CN113284148A - Screen dust filtering method - Google Patents
Screen dust filtering method Download PDFInfo
- Publication number
- CN113284148A CN113284148A CN202110834814.5A CN202110834814A CN113284148A CN 113284148 A CN113284148 A CN 113284148A CN 202110834814 A CN202110834814 A CN 202110834814A CN 113284148 A CN113284148 A CN 113284148A
- Authority
- CN
- China
- Prior art keywords
- image
- mask
- screen
- pixel
- stage
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 57
- 239000000428 dust Substances 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 238000002360 preparation method Methods 0.000 claims abstract description 4
- 238000005498 polishing Methods 0.000 claims description 30
- 230000007547 defect Effects 0.000 claims description 18
- 230000003628 erosive effect Effects 0.000 claims description 16
- 150000001875 compounds Chemical class 0.000 claims description 15
- 230000010339 dilation Effects 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 14
- 230000007797 corrosion Effects 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 8
- 206010070245 Foreign body Diseases 0.000 claims description 6
- 101100534231 Xenopus laevis src-b gene Proteins 0.000 claims description 6
- 238000011049 filling Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000011282 treatment Methods 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 241000760358 Enodes Species 0.000 claims description 3
- 229920002120 photoresistant polymer Polymers 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000008961 swelling Effects 0.000 claims 1
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 230000006872 improvement Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000000877 morphologic effect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a screen dust filtering method, which comprises the following steps: 1) the first stage, the preparation stage: providing a screen to be filtered, arranging at least one group of side light sources beside the upper surface of the screen to be filtered, and respectively arranging at least one group of image capturing units and backlight sources at the upper side and the lower side of the screen to be filtered; 2) the second stage, image acquisition stage: obtaining a single top-lighting image
With single underlying lighting image
，
=1,2,3…,n(ii) a 3) A third stage, an image processing stage: several single filtering masks
Integrating according to the second stage of segmentation rule to obtain the total filtering mask
. According to the invention, the method not only can distinguish and identify whether the dust foreign matters are on the upper surface or the lower surface of the screen, but also can distinguish and identify the dust foreign matters on the backlight source, and filters the dust foreign matters together, so that the steps are simple and convenient, the operation is easy, the detection time is saved, the detection precision is improved, the misjudgment rate is reduced, and the productivity is improved.
Description
Technical Field
The invention relates to the field of image defect detection, in particular to a screen dust filtering method.
Background
Today, with the rapid development of industrial technologies, electronic products of various sizes, models, types and structures are full of our daily lives, screens or display panels are more important indispensable components in electronic products, and the detection of screen defects is essential in the process from the production completion to the factory shipment of the screens or display panels. In the process of researching and realizing screen defect detection, researchers find that the screen detection method in the prior art has the following problems:
for the screen defect detection, manual detection is time-consuming and labor-consuming, so that most of the prior art detects the screen by using an automatic detection device (AOI) based on machine vision, and in the back-end process of the screen, dust in the production environment falls on the screen panel to cause the AOI to detect foreign matters such as dust and the like as defects, so that a large amount of misjudgments are caused, the defect rate of the screen is higher than the real level, and unnecessary rework and capacity waste of the screen are caused.
In view of the above, it is necessary to develop a screen dust filtering method to solve the above problems.
Disclosure of Invention
In order to overcome the problems of the dust filtering method, the invention provides a screen dust filtering method, which solves the problem that the backlight foreign matter and the lower foreign matter cannot be identified and filtered simultaneously in the traditional method, can distinguish and identify whether the dust foreign matter is on the upper surface or the lower surface of a screen, can distinguish and identify the dust foreign matter on the backlight, and filters the dust foreign matter together, and has the advantages of simple steps, easy operation, detection time saving, detection precision improvement, misjudgment rate reduction and capacity improvement.
As for the dust filtering method, the screen dust filtering method of the present invention for solving the above technical problems includes the steps of:
1) the first stage, the preparation stage:
providing a screen to be filtered, arranging at least one group of side light sources beside the upper surface of the screen to be filtered, and respectively arranging at least one group of image capturing units and backlight sources at the upper side and the lower side of the screen to be filtered;
2) the second stage, image acquisition stage:
positioning an ROI on a screen through a predetermined rule, generating ROI information, and segmenting the screen according to the ROI information to obtain at least one effective detection area, wherein each group of image capturing units is aligned with a corresponding effective detection area;
each group of image capturing units captures the upper surface of the corresponding effective detection area to obtain a single upper light-striking image in the states that the side light source is opened and the backlight source is closed
Or a single lower lighting image is obtained by capturing the lower surface of the corresponding effective detection area under the states of the side light source being closed, the screen being electrified and the backlight source being opened
，i=1,2,3…,n；
3) A third stage, an image processing stage:
an image preprocessing step: sequentially polishing the single sheet
And a single under-lighting image
Performing pretreatment to form single-piece upper-polishing foreign-matter masks
With single underlying foreign matter polishing mask
, i =1,2,3…,n；
Mask synthesis: make a single piece of foreign matter mask
With single underlying foreign matter polishing mask
Are combined to form a single filter mask
And a plurality of single filter masks are arranged
Integrating according to the second stage of segmentation rule to obtain the total filtering mask
Said total filtering mask
For filtering out dust in subsequent screen defect detection to prevent defect misjudgment, wherein,
，i =1,2,3…,n。
optionally, the image preprocessing step in the third stage includes the following steps:
step S1, respectively polishing the single sheet according to the ROI information and the effective detection region obtained in the second stage
And a single under-lighting image
Sequentially correcting and detecting dust to obtain a single-piece foreign matter mask
With single underlying foreign matter polishing mask
；
Step S2, removing noise points in the mask, and forming a single top-polished foreign-body mask obtained in step S1
With a single underlying photoresist foreign-body mask
Performing a morphological treatment comprising erosion and dilation;
optionally, in the third stage of mask synthesis, the morphologically processed single piece is masked with a polished foreign matter
With single underlying foreign matter polishing mask
Performing pixel-by-pixel or operation to obtain single filter mask
，i =1,2,3…,n。
Optionally, the step S1 includes the following steps:
step S11, adjusting each effective detection area by expanding and contracting the effective area;
step S12, polishing the image on the single sheet
And a single under-lighting image
Carrying out fuzzy processing and denoising;
step S13, for longitudeSingle-sheet under-laid-out image processed at step S12
Performing gray closing operation to erase the lower lighting image of a single sheet
The dark spot in the middle can obtain a single lower lighting comparison picture
，i =1,2,3…,n；
Step S14, single polishing comparison chart
With corresponding single underlying luminous image
By subtraction, a single underlying luminous image is formed
The dark spot area in the picture is lightened to obtain a corresponding single lower lighting response picture
，i =1,2,3…,n；
Step S15, for the single-sheet lower-lighting response chart obtained in step S14
Single window mean map for maximum
，i =1,2,3…,n；
Step S16, the single-sheet lower-striking response chart obtained in the step S14
Corresponding single-window mean map obtained in step S15
Subtracting to enhance the response of the real dark spot;
step S17, performing binary segmentation on the result of the step S16 to obtain a binary image containing dark point information, wherein the area higher than the threshold value is the dark point in the image;
step S18, screening the result of the step S17, selecting the points meeting the conditions as the final detection result to obtain a single piece of lower-beat light foreign body mask
。
Optionally, in step S13, the formula of the gray closing operation is:
wherein, the gray scale expansion operation formula is as follows:
the corrosion formula is:
in the formula (I), the compound is shown in the specification,
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates; dst represents: an image processed by gray closing operation;
indicating an erosion/expansion nucleus, a matrix of elements m x n in size, each 1, m and n being controlled by external parameters,can be adjusted according to the image condition;
represents: pixel x-axis coordinates in the erosion/dilation kernel;
represents: pixel y-axis coordinates in erosion/dilation kernel; max represents: solving the maximum value of the element; min represents: solving the minimum value of the elements; an element refers to the gray scale of a pixel; close represents: closing operation; the enode represents: carrying out corrosion operation; dilate denotes: an expansion operation; src represents: and (6) original drawing.
Optionally, in step S14, the subtraction formula is:
in the formula (I), the compound is shown in the specification,
represents: a single pixel in a discrete image;
represents: a marking of the pixel in the mask; dst represents: an image processed by gray closing operation; saturrate denotes: filling operation; src1 and src2 represent: two images needing subtraction operation;
represents: only the regions of the mask that are not 0 are subtracted.
Alternatively, the window maximum in step S15 is equivalent to the gray scale expansion operation, and the formula is:
window mean uses mean filtering:
wherein kernel denotes the filtering kernel of the mean filtering
In the formula (I), the compound is shown in the specification,
comprises the following steps: the abbreviation of kernel;
represents: the number of columns of the filter kernel;
represents: the number of rows of the filter kernel;
represents: the width of the filter kernel, i.e. the number of columns of the filter kernel;
represents: the height of the filter kernel, i.e. the number of rows of the filter kernel;
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates;
represents: pixel x-axis coordinates in the erosion/dilation kernel;
represents: pixel y-axis coordinates in erosion/dilation kernel; dst represents: an image processed by gray closing operation; src represents: original drawing; max represents: finding the maximum value of the element, the element meansThe gray scale of the pixel; and, anchor. x represents: filtering the x coordinate of the kernel anchor point; and, anchor. The y-coordinate of the anchor point is filtered.
Optionally, the binarization formula in step S17 is:
in the formula (I), the compound is shown in the specification,
comprises the following steps: gray values at the original image coordinates (x, y);
comprises the following steps: the threshold value is set to a value that is,
comprises the following steps: a non-zero value that should be assigned in the mask;
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates; dst represents: and (5) processing the image through a gray closing operation.
Optionally, the merging in step S18 is disclosed as:
in the formula (I), the compound is shown in the specification,
represents: a single pixel in a discrete image; dst represents: an image processed by gray closing operation; saturrate denotes: filling operation; src1 and src2 represent: two images needing to be combined;
represents:merging is only performed on areas of the mask that are not 0.
One of the above technical solutions has the following advantages or beneficial effects: the method solves the problem that the foreign matters on the backlight source and the foreign matters on the lower surface cannot be identified and filtered simultaneously in the traditional method, can distinguish and identify whether the dust foreign matters are on the upper surface or the lower surface of the screen, can distinguish and identify the dust foreign matters on the backlight source, and filters the dust foreign matters together.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings of the embodiments will be briefly described below, and it is apparent that the drawings in the following description relate only to some embodiments of the present invention and are not limiting thereof, wherein:
fig. 1 is a front view of an on-screen dust filtering apparatus according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating screen originals captured by a single set of image capture units in a screen dust filtering method according to an embodiment of the present invention;
fig. 3 is a diagram illustrating a corresponding effective detection area obtained after extracting screen original images captured by a single group of image capturing units in a screen dust filtering method according to an embodiment of the present invention;
fig. 4 is a single upper luminous image photographed in the screen dust filtering method according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a single piece of the upper-polished image obtained in FIG. 4 is processed to obtain a corresponding single piece of the upper-polished foreign matter mask;
FIG. 6 is a diagram illustrating a single under-bump image captured on the lower surface of a corresponding effective detection area in a screen dust filtering method according to an embodiment of the present invention;
FIG. 7 is a corresponding single underlying smooth foreign matter mask obtained by processing the single underlying smooth image obtained in FIG. 6;
fig. 8 is a diagram illustrating that the single upper polished foreign matter mask obtained in fig. 5 and the corresponding single lower polished foreign matter mask obtained in fig. 7 are combined to obtain a single filtering mask;
fig. 9 is an original of an under-lighting image obtained by the screen dust filtering method according to an embodiment of the present invention, in which bottom surface dust and backlight dust appear dark;
FIG. 10 illustrates an image of the original of the under-lighted image of FIG. 9 after blurring;
FIG. 11 shows the image of FIG. 10 after the close operation;
fig. 12 shows an image obtained by subtracting the image in fig. 11 from the image in fig. 9;
the image after the enhanced response to the image of fig. 12 is shown in fig. 13;
fig. 14 shows an image obtained by subjecting the image in fig. 13 to binarization processing;
FIG. 15 illustrates the resulting upper polish dust mask captured and processed by a corresponding set of image capture units;
the merged single filter mask is shown in fig. 16.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
In the drawings, the shape and size may be exaggerated for clarity, and the same reference numerals will be used throughout the drawings to designate the same or similar components.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The use of "first," "second," and similar terms in the description and claims of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. Also, the use of the terms "a," "an," or "the" and similar referents do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprise" or "comprises", and the like, means that the element or item listed before "comprises" or "comprising" covers the element or item listed after "comprising" or "comprises" and its equivalents, and does not exclude other elements or items. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
In the following description, terms such as center, thickness, height, length, front, back, rear, left, right, top, bottom, upper, lower, etc., are defined with respect to the configurations shown in the respective drawings, and in particular, "height" corresponds to a dimension from top to bottom, "width" corresponds to a dimension from left to right, "depth" corresponds to a dimension from front to rear, which are relative concepts, and thus may be varied accordingly depending on the position in which it is used, and thus these or other orientations should not be construed as limiting terms.
Terms concerning attachments, coupling and the like (e.g., "connected" and "attached") refer to a relationship wherein structures are secured or attached, either directly or indirectly, to one another through intervening structures, as well as both movable or rigid attachments or relationships, unless expressly described otherwise.
Example 1
Fig. 1 shows embodiment 1 of the present invention, and as can be seen in conjunction with the illustration of fig. 1, the screen dust filtering method includes the steps of:
1) the first stage, the preparation stage:
providing a screen 11 to be filtered, arranging at least one group of side light sources 14 beside the upper surface of the screen 11 to be filtered, and respectively arranging at least one group of image capturing units 13 and a backlight source 12 at the upper side and the lower side of the screen 11 to be filtered; wherein, the upper surface of the screen 11 may be attached with screen upper surface dust 111, the inside of the screen 11 may be formed with screen internal defects 113, the lower surface of the screen 11 may be attached with screen lower surface dust 112, and the upper surface and the inside of the backlight 12 may be attached with lamp box dust 121;
2) the second stage, image acquisition stage:
positioning the ROI on the screen 11 by a predetermined rule, generating ROI information, segmenting the screen 11 according to the ROI information to obtain at least one effective detection region, each set of the image capturing units 13 being aligned with a corresponding one of the effective detection regions;
each group of image capturing units 13 captures the upper surface of the corresponding effective detection area to obtain a single upper light-striking image in the state that the side light source 14 is opened and the backlight source 12 is closed
Or a single lower lighting image is obtained by capturing the lower surface of the corresponding effective detection area under the state that the side light source 14 is closed, the screen 11 is powered on and the backlight source 12 is opened
，i =1,2,3…,n；
3) A third stage, an image processing stage:
an image preprocessing step: sequentially polishing the single sheet
And a single under-lighting image
Performing pretreatment to form single-piece upper-polishing foreign-matter masks
With single underlying foreign matter polishing mask
, i =1,2,3…,n；
Mask synthesis: make a single piece of foreign matter mask
With single underlying foreign matter polishing mask
Are combined to form a single filter mask
And a plurality of single filter masks are arranged
Integrating according to the second stage of segmentation rule to obtain the total filtering mask
Said total filtering mask
For filtering out dust in subsequent screen defect detection to prevent defect misjudgment, wherein,
，i =1,2,3…,n。
as a further improvement, the image preprocessing step in the third stage includes the steps of:
step S1, respectively polishing the single sheet according to the ROI information and the effective detection region obtained in the second stage
And a single under-lighting image
Sequentially correcting and detecting dust to obtain a single-piece foreign matter mask
With single underlying foreign matter polishing mask
；
Step S2, removing noise points in the mask, and forming a single top-polished foreign-body mask obtained in step S1
With a single underlying photoresist foreign-body mask
Performing a morphological treatment comprising erosion and dilation; FIG. 15 illustrates a top-lit dust mask captured and processed by a set of image capture units;
as a further improvement, in the third stage mask synthesis step, the single piece after morphological treatment is polished to form a foreign body mask
With single underlying foreign matter polishing mask
Performing pixel-by-pixel or operation to obtain single filter mask
，i =1,2,3…,n. The merged single sheet filter mask is shown in FIG. 16
。
As a further improvement, the step S1 includes the following steps:
step S11, adjusting each effective detection area by expanding and contracting the effective area;
step S12, polishing the image on the single sheet
And under a single sheetPolishing images
Carrying out fuzzy processing and denoising; fig. 9 shows an original of one of the underlying luminous images, the lower surface dust and the backlight dust appear dark, and fig. 10 shows an image of the original after blurring processing;
step S13, the single under-lighting image processed by step S12
Performing gray closing operation to erase the lower lighting image of a single sheet
The dark spot in the middle can obtain a single lower lighting comparison picture
，i =1,2,3…,n(ii) a An image obtained after the close operation processing is shown in fig. 11;
step S14, single polishing comparison chart
With corresponding single underlying luminous image
By subtraction, a single underlying luminous image is formed
The dark spot area in the picture is lightened to obtain a corresponding single lower lighting response picture
，i =1,2,3…,n(ii) a Fig. 12 shows an image obtained by the subtraction processing;
step S15, for the single-sheet lower-lighting response chart obtained in step S14
Single window mean map for maximum
，i =1,2,3…,n；
Step S16, the single-sheet lower-striking response chart obtained in the step S14
Corresponding single-window mean map obtained in step S15
Subtracting to enhance the response of the real dark spot; the image after the enhanced response is shown in FIG. 13;
step S17, performing binary segmentation on the result of the step S16 to obtain a binary image containing dark point information, wherein the area higher than the threshold value is the dark point in the image; fig. 14 shows an image after the binarization processing;
step S18, screening the result of the step S17, selecting the points meeting the conditions as the final detection result to obtain a single piece of lower-beat light foreign body mask
。
As a further improvement, in step S13, the formula of the gray closing operation is:
wherein, the gray scale expansion operation formula is as follows:
the corrosion formula is:
in the formula (I), the compound is shown in the specification,
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates; dst represents: an image processed by gray closing operation;
the corrosion/expansion nucleus is a matrix with m × n elements of 1, and m and n are controlled by external parameters and can be adjusted according to the image condition;
represents: pixel x-axis coordinates in the erosion/dilation kernel;
represents: pixel y-axis coordinates in erosion/dilation kernel; max represents: solving the maximum value of the element; min represents: solving the minimum value of the elements; an element refers to the gray scale of a pixel; close represents: closing operation; the enode represents: carrying out corrosion operation; dilate denotes: an expansion operation; src represents: and (6) original drawing.
As a further improvement, in step S14, the subtraction formula is:
in the formula (I), the compound is shown in the specification,
represents: a single pixel in a discrete image is represented,
represents: a marking of the pixel in the mask; dst represents: an image processed by gray closing operation; saturrate denotes: filling operation; src1 and src2 represent: two images needing subtraction operation;
represents: only the regions of the mask that are not 0 are subtracted.
As a further improvement, the window maximum in step S15 is equivalent to the gray scale expansion operation, which is expressed by the formula:
window mean uses mean filtering:
wherein kernel is the filtering kernel of mean filtering
In the formula (I), the compound is shown in the specification,
comprises the following steps: the abbreviation of kernel;
represents: the number of columns of the filter kernel;
represents: the number of rows of the filter kernel;
represents: the width of the filter kernel, i.e. the number of columns of the filter kernel;
represents: the height of the filter kernel, i.e. the number of rows of the filter kernel;
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates;
represents: pixel x-axis coordinates in the erosion/dilation kernel;
represents: pixel y-axis coordinates in erosion/dilation kernel; dst represents: an image processed by gray closing operation; src represents: original drawing; max represents: solving the maximum value of an element, wherein the element refers to the gray level of a pixel; and, anchor. x represents: filtering the x coordinate of the kernel anchor point; and, anchor. The y-coordinate of the anchor point is filtered.
As a further improvement, the binarization formula in step S17 is:
in the formula (I), the compound is shown in the specification,
comprises the following steps: gray values at the original image coordinates (x, y);
comprises the following steps: the threshold value is set to a value that is,
comprises the following steps: a non-zero value that should be assigned in the mask;
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates; dst represents: and (5) processing the image through a gray closing operation.
As a further improvement, the merging in step S18 is disclosed as:
in the formula (I), the compound is shown in the specification,
represents: a single pixel in a discrete image; dst represents: an image processed by gray closing operation; saturrate denotes: filling operation; src1 and src2 represent: two images needing to be combined;
represents: merging is only performed on areas of the mask that are not 0.
The merged single sheet filter mask is shown in FIG. 16
Repeatedly executing the steps to obtain single filter masks processed and combined by the original images obtained by other groups of image capturing units, and reversely combining all the single filter masks according to the ROI segmentation rule to obtain the total filter mask
Said total filtering mask
The screen defect detection device is used for filtering out dust in subsequent screen defect detection so as to prevent defect misjudgment.
Example 2
Fig. 2 to 8 show embodiment 2 of the present invention, and referring to fig. 2, it can be seen that embodiment 2 differs from embodiment 1 in that more detailed filtering steps are disclosed:
the first step is as follows: bright screen detection (turning on the backlight, lighting the screen), determining whether to light (the central area is lighted with the gray scale greater than 40);
and secondly, extracting effective ROI detection areas, specifically, positioning the ROI of the screen to be filtered according to a predetermined rule of 2 x 3 (rows and columns), generating ROI information, uniformly dividing the screen 11 into 6 effective detection areas according to the ROI information, arranging six groups of image capturing units 13, forming image capturing groups of 2 x 3 (rows and columns) by the six groups of image capturing units 13 in an equidistant array mode, and aligning each group of image capturing units with a corresponding effective detection area.
Since the dust filtering steps of each group of image capturing units 13 are the same, for the sake of space saving, the subsequent steps only describe the filtering process for one group of image capturing units 13 in detail, the screen original image captured by a single group of image capturing units 13 is shown in fig. 2, and the corresponding effective detection area obtained after extraction is shown in fig. 3;
thirdly, closing the backlight, opening the upper side light, switching to a black picture or cutting off the black picture, and shooting a single upper lighting image
As shown in FIG. 4, the corresponding single piece of photo-mask is obtained after the treatment
As shown in fig. 5, a single lower lighting image is captured and obtained from the lower surface of the corresponding effective detection area in the states of the side light source 14 being turned off, the screen 11 being powered on and the backlight source 12 being turned on
As shown in fig. 6, the corresponding single piece of bottom-lighting foreign matter mask is obtained after the treatment
As shown in fig. 7; in the embodiment shown in fig. 2, six sets of image capturing units are arranged, and accordingly six upper lighting images are formed, respectively:
and correspondingly carrying out co-processing to obtain six upper polishing photomasks:
(ii) a Likewise, co-growSix lower polishing patterns are respectively as follows:
and correspondingly carrying out co-processing to obtain six lower-printing photomasks:
。
fourthly, as shown in FIG. 8, a single piece is masked with a foreign material
With single underlying foreign matter polishing mask
Are combined to form a single filter mask
And a plurality of single filter masks are arranged
Performing integration according to the segmentation rule to obtain the total filtering mask
Said total filtering mask
For filtering out dust in subsequent screen defect detection to prevent defect misjudgment, wherein,
，i =1,2,3…,6。
the number of apparatuses and the scale of the process described herein are intended to simplify the description of the present invention. Applications, modifications and variations of the present invention will be apparent to those skilled in the art.
The features of the different implementations described herein may be combined to form other embodiments not specifically set forth above. The components may be omitted from the structures described herein without adversely affecting their operation. Further, various individual components may be combined into one or more components to perform the functions described herein.
Furthermore, while embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in a variety of fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (9)
1. A screen dust filtering method is characterized by comprising the following steps:
1) the first stage, the preparation stage:
providing a screen (11) to be filtered, arranging at least one group of side light sources (14) beside the upper surface of the screen (11) to be filtered, and respectively arranging at least one group of image capturing units (13) and backlight sources (12) at the upper side and the lower side of the screen (11) to be filtered;
2) the second stage, image acquisition stage:
-locating a ROI on the screen (11) by predetermined rules and generating ROI information, segmenting the screen (11) in accordance with the ROI information to obtain at least one active detection region, each group of said image capturing units (13) being aligned with a respective one of the active detection regions;
each group of image capturing units (13) captures the upper surface of the corresponding effective detection area to obtain a single upper light-striking image in the state that the side light source (14) is opened and the backlight source (12) is closed
Or a single lower lighting image is obtained by capturing the lower surface of the corresponding effective detection area under the states that the side light source (14) is closed, the screen (11) is electrified and the backlight source (12) is opened
，i=1,2,3…,n；
3) A third stage, an image processing stage:
an image preprocessing step: sequentially polishing the single sheet
And a single under-lighting image
Performing pretreatment to form single-piece upper-polishing foreign-matter masks
With single underlying foreign matter polishing mask
, i =1,2,3…,n；
Mask synthesis: make a single piece of foreign matter mask
With single underlying foreign matter polishing mask
Are combined to form a single filter mask
And a plurality of single filter masks are arranged
According to the firstTwo stages of segmentation rules are integrated to obtain a total filtering mask
Said total filtering mask
For filtering out dust in subsequent screen defect detection to prevent defect misjudgment, wherein,
，i =1,2,3…,n。
2. the screen dust filtering method of claim 1, wherein the image preprocessing step in the third stage comprises the steps of:
step S1, respectively polishing the single sheet according to the ROI information and the effective detection region obtained in the second stage
And a single under-lighting image
Sequentially correcting and detecting dust to obtain a single-piece foreign matter mask
With single underlying foreign matter polishing mask
；
Step S2, removing noise points in the mask, and forming a single top-polished foreign-body mask obtained in step S1
With a single underlying photoresist foreign-body mask
Morphological treatments including erosion and dilation are performed.
3. The screen dust filtering method of claim 2, wherein the morphologically processed sheet is masked with the foreign matter in the mask synthesizing step of the third stage
With single underlying foreign matter polishing mask
Performing pixel-by-pixel or operation to obtain single filter mask
，i =1,2,3…,n。
4. The screen dust filtering method of claim 2, wherein the step S1 includes the steps of:
step S11, adjusting each effective detection area by expanding and contracting the effective area;
step S12, polishing the image on the single sheet
And a single under-lighting image
Carrying out fuzzy processing and denoising;
step S13, the single under-lighting image processed by step S12
Performing gray closing operation to erase the lower lighting image of a single sheet
The dark spot in the middle can obtain a single lower lighting comparison picture
，i =1,2,3…,n；
Step S14, single polishing comparison chart
With corresponding single underlying luminous image
By subtraction, a single underlying luminous image is formed
The dark spot area in the picture is lightened to obtain a corresponding single lower lighting response picture
，i =1,2,3…,n；
Step S15, for the single-sheet lower-lighting response chart obtained in step S14
Single window mean map for maximum
，i =1,2,3…,n；
Step S16, the single-sheet lower-striking response chart obtained in the step S14
Corresponding single-window mean map obtained in step S15
Subtraction to enhance true darknessThe response of the point;
step S17, performing binary segmentation on the result of the step S16 to obtain a binary image containing dark point information, wherein the area higher than the threshold value is the dark point in the image;
step S18, screening the result of the step S17, selecting the points meeting the conditions as the final detection result to obtain a single piece of lower-beat light foreign body mask
。
5. The screen dust filtering method of claim 4, wherein in the step S13, the gray closing operation formula is:
wherein, the gray scale expansion operation formula is as follows:
the corrosion formula is:
in the formula (I), the compound is shown in the specification,
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates; dst represents: an image processed by gray closing operation;
denotes the corrosion/swelling nuclei, m x n sizeThe elements of (1) are matrixes of 1, and m and n are controlled by external parameters and can be adjusted according to the image condition;
represents: pixel x-axis coordinates in the erosion/dilation kernel;
represents: pixel y-axis coordinates in erosion/dilation kernel; max represents: solving the maximum value of the element; min represents: solving the minimum value of the elements; an element refers to the gray scale of a pixel; close represents: closing operation; the enode represents: carrying out corrosion operation; dilate denotes: an expansion operation; src represents: and (6) original drawing.
6. The screen dust filtering method of claim 4, wherein in step S14, the subtraction formula is:
in the formula (I), the compound is shown in the specification,
represents: a single pixel in a discrete image is represented,
represents: a marking of the pixel in the mask; dst represents: an image processed by gray closing operation; saturrate denotes: filling operation; src1 and src2 represent: two images needing subtraction operation;
represents: only the regions of the mask that are not 0 are subtracted.
7. The screen dust filtering method of claim 4, wherein the window maximum in the step S15 is equivalent to a gray scale expansion operation, which is expressed by the formula:
window mean uses mean filtering:
wherein kernel denotes the filtering kernel of the mean filtering
In the formula (I), the compound is shown in the specification,
comprises the following steps: the abbreviation of kernel;
represents: the number of columns of the filter kernel;
represents: the number of rows of the filter kernel;
represents: the width of the filter kernel, i.e. the number of columns of the filter kernel;
represents: the height of the filter kernel, i.e. the number of rows of the filter kernel;
represents: target pixel x-axis coordinates;
represents: eyes of a userMarking the y-axis coordinate of the pixel;
represents: pixel x-axis coordinates in the erosion/dilation kernel;
represents: pixel y-axis coordinates in erosion/dilation kernel; dst represents: an image processed by gray closing operation; src represents: original drawing; max represents: solving the maximum value of an element, wherein the element refers to the gray level of a pixel; and, anchor. x represents: filtering the x coordinate of the kernel anchor point; and, anchor. The y-coordinate of the anchor point is filtered.
8. The screen dust filtering method of claim 4, wherein the binarization formula in step S17 is:
in the formula (I), the compound is shown in the specification,
comprises the following steps: gray values at the original image coordinates (x, y);
comprises the following steps: the threshold value is set to a value that is,
comprises the following steps: a non-zero value that should be assigned in the mask;
represents: target pixel x-axis coordinates;
represents: target pixel y-axis coordinates; dst represents: and (5) processing the image through a gray closing operation.
9. The screen dust filtering method of claim 4, wherein the merged presentation in the step S18 is:
in the formula (I), the compound is shown in the specification,
represents: a single pixel in a discrete image; dst represents: an image processed by gray closing operation; saturrate denotes: filling operation; src1 and src2 represent: two images needing to be combined;
represents: merging is only performed on areas of the mask that are not 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834814.5A CN113284148B (en) | 2021-07-23 | 2021-07-23 | Screen dust filtering method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834814.5A CN113284148B (en) | 2021-07-23 | 2021-07-23 | Screen dust filtering method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113284148A true CN113284148A (en) | 2021-08-20 |
| CN113284148B CN113284148B (en) | 2021-10-15 |
Family
ID=77287102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110834814.5A Active CN113284148B (en) | 2021-07-23 | 2021-07-23 | Screen dust filtering method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113284148B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311448A (en) * | 2022-09-02 | 2022-11-08 | 敬科(深圳)机器人科技有限公司 | Method and device for positioning mesh material and storage medium |
| CN117934453A (en) * | 2024-03-18 | 2024-04-26 | 深圳市酷童小样科技有限公司 | Method and system for diagnosing defects of backlight foreign matters of mobile phone screen |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013064298A1 (en) * | 2011-11-01 | 2013-05-10 | Asml Holding N.V. | Lithographic apparatus and device manufacturing method |
| CN109829904A (en) * | 2019-01-29 | 2019-05-31 | 京东方科技集团股份有限公司 | Detect the method, apparatus of dust, electronic equipment, readable storage medium storing program for executing on screen |
| CN110445921A (en) * | 2019-09-06 | 2019-11-12 | 东北大学 | A kind of Mobile phone screen backlight foreign matter defect diagnostic method and device based on machine vision |
| CN110490864A (en) * | 2019-08-22 | 2019-11-22 | 易思维（杭州）科技有限公司 | The adaptive defect inspection method of image |
| CN111272763A (en) * | 2018-12-04 | 2020-06-12 | 通用电气公司 | System and method for workpiece inspection |
| CN112858318A (en) * | 2021-04-26 | 2021-05-28 | 惠州高视科技有限公司 | Method for distinguishing screen foreign matter defect from dust, electronic equipment and storage medium |
-
2021
- 2021-07-23 CN CN202110834814.5A patent/CN113284148B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013064298A1 (en) * | 2011-11-01 | 2013-05-10 | Asml Holding N.V. | Lithographic apparatus and device manufacturing method |
| CN111272763A (en) * | 2018-12-04 | 2020-06-12 | 通用电气公司 | System and method for workpiece inspection |
| CN109829904A (en) * | 2019-01-29 | 2019-05-31 | 京东方科技集团股份有限公司 | Detect the method, apparatus of dust, electronic equipment, readable storage medium storing program for executing on screen |
| CN110490864A (en) * | 2019-08-22 | 2019-11-22 | 易思维（杭州）科技有限公司 | The adaptive defect inspection method of image |
| CN110445921A (en) * | 2019-09-06 | 2019-11-12 | 东北大学 | A kind of Mobile phone screen backlight foreign matter defect diagnostic method and device based on machine vision |
| CN112858318A (en) * | 2021-04-26 | 2021-05-28 | 惠州高视科技有限公司 | Method for distinguishing screen foreign matter defect from dust, electronic equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311448A (en) * | 2022-09-02 | 2022-11-08 | 敬科(深圳)机器人科技有限公司 | Method and device for positioning mesh material and storage medium |
| CN117934453A (en) * | 2024-03-18 | 2024-04-26 | 深圳市酷童小样科技有限公司 | Method and system for diagnosing defects of backlight foreign matters of mobile phone screen |
| CN117934453B (en) * | 2024-03-18 | 2024-06-04 | 深圳市酷童小样科技有限公司 | Method and system for diagnosing defects of backlight foreign matters of mobile phone screen |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113284148B (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106770362B (en) | Macroscopic defect detection device and method based on AOI | |
| CN113284148B (en) | Screen dust filtering method | |
| CN104749184B (en) | Automatic optical detection method and system | |
| US7783103B2 (en) | Defect detecting device, image sensor device, image sensor module, image processing device, digital image quality tester, and defect detecting method | |
| CN109978839A (en) | The detection method of the low texture defect of wafer | |
| CN110211182A (en) | A kind of LCD backlight vision positioning method based on Gray-scale Matching and objective contour | |
| CN108876768B (en) | Shadow defect detection method for light guide plate | |
| US20080075385A1 (en) | Detection and Correction of Flash Artifacts from Airborne Particulates | |
| CN111474177A (en) | Liquid crystal screen backlight foreign matter defect detection method based on computer vision | |
| CN115908415B (en) | Edge-based defect detection method, device, equipment and storage medium | |
| CN112164050B (en) | Method and device for detecting surface defects of products on production line and storage medium | |
| Kuo et al. | Integrating image processing and classification technology into automated polarizing film defect inspection | |
| CN112085700B (en) | Automatic extraction method, system and medium for weld joint region in X-ray image | |
| CN110514665A (en) | A kind of detection method of electronic product plastic shell scratch defects | |
| CN113033558B (en) | Text detection method and device for natural scene and storage medium | |
| CN117152165B (en) | Photosensitive chip defect detection method and device, storage medium and electronic equipment | |
| CN115661110B (en) | Transparent workpiece identification and positioning method | |
| CN112396575A (en) | Image-based classification system | |
| CN109064439B (en) | Partition-based single-side light-entering type light guide plate shadow defect extraction method | |
| Ma et al. | An automatic detection method of Mura defects for liquid crystal display | |
| CN113034488A (en) | Visual detection method of ink-jet printed matter | |
| CN117876367B (en) | Exposure optimization method for circuit board printing | |
| CN111563869B (en) | Stain test method for quality inspection of camera module | |
| Han et al. | Automatic illumination and color compensation using mean shift and sigma filter | |
| CN110530894B (en) | Light guide plate bright spot defect detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |