424843.7A CN110148141B (en) | 2019-05-21 | 2019-05-21 | Silk-screen optical filter small piece detection counting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110148141A CN110148141A (en) | 2019-08-20 |
| CN110148141B true CN110148141B (en) | 2023-07-25 |
Family
ID=67592356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910424843.7A Active CN110148141B (en) | 2019-05-21 | 2019-05-21 | Silk-screen optical filter small piece detection counting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110148141B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562266A (en) * | 2020-05-19 | 2020-08-21 | 东莞市瑞图新智科技有限公司 | Package quality detection method and package quality detection device |
| CN112017207A (en) * | 2020-08-31 | 2020-12-01 | 浙江水晶光电科技股份有限公司 | Optical filter counting method and counting device |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08271436A (en) * | 1995-03-29 | 1996-10-18 | Sharp Corp | Inspection equipment for color filter substrate |
| JPH08292126A (en) * | 1995-04-24 | 1996-11-05 | Dainippon Printing Co Ltd | Inspection of color filter |
| JPH0972855A (en) * | 1995-09-06 | 1997-03-18 | Toray Ind Inc | Apparatus and method for measurement of light transmission distribution as well as manufacture of sheetlike object |
| JP3833229B2 (en) * | 2004-12-06 | 2006-10-11 | 大日本印刷株式会社 | Color sample inspection method |
| CN202021645U (en) * | 2011-03-07 | 2011-11-02 | 苏州鼎旺科技有限公司 | Counting device for optical communication optical filter |
| US9927369B2 (en) * | 2015-06-03 | 2018-03-27 | Materion Corporation | Automated defect detection and mapping for optical filters |
| CN106814083B (en) * | 2015-11-30 | 2020-01-10 | 宁波舜宇光电信息有限公司 | Filter defect detection system and detection method thereof |
| CN107014816A (en) * | 2016-01-27 | 2017-08-04 | 上海弘米智能科技有限公司 | A kind of fastener process line real-time quality detection method and system |
| CN108898563B (en) * | 2018-07-02 | 2021-01-22 | 京东方科技集团股份有限公司 | Processing method of optical detection image of display panel and computer readable medium |
-
2019
- 2019-05-21 CN CN201910424843.7A patent/CN110148141B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110148141A (en) | 2019-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11774735B2 (en) | System and method for performing automated analysis of air samples | |
| CN100367293C (en) | Method and apparatus for optical inspection of a display | |
| CN110189322B (en) | Flatness detection method, device, equipment, storage medium and system | |
| CN108562250B (en) | Keyboard keycap flatness rapid measurement method and device based on structured light imaging | |
| CN111025701B (en) | Curved surface liquid crystal screen detection method | |
| CN116559183B (en) | Method and system for improving defect judging efficiency | |
| CN110148141B (en) | Silk-screen optical filter small piece detection counting method and device | |
| CN109406527B (en) | System and method for detecting fine appearance defects of micro camera module lens | |
| CN110567976A (en) | mobile phone cover plate silk-screen defect detection device and detection method based on machine vision | |
| TWI512284B (en) | Bubble inspection system for glass | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN115880301A (en) | System for identifying bubble defects of glass substrate | |
| KR101876908B1 (en) | Enhancement method for location accuracy of display panel defect | |
| JP2010181328A (en) | Device, program and method for inspecting surface of solar battery wafer | |
| CN110596118A (en) | Print pattern detection method and print pattern detection device | |
| JP2005345290A (en) | Streak-like flaw detecting method and streak-like flaw detector | |
| CN112648920B (en) | Mask opening size measuring method, mask plate stretching device and screen expanding machine | |
| CN110136148B (en) | Method and equipment for detecting and counting small pieces without silk-screen optical filter | |
| CN111738936A (en) | Image processing-based multi-plant rice spike length measuring method | |
| WO2019176614A1 (en) | Image processing device, image processing method, and computer program | |
| CN116256366A (en) | Chip defect detection method, detection system and storage medium | |
| JP2013117490A (en) | Inspection system and method for setting recipe | |
| CN115984197A (en) | Defect detection method based on standard PCB image and related device | |
| CN110412056A (en) | A kind of vehicle-mounted glass molds group automatic optical detection method and device | |
| CN115598136A (en) | Detection apparatus for screen rubber coating quality |
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 |