CN111275704B - Method and equipment for detecting stains of mask plate - Google Patents
Method and equipment for detecting stains of mask plate Download PDFInfo
- Publication number
- CN111275704B CN111275704B CN202010130217.XA CN202010130217A CN111275704B CN 111275704 B CN111275704 B CN 111275704B CN 202010130217 A CN202010130217 A CN 202010130217A CN 111275704 B CN111275704 B CN 111275704B
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- local
- stain
- 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
- 238000000034 method Methods 0.000 title claims description 24
- 238000001514 detection method Methods 0.000 claims abstract description 47
- 238000010586 diagram Methods 0.000 description 25
- 230000009286 beneficial effect Effects 0.000 description 5
- 239000002689 soil Substances 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000007747 plating Methods 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- 238000005019 vapor deposition process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a stain detection method and device for a mask plate. The stain detection method of the mask plate comprises the following steps: presetting a group of multi-level standard images with sizes ranging from large to small, calling a non-minimum-size one-level standard image in the multi-level standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result; the size of the local image of the mask plate to be detected containing the stains is reduced step by step, and a mode that each opening in the image of the mask plate is compared one by one is avoided, so that the position of the stains can be positioned more quickly. Compared with the prior art, the embodiment of the invention improves the efficiency of stain detection.
Description
Technical Field
The embodiment of the invention relates to the technical field of display, in particular to a stain detection method and device for a mask plate.
Background
With the continuous development of display technology, the application range of display panels is wider and wider, the requirements of people on the display panels are higher and higher, and the process requirements of display panel manufacturers on the display panels are also higher and higher.
The vapor deposition process is an important step of a panel manufacturing process, and the mask plate is a key component used in the vapor deposition process. Along with the production of vapor plating, vapor plating material can remain on the surface of the mask plate to form stains and shield the open pores of the mask plate. If the stains on the mask plate can not be timely and effectively detected, the mask plate containing the stains is adopted for production, and the product yield of the display panel can be influenced. However, the conventional stain detection method has a problem of low detection efficiency.
Disclosure of Invention
The embodiment of the invention provides a stain detection method and device for a mask plate, and aims to improve the stain detection efficiency.
In order to achieve the technical purpose, the embodiment of the invention provides the following technical scheme:
a stain detection method of a mask plate comprises the following steps:
presetting a group of multi-level standard images with sizes arranged from large to small; in the multi-level standard images, a first-level standard image is a local standard image of a mask plate to be detected, and the other levels of images in the standard images are local standard images of a previous-level standard image;
acquiring an image of a mask plate to be detected;
taking the whole area of the image of the mask plate to be detected as an image of the area to be detected, calling a first-level standard image with a size which is not the smallest in the multi-level standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result;
if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling a next-level standard image of the comparison image as a new comparison image, comparing the new to-be-detected area image with the local image, judging whether the local image of the to-be-detected area image contains the stain image according to a comparison result, and executing the step circularly until the called comparison image is the minimum-level standard image in the multi-level standard images so as to obtain the position of the stain image in the to-be-detected mask plate image.
The technical scheme is that the embodiment of the invention creatively provides a novel method for detecting the stain of the mask plate, and is different from the prior art in that the embodiment of the invention gradually reduces the size of the comparison image, correspondingly, the size of the local image of the mask plate to be detected containing the stain is gradually reduced, and the mode of comparing each opening in the image of the mask plate one by one is avoided, so that the embodiment of the invention can more quickly position the stain and improve the stain detection efficiency.
Further, the multi-level standard images comprise a first-level standard image, a second-level standard image and a third-level standard image which are arranged from large to small in size;
after the mask plate image to be detected is obtained, the method comprises the following steps:
taking the whole area of the image of the mask plate to be detected as an image of an area to be detected, calling the first-level standard image as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result;
if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling the second-level standard image as a new comparison image, comparing the new to-be-detected area image with the second-level standard image, and judging whether the local image of the to-be-detected area image contains the stain image or not according to a comparison result;
if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling the third-level standard image as a new comparison image, comparing the new to-be-detected area image with the third-level standard image, and judging whether the local image of the to-be-detected area image contains the stain image or not according to a comparison result; and obtaining the stain image position in the image of the mask plate to be detected.
Comparing the first-level standard image with the image of the mask plate to be detected, and determining whether the local image of the mask plate to be detected contains stains; if the local image contains the stains, taking the local image as a new image of the area to be detected, comparing the second-level standard image with the new image of the mask plate to be detected, and determining whether the local image of the new image of the mask plate to be detected contains the stains; and if the local image contains the dirt, taking the local image as a new image of the area to be detected, comparing the third-level standard image with the new image of the mask plate to be detected, and determining whether the local image of the new image of the mask plate to be detected contains the dirt. In other words, the embodiment of the invention adopts a three-level comparison mode, gradually reduces the size of the standard image compared with the image of the mask plate to be detected, can position the spot more quickly, and improves the spot detection efficiency.
Further, the stain detection method of the mask plate further comprises the following steps:
if the local image does not contain the dirt, comparing other local images in the to-be-detected area image with the comparison image, and judging whether the local image of the to-be-detected area image contains the dirt image according to the comparison result. Therefore, the local images which do not contain the stains do not need to be compared further, so that the comparison time is saved, the positions of the stains can be located more quickly, and the stain detection efficiency is further improved.
Furthermore, the image of the region to be detected comprises a plurality of local images, and the plurality of local images are arranged in an array;
comparing local images in the to-be-detected region image with the comparison image in sequence along the row direction; or,
comparing the local images in the to-be-detected region image with the comparison image in sequence along the column direction; or,
the local images in the images of the area to be measured are sequentially compared with the comparison images along a spiral track; or,
and sequentially comparing the local images in the to-be-detected region image with the comparison image along the zigzag track.
The embodiment of the invention is arranged in such a way, which is beneficial to sequentially comparing a plurality of local image areas of the image of the area to be detected, and the local image at a certain position is not easy to miss.
Further, when obtaining the spot position of the image of the mask plate to be detected, the method further comprises the following steps: and counting the number of stains in the image of the mask plate to be detected. The embodiment of the invention is arranged in such a way, not only can the position of the stain be positioned, but also the number of the stains can be counted, the functions of the stain detection method of the mask plate are enriched, and the practicability is stronger.
Further, the primary standard image of the smallest size includes an opening;
the partial image to be compared with the primary standard image of the smallest size includes an opening.
According to the embodiment of the invention, the positions of the holes shielded by the stains can be used for representing the positions of the stains, compared with other modes for describing the positions of the stains, the method and the device can reflect the influence of the stains on the mask plate, do not need to judge the shielding rate of the stains on the holes, and further improve the stain detection efficiency.
Further, the local image of the to-be-detected region image and the comparison image are the same in shape and size. The embodiment of the invention is arranged in such a way, other variables except for dirt of the local image and the comparison image can be controlled to be kept unchanged, and thus the comparison precision is favorably improved.
Further, the standard image includes N × N openings, where N is a positive integer. Therefore, the image of the mask plate to be detected can be divided, and the stain detection efficiency is further improved.
Further, the shape of the standard image includes: at least one of rectangle, sector, circle and ring shape, so that the standard image can adapt to the images of the masks to be detected in different shapes, and the practicability of the stain detection method of the masks is further improved.
Correspondingly, the invention also provides a stain detection device of the mask plate, which comprises:
the standard image setting module is used for presetting a group of multi-level standard images with sizes arranged from large to small; in the multi-level standard images, a first-level standard image is a local standard image of a mask plate to be detected, and the other levels of images in the standard images are local standard images of a previous-level standard image;
the image acquisition module is used for acquiring an image of the mask plate to be detected;
the comparison module is used for taking the whole area of the mask plate image to be detected as an image of the area to be detected, calling a primary standard image with a non-minimum size in the multi-level standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result;
and the position determining module is used for taking the local image as a new image of the area to be detected if the local image comprises a stain image, calling a next-level standard image of the comparison image as a new comparison image, comparing the new image with the new image of the area to be detected, judging whether the local image of the area to be detected comprises the stain image according to a comparison result, and circularly executing the step until the called comparison image is the minimum-level standard image in the multi-level standard images so as to obtain the position of the stain image in the image of the mask plate to be detected.
The embodiment of the invention creatively provides a novel stain detection method for a mask plate, and is different from the prior art in that a group of multi-level standard images with sizes arranged from large to small are preset, a first-level standard image with a non-minimum size in the multi-level standard images is called as a comparison image to be compared with an image of a region to be detected, and whether a local image of the region to be detected comprises a stain image or not is judged according to a comparison result; if the local image contains a stain image, taking the local image as a new image of the area to be detected, calling a next-level standard image of the comparison image as a new comparison image, comparing the new image with the image of the area to be detected, judging whether the local image of the area to be detected contains the stain image according to a comparison result, and circularly executing the step until the called comparison image is the minimum-level standard image in the multi-level standard images so as to accurately position the position of the stain on the mask plate to be detected. According to the embodiment of the invention, the size of the image to be compared is reduced step by step, correspondingly, the size of the local image of the mask plate to be detected containing the stains is reduced step by step, and a mode of comparing each opening in the image of the mask plate one by one is avoided.
Drawings
Fig. 1 is a schematic flow chart of a stain detection method for a mask plate according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a standard image according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an image of a mask to be detected according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of another standard image according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of another image of a mask to be detected according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of another standard image according to an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of another standard image according to an embodiment of the present invention;
fig. 8 is a schematic flowchart of another method for detecting stains on a mask according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of another image of a mask to be detected according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of another image of a mask to be detected according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of another image of a mask to be detected according to an embodiment of the present invention;
FIG. 12 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to an embodiment of the present invention;
FIG. 13 is a schematic diagram illustrating another comparison sequence of a plurality of partial images according to an embodiment of the present invention;
FIG. 14 is a diagram illustrating a comparison sequence of a plurality of partial images according to an embodiment of the present invention;
FIG. 15 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to an embodiment of the present invention;
FIG. 16 is a schematic structural diagram of another standard image according to an embodiment of the present invention;
FIG. 17 is a schematic structural diagram of another standard image according to an embodiment of the present invention;
FIG. 18 is a schematic diagram of a structure of another standard image according to an embodiment of the present invention;
FIG. 19 is a schematic structural diagram of another standard image according to an embodiment of the present invention;
FIG. 20 is a diagram illustrating a comparison sequence of a plurality of partial images according to an embodiment of the present invention;
FIG. 21 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to an embodiment of the present invention;
fig. 22 is a schematic flowchart of a stain detection method for a mask plate according to another embodiment of the present disclosure;
fig. 23 is a schematic structural view of a stain detection apparatus for a mask plate according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.
The embodiment of the invention provides a stain detection method of a mask plate, which can be executed by stain detection equipment of the mask plate and can be realized by software and/or hardware, so that stain detection is carried out on an image of the mask plate to be detected, and the position of stains in the image of the mask plate to be detected is determined. Fig. 1 is a schematic flow chart of a stain detection method for a mask plate according to an embodiment of the present invention. Referring to fig. 1, the stain detection method of the mask plate includes the steps of:
s110, presetting a group of multi-level standard images with sizes arranged from large to small; in the multi-level standard images, the first level standard image is a local standard image of the mask plate to be detected, and the rest level images in the standard images are local standard images of the previous level standard image.
The preset standard image can be stored in a memory and called when image comparison is carried out. In conjunction with the standard image 310 shown in fig. 2, the standard image 310 refers to an image of a clean mask, i.e., an image of a mask without stains.
And S120, obtaining an image of the mask plate to be detected.
In conjunction with the mask image 100 to be detected shown in fig. 3, the mask image 100 to be detected can be captured by an optical probe in the stain detection apparatus. The image 100 of the mask to be detected may be an image of the entire mask, or may be an image of a part of the mask captured from the image of the entire mask. The mask image 100 to be detected includes a plurality of local images 210, that is, the size of the local images 210 is smaller than the size of the mask image 100 to be detected, and the number of the openings 101 included in the local images 210 is smaller than the number of the openings 101 included in the mask image 100 to be detected. Illustratively in fig. 2, each partial image 210 includes 4 apertures 101.
S130, taking the whole area of the image of the mask plate to be detected as an image of the area to be detected, calling a first-level standard image with non-minimum size in the multi-level standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result.
Referring to fig. 2 and 3, the partial image 210 and the standard image 310 have the same shape and the same size. Illustratively, the standard images 310 are rectangular in shape, each standard image 310 includes 4 apertures 101, and correspondingly, the image areas 210 to which the standard images 310 are compared are rectangular in shape, each image area 210 including 4 apertures 101. Therefore, by comparing the mask image 100 to be detected with the standard image 310, it can be quickly determined whether a certain partial image 210 in the mask image 100 to be detected contains the dirt 400.
Illustratively, the technique for performing comparison may be similarity comparison, and the technique for performing similarity comparison may be image processing techniques, such as mean absolute difference algorithm (MAD), sum of absolute difference algorithm (SAD), sum of squared error algorithm (SSD), sum of squared average error algorithm (MSD), normalized product correlation algorithm (NCC), Sequential Similarity Detection Algorithm (SSDA), or hadamard transform algorithm (SATD). The image data of the partial image 210 and the standard image 310 include: brightness or color, etc. The similarity between the local image 210 and the standard image 310 can be calculated through an image processing technology, and if the similarity is within a preset range, the local image 210 is judged to be free of stains 400; if the similarity is outside the predetermined range, it is determined that the local image area 210 contains the stain 400. Taking the standard image 310 and the local image 210 at the top left corner in fig. 2 as an example, if the similarity between the local image 210 at the top left corner in fig. 2 and the standard image 310 is outside the preset range, it is determined that the local image 210 contains the stain 400; taking the standard image 310 and the partial image 210 at the upper right corner in fig. 2 as an example, if the similarity between the partial image 210 at the upper right corner in fig. 2 and the standard image 310 is within a preset range, it is determined that the partial image 210 is free of stains 400.
Therefore, whether the partial image 210 contains the stain 400 can be quickly determined by comparing the similarity between the mask image 100 to be detected and the standard image 310. Referring to fig. 3, in S130, it may be determined that the stain 400 is located at the upper left corner of the image 100 of the mask to be detected, but the specific location of the stain 400 in the partial image 210 at the upper left corner cannot be determined.
And S140, if the local image contains the stain image, taking the local image as a new to-be-detected region image, calling a next-stage standard image of the comparison image as a new comparison image, comparing the new to-be-detected region image with the local image, judging whether the local image of the to-be-detected region image contains the stain image according to a comparison result, and executing the step in a circulating mode until the called comparison image is the minimum-level standard image in the multi-stage standard image, so that the position of the stain image in the to-be-detected mask plate image is obtained.
As shown in fig. 4, the size of the next-level standard image 320 is smaller than that of the previous-level standard image 310. The next level of standard image 320 of the contrast image is called, so that the area where the stain 400 is located can be reduced step by step until the accurate position of the stain 400 is located.
Wherein the minimum level standard image refers to a standard image capable of locating the position of the stain 400. Optionally, the position of the stain 400 is represented by the position of the opening 101 blocked by the stain 400, so that the influence of the stain 400 on the mask plate can be reflected more than other ways of describing the position of the stain 400. At this time, the minimum-level standard image may be set to include one opening 101. Then, in fig. 4, the next-level standard image 220 is the minimum-level standard image.
Taking fig. 5 as an example, the local image 210 located at the upper left corner of the image 100 of the mask to be detected is compared with the next-stage standard image. With reference to fig. 4 and fig. 5, exemplarily, the local image 220 in the 1 st row and the 1 st column is compared with the standard image 320, and the similarity is within the preset range, so as to determine that the 1 st row and the 1 st column are free of stains 400; comparing the similarity between the local image 220 in the 1 st row and the 2 nd column and the standard image 320, wherein the similarity is out of a preset range, and the position of the stain 400 is positioned as the 1 st row and the 2 nd column; comparing the similarity of the local image 220 in the row 2 and the column 1 with the standard image 320, and judging that the row 2 and the column 1 are free of stains 400 if the similarity is within a preset range; the local image 220 in row 2 and column 2 is compared with the standard image 320 for similarity, and the absence of the stain 400 in row 2 and column 2 is determined if the similarity is within a preset range. Thus, the comparison of all 4 partial images 220 is complete, and the stain 400 can be located on row 1, column 2.
And S150, if the local image does not contain the dirt, comparing other local images in the image of the area to be detected with the comparison image, and judging whether the local image of the area to be detected contains the dirt image or not according to the comparison result.
In summary, different from the prior art, in the embodiment of the present invention, a group of multi-level standard images arranged from large to small in size is preset, a non-minimum-sized one-level standard image in the multi-level standard images is called as a comparison image to be compared with an image of a region to be detected, and whether a local image of the region to be detected includes a stain image is determined according to a comparison result; if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling a next-stage standard image of the comparison image as a new comparison image, comparing the new to-be-detected area image with the local image, judging whether the local image of the to-be-detected area image contains the stain image according to a comparison result, and circularly executing the step until the called comparison image is the minimum-level standard image in the multi-stage standard image so as to accurately position the position of the stain on the to-be-detected mask plate. According to the embodiment of the invention, the size of the comparison image is reduced step by step, correspondingly, the size of the local image of the mask plate to be detected containing the dirt is reduced step by step, and a mode of comparing each opening in the image of the mask plate one by one is avoided, so that the position of the dirt can be positioned more quickly, and the dirt detection efficiency is improved.
It should be noted that, the size of the standard image 310 is not limited in the embodiment of the present invention, and the larger the area of the standard image 310 is, the larger the number of the openings 101 is. The standard image 310 may include 4(2 × 2) openings 101 as shown in fig. 2; the standard image 310 may also include 9(3 × 3) openings 101 as shown in fig. 6; the standard image 310 may also include 16(4 x 4) apertures 101 as shown in fig. 7. The standard image 310 may further include N × N (N is a positive integer) openings 101, which are not listed. Preferably, the standard image 310 with a larger size is selected in S130 to reduce the number of the local images 210, reduce the number of the alignments, and improve the detection efficiency.
It should be further noted that, in the above embodiment, the comparison between the mask plate image 100 to be detected and the standard image of two levels (such as the standard images shown in fig. 2 and fig. 4) is exemplarily shown, and the invention is not limited thereto. In other embodiments, the mask plate image 100 to be detected may be compared with a standard image of three levels, a standard image of four levels, or a standard image of more levels, and may be set as needed in practical application. The mask image 100 to be measured is compared with the three levels of standard images to be described below.
Fig. 8 is a schematic flowchart of another stain detection method for a mask plate according to an embodiment of the present disclosure. Referring to fig. 8, in an embodiment of the present invention, optionally, the method for detecting stains on a mask plate includes the following steps:
s210, presetting a first-stage standard image, a second-stage standard image and a third-stage standard image which are arranged from large to small in size; the first-stage standard image is a local standard image of the mask to be detected, the second-stage standard image is a local standard image of the first-stage standard image, and the third standard image is a local standard image of the second-stage standard image.
And S220, acquiring an image of the mask plate to be detected.
And S230, taking the whole area of the image of the mask plate to be detected as an image of the area to be detected, calling the first-level standard image as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result.
Referring to fig. 9, comparing the first-level standard image 310 with the partial image 210 located at the upper left corner of the mask image 100 to be detected, it can be quickly determined whether the partial image 210 contains the stains 400.
And S240, if the local image contains the stain image, taking the local image as a new image of the area to be detected, calling the second-level standard image as a new comparison image, comparing the new image with the image of the area to be detected, and judging whether the local image of the area to be detected contains the stain image according to the comparison result.
Referring to fig. 10, the partial image 210 located at the upper left corner of the mask image 100 to be detected contains the stain 400, the partial image 210 is used as a new image of the region to be detected, and the second-level standard image 320 is called as a new comparison image. That is, the image 210 located at the upper left corner is compared with the second-level standard image 320 to determine whether the partial image 220 includes the stain image.
S250, if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling a third-level standard image as a new comparison image, comparing the third-level standard image with the new to-be-detected area image, and judging whether the local image of the to-be-detected area image contains the stain image or not according to a comparison result; and obtaining the position of the stain image in the image of the mask plate to be detected.
Referring to fig. 11, the partial image 220 located at the upper left corner of the partial image 210 contains stains 400, and the partial image 220 located at the upper left corner of the partial image 210 is compared with the third-level standard image 330. The similarity between the local image 230 in the 1 st row and the 1 st column of the 1 st row and the third-level standard image 330 is within a preset range, and the condition that the 1 st row and the 1 st column are dirty 400 is judged; the similarity between the local image 230 in the 1 st row and the 2 nd column and the third-level standard image 330 is out of the preset range, and the position of the stain 400 is positioned in the 1 st row and the 2 nd column; the similarity between the local image 230 in the 2 nd row and the 1 st column and the third-level standard image 330 is within a preset range, and the absence of stains 400 in the 2 nd row and the 1 st column is judged; the similarity between the local image 230 in row 2 and column 2 and the third-level standard image 330 is within a predetermined range, and it is determined that the row 2 and column 2 are free of stains 400. Thus, the stain 400 can be localized on row 1, column 2.
And S260, if the local image does not contain the dirt, comparing other local images in the image of the area to be detected with the comparison image, and judging whether the local image of the area to be detected contains the dirt image or not according to the comparison result.
Comparing the first-level standard image with the image of the mask plate to be detected, and determining whether the local image of the mask plate to be detected contains stains; if the local image contains stains, taking the local image as a new image of the area to be detected, comparing the second-level standard image with the new image of the mask plate to be detected, and determining whether the local image of the new image of the mask plate to be detected contains stains; and if the local image contains the dirt, taking the local image as a new image of the area to be detected, comparing the third-level standard image with the new image of the mask plate to be detected, and determining whether the local image of the new image of the mask plate to be detected contains the dirt. In other words, the embodiment of the invention adopts a three-level comparison mode, reduces the size of the standard image compared with the image of the mask plate to be detected step by step, can position the position of the stain more quickly, and improves the stain detection efficiency.
It should be noted that, in each of the above embodiments, it is exemplarily shown that, after the local image 210 is determined to include the stain 400, the area of the similarity comparison is first reduced step by step for the local image 210, the position of the stain 400 is located, and then the similarity comparison is performed on the next local image 210, which is not limited by the invention. In other embodiments, after the local image 210 is determined to contain the stain 400, the similarity comparison may be performed on the next local image 210, and then the area of the similarity comparison is reduced step by step for the local image 210 containing the stain 400, so as to locate the position of the stain 400, which may be set as required in practical applications. In any way, when the local image 210 is determined not to contain the stain, the embodiment of the present invention performs the step of determining whether the local image 210 contains the stain by using the next local image 210 as the comparison object. Therefore, for the local image 210 without the stain, the further similarity comparison is not needed, so that the time for the similarity comparison is saved, the position of the stain can be located more quickly, and the stain detection efficiency is further improved.
In the above embodiments, the position relationship of the next partial image 210 may be located on the left side, the right side, the upper side or the lower side of the current partial image 210, and there are various orders for sequentially comparing the plurality of partial images 210, which are described below, but not limiting the present invention.
Fig. 12 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to an embodiment of the present invention. Referring to fig. 12, in an embodiment of the present invention, optionally, the plurality of local images 210 are arranged in an array, and the local images 210 in the image 100 of the region to be measured are sequentially compared with the comparison image (the standard image 310) along the row direction. By this arrangement, it is beneficial to compare the plurality of partial images 210 in sequence, and a partial image 210 is not easy to miss.
Fig. 13 is a schematic diagram of another comparison sequence of a plurality of partial images according to an embodiment of the present invention. Referring to fig. 13, in an embodiment of the present invention, optionally, the plurality of partial images 210 are arranged in an array, and the partial images 210 in the image 100 of the region to be measured are sequentially compared with the comparison image (the standard image 310) along the column direction. By this arrangement, it is beneficial to compare the plurality of partial images 210 in sequence, and it is not easy to miss a certain partial image 210.
Fig. 14 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to another embodiment of the present invention. Referring to fig. 14, in an embodiment of the present invention, optionally, the plurality of local images 210 are arranged in an array, and the local images 210 in the image 100 of the region to be measured are sequentially compared with the comparison image (the standard image 310) along a spiral track. This arrangement is advantageous in comparing a plurality of partial images 210 in sequence, and a partial image 210 is not easily missed.
Fig. 15 is a schematic diagram of a comparison sequence of a plurality of partial images according to another embodiment of the present invention. Referring to fig. 15, in an embodiment of the present invention, optionally, the plurality of partial images 210 are arranged in an array, and the partial images 210 in the image 100 of the region to be measured are sequentially compared with the comparison image (the standard image 310) along a zigzag track. By this arrangement, it is beneficial to compare the plurality of partial images 210 in sequence, and it is not easy to miss a certain partial image 210.
It should be noted that fig. 12 to 15 exemplarily show the order of comparing the four kinds of partial images 210, but the present invention is not limited thereto, and the comparison of the plurality of partial images 220 may be performed in another order. And, the above comparison sequence is also applicable to each level of the partial image 220.
It should be noted that, in the above embodiments, the standard image 310 is exemplarily shown as a rectangle including N × N openings 101, and is not a limitation of the present invention. In other embodiments, the standard image 310 may also be shaped including: the structure comprises at least one of a rectangle (shown in figure 16), a sector (shown in figure 17), a circle (shown in figure 18), and a ring (shown in figure 19) and a sum of NxM openings 101, wherein M and N are positive integers, and N is not equal to M. The standard image 310 is arranged in such a way, so that the standard image can be suitable for the stains 400 in normal area positions such as a rectangle, and the stains 400 in special area positions such as a chamfer, a hole and a Liu Hai area of a mask plate can be detected.
Fig. 20 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to another embodiment of the present invention. Referring to fig. 20, an image 100 of a mask to be detected includes 42 openings 101, and the image 100 of the mask to be detected is compared with a first standard image 380 to determine whether a local image 280 includes a stain image; the image 100 of the mask to be detected is compared with the second standard image 390 to determine whether the local image 290 includes a stain image. The mask image 100 to be measured includes 9 partial images 280 and 3 partial images 290. The partial image 280 includes 4(2 × 2) openings 101, and the first standard image 380 includes 4(2 × 2) openings 101; the partial image 290 includes 2(1 × 2) openings 101, and the second standard image 290 includes 2(1 × 2) openings 101. During soil detection, the location of the soil is also located using a minimal primary standard image (including only one aperture 101). The specific detection method is similar to the previous embodiments and is not described again.
Fig. 21 is a schematic diagram illustrating a comparison sequence of a plurality of partial images according to another embodiment of the present invention. Referring to fig. 21, an exemplary mask image 100 to be detected includes 44 openings 101, and the mask image 100 to be detected is compared with the first standard image 380 to determine whether the local image 280 includes a stain image; the mask image 100 to be measured is compared with the second standard image 390 to determine whether the local image 290 includes a stain image. The mask image 100 to be detected includes 8 partial images 280 and 4 partial images 290. Wherein the partial image 280 includes 4(2 × 2) openings 101, and the first standard image 380 includes 4(2 × 2) openings 101; the partial image 290 includes 3 apertures 101, and the second standard image 290 includes 3 apertures 101. During soil detection, the location of the soil is also located using a minimal primary standard image (including only one aperture 101). The specific detection method is similar to the previous embodiments and is not described again.
Fig. 22 is a schematic flowchart of a stain detection method for a mask plate according to another embodiment of the present invention. Referring to fig. 22, in an embodiment of the present invention, optionally, the stain detection method of the mask plate includes the following steps:
s310, presetting a group of multi-level standard images with sizes arranged from large to small; in the multi-level standard images, the first level standard image is a local standard image of the mask plate to be detected, and the rest level images in the standard images are local standard images of the previous level standard image.
And S320, obtaining an image of the mask plate to be detected.
S330, taking the whole area of the image of the mask plate to be detected as an image of the area to be detected, calling a first-level standard image with a size which is not the smallest in the multi-level standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result.
S340, if the local image contains the stain image, taking the local image as a new to-be-detected region image, calling a next-level standard image of the comparison image as a new comparison image, comparing the new to-be-detected region image with the new to-be-detected region image, judging whether the local image of the to-be-detected region image contains the stain image according to a comparison result, and executing the step in a circulating mode until the called comparison image is the minimum-level standard image in the multi-level standard image, so that the position of the stain image in the to-be-detected mask plate image is obtained, and the stain quantity of the to-be-detected mask plate image is counted.
The positions of the stains can be represented by the positions of the holes of the mask plate covered by the stains, the number of the stains can be represented by the number of the holes of the mask plate covered by the stains, and the positions of the stains correspond to the number of the stains. And when one spot is detected, correspondingly counting the number of the spots by +1 so as to count the number of the spots of the image of the mask plate to be detected.
And S350, if the local image does not contain the dirt, comparing other local images in the image of the area to be detected with the comparison image, and judging whether the local image of the area to be detected contains the dirt image according to the comparison result.
Therefore, different from the above embodiments, the embodiment can not only locate the position of the stain, but also count the number of the stains, enrich the functions of the stain detection method of the mask plate, and have higher practicability.
The embodiment of the invention also provides stain detection equipment of the mask plate, which can be used for executing the stain detection method of the mask plate provided by any embodiment of the invention. Fig. 23 is a schematic structural view of a stain detection apparatus for a mask plate according to an embodiment of the present invention. Referring to fig. 23, the stain detection apparatus of the mask plate includes: a standard image setting module 510, an image acquisition module 520, a comparison module 530, and a location determination module 540. The standard image setting module 510 is configured to preset a group of multi-level standard images arranged from large to small in size; in the multi-level standard images, a first-level standard image is a local standard image of the mask plate to be detected, and the other levels of images in the standard images are local standard images of the previous-level standard image. The image obtaining module 520 is configured to obtain an image of the mask to be detected. The comparison module 530 is configured to use the whole area of the mask plate image to be detected as an image of an area to be detected, call a first-level standard image with a non-minimum size in the multi-level standard images as a comparison image to compare with the image of the area to be detected, and determine whether a local image of the area to be detected includes a stain image according to a comparison result. The position determining module 540 is configured to, if the local image includes a stain image, take the local image as a new image of the area to be detected, call a next-level standard image of the comparison image as a new comparison image, compare the new image with the new image of the area to be detected, determine whether the local image of the area to be detected includes the stain image according to a comparison result, and execute this step in a circulating manner until the called comparison image is a minimum-level standard image in the multi-level standard image, so as to obtain a position of the stain image in the image of the mask plate to be detected.
The stain detection device for the mask plate provided by the embodiment of the invention can execute the stain detection method for the mask plate provided by any embodiment of the invention, has corresponding functional modules and beneficial effects of the execution method, and is not described again.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A stain detection method of a mask plate is characterized by comprising the following steps:
presetting a group of multi-level standard images with sizes arranged from large to small; in the multi-level standard images, a first-level standard image is a local standard image of the mask plate to be detected, and the other levels of images in the standard images are local standard images of the previous-level standard image;
acquiring an image of a mask plate to be detected;
taking the whole area of the mask plate image to be detected as an image of the area to be detected, calling a primary standard image with a non-minimum size in the multi-stage standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image according to a comparison result;
if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling a next-level standard image of the comparison image as a new comparison image, comparing the new to-be-detected area image with the local image, judging whether the local image of the to-be-detected area image contains the stain image according to a comparison result, and executing the step circularly until the called comparison image is the minimum-level standard image in the multi-level standard images so as to obtain the position of the stain image in the to-be-detected mask plate image.
2. A method of detecting stains on a mask according to claim 1, wherein the multi-level standard images include a first level standard image, a second level standard image and a third level standard image which are arranged in a size from large to small;
after the mask plate image to be detected is obtained, the method comprises the following steps:
taking the whole area of the image of the mask plate to be detected as an image of an area to be detected, calling the first-level standard image as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result;
if the local image contains the stain image, taking the local image as a new to-be-detected area image, calling the second-level standard image as a new comparison image, comparing the new to-be-detected area image with the second-level standard image, and judging whether the local image of the to-be-detected area image contains the stain image or not according to a comparison result;
if the local image contains the stain image, taking the local image as a new to-be-detected region image, calling the third-level standard image as a new comparison image, comparing the new to-be-detected region image with the third-level standard image, and judging whether the local image of the to-be-detected region image contains the stain image or not according to a comparison result; and obtaining the stain image position in the image of the mask plate to be detected.
3. The method for detecting stains on a mask plate according to claim 1, further comprising:
if the local image does not contain the dirt, comparing other local images in the image of the area to be detected with the comparison image, and judging whether the local image of the area to be detected contains the dirt image according to the comparison result.
4. The stain detection method of a mask plate according to claim 3, wherein the image of the region to be detected comprises a plurality of local images, and the plurality of local images are arranged in an array;
comparing the local images in the to-be-detected region image with the comparison image in sequence along the row direction; or,
comparing the local images in the to-be-detected region image with the comparison image in sequence along the column direction; or,
the local images in the images of the area to be measured are sequentially compared with the comparison images along a spiral track; or,
and comparing the local images in the image of the area to be detected with the comparison image in sequence along the zigzag track.
5. The method for detecting the stain of the mask plate according to claim 1, wherein while obtaining the stain position of the image of the mask plate to be detected, the method further comprises:
and counting the stain quantity of the image of the mask plate to be detected.
6. A method of detecting stains on a mask according to claim 1, wherein the primary standard image having the smallest size includes an opening;
the partial image to be compared with the primary standard image of the smallest size includes an opening.
7. A method for detecting stains on a mask according to claim 1, wherein the local image of the region to be detected and the comparison image have the same shape and size.
8. A method of detecting stains on a mask according to claim 7, wherein the standard image comprises N x N openings, wherein N is a positive integer.
9. A method for detecting stains on a mask plate according to claim 7, wherein the shape of the standard image comprises: at least one of rectangular, fan-shaped, circular, and annular.
10. The utility model provides a spot check out test set of mask plate which characterized in that includes:
the standard image setting module is used for presetting a group of multi-level standard images with sizes arranged from large to small; in the multi-level standard images, a first-level standard image is a local standard image of a mask plate to be detected, and the other levels of images in the standard images are local standard images of a previous-level standard image;
the image acquisition module is used for acquiring an image of the mask plate to be detected;
the comparison module is used for taking the whole area of the mask plate image to be detected as an image of the area to be detected, calling a primary standard image with a non-minimum size in the multi-level standard images as a comparison image to be compared with the image of the area to be detected, and judging whether a local image of the area to be detected contains a stain image or not according to a comparison result;
and the position determining module is used for taking the local image as a new image of the area to be detected if the local image comprises a stain image, calling a next-level standard image of the comparison image as a new comparison image, comparing the new image with the new image of the area to be detected, judging whether the local image of the area to be detected comprises the stain image according to a comparison result, and circularly executing the step until the called comparison image is the minimum-level standard image in the multi-level standard images so as to obtain the position of the stain image in the image of the mask plate to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010130217.XA CN111275704B (en) | 2020-02-28 | 2020-02-28 | Method and equipment for detecting stains of mask plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010130217.XA CN111275704B (en) | 2020-02-28 | 2020-02-28 | Method and equipment for detecting stains of mask plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111275704A CN111275704A (en) | 2020-06-12 |
| CN111275704B true CN111275704B (en) | 2022-07-26 |
Family
ID=70999265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010130217.XA Active CN111275704B (en) | 2020-02-28 | 2020-02-28 | Method and equipment for detecting stains of mask plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111275704B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116475158B (en) * | 2023-06-20 | 2023-11-03 | 国网浙江省电力有限公司宁波供电公司 | Method for controlling washing of transformer oil sample container, washing device and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803244B (en) * | 2016-11-24 | 2019-09-03 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
| CN106898082B (en) * | 2017-03-15 | 2019-08-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
| CN110288040B (en) * | 2019-06-30 | 2022-02-11 | 北京华融塑胶有限公司 | Image similarity judging method and device based on topology verification |
| CN110766679B (en) * | 2019-10-25 | 2022-09-06 | 普联技术有限公司 | Lens contamination detection method and device and terminal equipment |
-
2020
- 2020-02-28 CN CN202010130217.XA patent/CN111275704B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111275704A (en) | 2020-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112750116B (en) | Defect detection method, device, computer equipment and storage medium | |
| KR101934151B1 (en) | Detection of defects embedded in noise for inspection in semiconductor manufacturing | |
| CN107920246B (en) | The gradient test method and device of camera module | |
| CN111246204A (en) | Relative brightness deviation-based dirt detection method and device | |
| CN106408583B (en) | A kind of multiple edge defect inspection method and device | |
| JP2005529388A (en) | Pattern inspection method | |
| CN106412573A (en) | Method and device for detecting lens stain | |
| CN111275704B (en) | Method and equipment for detecting stains of mask plate | |
| CN111612757A (en) | Screen crack detection method, device, equipment and storage medium | |
| JPH0526136B2 (en) | ||
| CN110208973B (en) | Method for detecting qualification of liquid crystal display screen | |
| CN113392455A (en) | House type graph scale detection method and device based on deep learning and electronic equipment | |
| CN116012330B (en) | Pole piece defect detection method, device, equipment and computer storage medium | |
| CN114140336B (en) | Infrared image-based dead pixel processing method and device | |
| JP5155938B2 (en) | Pattern contour detection method | |
| US11803961B2 (en) | Die-to-multi-die wafer inspection | |
| US11514580B2 (en) | Image processing circuit and method | |
| CN115830052A (en) | Method and device for extracting features of image of electronic scanning microscope | |
| CN109982073B (en) | Method and device for detecting optical axis of camera module | |
| CN114399733A (en) | Image detection method, device, equipment and storage medium | |
| JP2014135007A (en) | Flat panel display automatic unevenness detection device and automatic unevenness detection method | |
| Tchendjou et al. | Self-Healing Image Sensor Using Defective Pixel Correction Loop | |
| CN117934414B (en) | Wafer test early warning method | |
| CN114324168B (en) | Surface defect detection method and system | |
| CN112559314B (en) | Testing method and testing device for man-machine interaction interface |
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 |