CN113643264A - Image processing method for graphite boat whole boat image warping detection - Google Patents
Image processing method for graphite boat whole boat image warping detection Download PDFInfo
- Publication number
- CN113643264A CN113643264A CN202110952592.7A CN202110952592A CN113643264A CN 113643264 A CN113643264 A CN 113643264A CN 202110952592 A CN202110952592 A CN 202110952592A CN 113643264 A CN113643264 A CN 113643264A
- Authority
- CN
- China
- Prior art keywords
- image
- array
- graphite boat
- boat
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 51
- 229910002804 graphite Inorganic materials 0.000 title claims abstract description 51
- 239000010439 graphite Substances 0.000 title claims abstract description 51
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000001914 filtration Methods 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000003491 array Methods 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 2
- 235000012431 wafers Nutrition 0.000 description 27
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 18
- 229910052710 silicon Inorganic materials 0.000 description 18
- 239000010703 silicon Substances 0.000 description 18
- 230000008569 process Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000000623 plasma-assisted chemical vapour deposition Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 230000000007 visual effect 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image processing method for whole boat image fin detection of a graphite boat, which comprises a graphite boat connecting rod positioning method (101), an in-out furnace detection method (102), an image motion correction method (103) and a fin detection method (104), wherein the in-out furnace state of the graphite boat is detected by positioning the graphite boat connecting rod, the whole boat image motion correction and pretreatment are used as basic images for judging fins, and finally the judgment is carried out by using a threshold value to finish the image fin detection.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a processing method of images shot by a linear array camera.
Background
The automatic loading and unloading machine of the graphite boat is taken as a typical representative of automatic equipment in the photovoltaic manufacturing industry, is used for automatically loading silicon wafers into the graphite boat or automatically loading the silicon wafers in the graphite boat into a wafer basket before and after a PECVD (plasma enhanced chemical vapor deposition) process in the production process of solar cells, has the characteristics of high automation and production efficiency, reduction of manual contact pollution with the silicon wafers, great increase of stability of taking and placing the wafers and the like, and is considered as key equipment in the photovoltaic manufacturing industry by industry public. The silicon wafers are inserted into each boat page in the graphite boat by the loading and unloading robot, the silicon wafers are placed on the clamping points on the vertical boat grooves by the robot in a clinging and placing mode, the silicon wafers in one boat groove are required to be placed in parallel, however, as the clamping points on the boat grooves are worn or vibrated in the operation process, the parallel silicon wafers are in a herringbone state, and the wafers are lapped; if the lapping is not timely processed, after entering the PECVD, the silicon wafer with the lapping condition can become waste products after reaction, thus wasting energy and increasing the reject ratio of the silicon wafer. Meanwhile, after the PECVD process, the graphite boat is taken out of the boat, and in the process of transmitting the graphite boat to an upper wafer loader and a lower wafer loader, the conditions of warping, lapping and dropping of silicon wafers can be caused due to expansion and contraction of air or the carrying process of a mechanical arm in the PECVD, and the conditions of warping, lapping and dropping of the silicon wafers in the graphite boat can be caused in the process of transmitting the silicon wafers, if abnormal silicon wafers are not processed, the abnormal silicon wafers can be broken by the mechanical arm when the mechanical arm of the upper wafer loader and the lower wafer loader enters a boat groove to take the wafers, so that a large amount of economic loss is caused to a company producing solar silicon wafers. Most of current solar cell manufacturers adopt a manual detection method to detect the silicon wafers tightly inserted into each boat page in the graphite boat one by one to eliminate the situations of the silicon wafers tilting, falling and picking, the temperature of the graphite boat is not reduced completely during manual detection, the detection environment temperature is relatively high, and the work with high repeatability cannot be continuously and stably completed usually.
Disclosure of Invention
In order to realize the machine vision detection with rapidity, repeatability and intellectualization, the invention provides an image processing method for graphite boat whole boat image fin detection by shooting whole boat images by a linear array camera array, so as to realize the detection of the fin state by a computer, replace the detection of naked eyes and play the role of reducing the number of workers and increasing the efficiency, and the technical scheme of the invention is as follows: the method comprises a graphite boat connecting rod positioning method, an in-out furnace detection method, an image motion correction method and a warping detection method;
the method for positioning the graphite boat connecting rod comprises the following steps:
step S101, reading a whole boat image on a hard disk according to a command message, and storing the whole boat image as original data in a memory;
step S102, accumulating according to pixel values of each row of images to obtain a numerical value A, wherein the numerical value A is a one-dimensional array, and the size of the numerical value A is the height of the images;
step S103, carrying out mean filtering on the array A to obtain an array B with the same size;
and step S104, scanning the array B to obtain local peak data to form an array C, wherein the value C is a one-dimensional array, and the number of the connecting columns of the graphite boat is increased by 1.
The method for detecting the furnace charging and discharging comprises the following steps:
step S201, reading a result array C of the positioning method of the graphite boat connecting column;
step S202, solving the difference of the array C to obtain a displacement array D;
step S203, accumulating the first three items of the displacement array D to obtain data E, judging whether the state is in-out state or not through DoorInOut threshold value, the state which is more than the DoorInOut value is in-in state, the other states are out-of-furnace state, and the threshold DoorInOut value is a setting parameter.
The image motion correction method comprises the following steps:
step S301, reading an original Image0 of the memory;
step S302, carrying out Gaussian filtering on the original Image0 to obtain an Image 1;
step S303, performing Sobel filtering on the Image1 to obtain an Image 2;
step S304, carrying out binarization processing by using a threshold value Door2 to obtain a BW0 image;
step S305, scanning BW0 images according to lines, obtaining the numerical value of a first white point, and forming an array D;
step S306, solving the difference of the array D to obtain a difference array C;
in step 307, each row of images is shifted according to arrays C and D to form image BW 1.
The method for detecting the warped piece comprises the following steps:
step S401, reading the binary image BW1 after the motion correction processing as a base image for determining the warping;
step S402, acquiring a sub-image coordinate RECT of each inspection area according to the array C and the configuration parameters, wherein the sub-image coordinate RECT is an area array and comprises coordinates and length and width in the image; the configuration parameters are obtained by calibrating the cameras installed in the system and are changed by the relative position of each group of cameras and the relative position change of the cameras and the graphite boat;
step S403, obtaining a detection sub-image BW2 according to the sub-image coordinate RECT of the inspection area and the correction image BW 1;
step S404, processing a connected domain aiming at the sub-image BW2, carrying out opening and closing operation to obtain a connected domain area array, judging by using a threshold Door3, wherein the condition that the fin exists when the threshold is larger than the threshold, and otherwise, the condition that the fin does not exist;
and S405, looping the step S403 and the step S404, finishing judging the fin states of all the slots of the graphite boat, and outputting the result.
The invention has the beneficial effects that: by adopting the detection method, manual visual detection can be replaced, automatic detection is realized, the whole detection operation time is less than one second, the detection accuracy is improved, and the whole production efficiency is greatly improved.
Drawings
FIG. 1 is a schematic view of a graphite boat according to the present invention;
FIG. 2 is an overall image processing flow diagram of the present invention;
FIG. 3 is a flowchart of a method for positioning a connecting column of a graphite boat according to an embodiment of the present invention;
FIG. 4A, B is a full boat image of a graphite boat, FIG. 4A is a discharge image, and FIG. 4B is a charge image according to an embodiment of the present invention;
FIG. 4C is a flowchart illustrating a method for detecting the status of the graphite boat entering and exiting the furnace according to an embodiment of the present invention;
FIG. 5 is a flowchart of an image motion correction method according to an embodiment of the present invention;
fig. 6 is a flowchart of a warpage detection method according to an embodiment of the present invention.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
Referring to fig. 1, the graphite boat is assembled by a graphite boat piece 1 and a ceramic double-head screw 2 to form a shape of multiple grooves and multiple columns, thereby forming a plurality of unit groove positions 3 for placing silicon wafers. The whole boat image is a spliced image acquired by a multi-path linear array camera array through internal triggering, the whole boat of the graphite boat is imaged at high resolution, the size of the image is 8192 ANG 9800, and the directions of the X, Y coordinate axes of the image are shown in figure 1.
The Y-axis resolution of the image changes along with the change of the motion speed of the graphite boat in the motion direction, and the deformation of the image in the Y-axis direction is generated; the image resolution of the line camera in the X-axis direction is unchanged, but image distortion is generated along with the shake and offset of the graphite boat during the orbital motion.
The image processing method provided by the invention comprises a graphite boat connecting rod positioning method 101, an in-and-out furnace detection method 102, an image motion correction method 103 and a warping detection method 104, and a detailed image processing flow chart is shown in figure 2.
Specifically, the method for positioning the graphite boat connecting rod obtains a one-dimensional array by image integration in the X direction, and obtains the position of the graphite boat connecting column in the Y axis direction through peak value judgment, so as to obtain the position of the graphite boat connecting column, and the processing flow chart is shown in fig. 3, and includes:
step S101, reading a whole boat image on a hard disk according to the command message, wherein the file format is JPG compressed image, decompressing to form W H (W is width, H is length) original image data, and storing the original image data in a memory;
step S102, accumulating according to the pixel value of each line of image to obtain a value A, wherein the value A is a one-dimensional array, and the size is the height of the image, and the specific formula is as follows:
…
step S103, carrying out mean filtering on the array A to obtain an array B with the same size, wherein the specific formula is as follows:
…
and step S104, scanning the array B to obtain local peak data to form an array C, wherein the value C is a one-dimensional array, and the number of the connecting columns of the graphite boat is increased by 1.
Specifically, the furnace in-out detection method judges the furnace out-of-furnace and in-furnace states of the graphite boat according to the position array C of the graphite boat connecting column, the difference of the images of the graphite boat in-out of the furnace is shown in FIGS. 4A and 4B, and the detailed processing flow chart is shown in FIG. 4C, and comprises the following steps:
step S201, reading a result array C of the positioning method of the graphite boat connecting column;
step S202, solving the difference of the array C to obtain a displacement array D, wherein the specific formula is as follows:
Di＝Ci+1-Ci
step S203, accumulating the first three items of the displacement array D to obtain data E, judging whether the state is in-out state or not through DoorInOut threshold value, the state which is more than the DoorInOut value is in-in state, the other states are out-of-furnace state, and the threshold DoorInOut value is a setting parameter.
E＝C1+C2+C3
E is more than or equal to DoorInOut charging state
E < DoorInOut tapping state
Specifically, the image motion correction method extracts the graphite boat edge on the original image to obtain the segment image distortion correction parameters; and applying the parameter to a binary image obtained by a Sobel and threshold method to obtain a corrected binary image, wherein a detailed flow chart is shown in FIG. 5 and comprises the following steps:
step S301, reading an original Image0 of the memory;
in step S302, the original Image0 is gaussian filtered to obtain Image1, where gaussian filtering is a general Image processing method and is mainly used to remove noise.
In step S303, Image1 is subjected to Sobel filtering to obtain Image2, which is a general Image processing method for obtaining an object edge.
In step S304, a threshold value Door2 is used to perform binarization processing, which is a general image processing method for obtaining the presence or absence of an object, to obtain a BW0 image.
Step S305, scanning BW0 images according to lines, obtaining the numerical value of a first white point, and forming an array D;
step S306, solving the difference of the array D to obtain a difference array C, wherein the difference formula is as follows:
Di＝Ci+1-Ci
in step 307, each row of images is shifted according to arrays C and D to form image BW 1.
Specifically, the fin detection method obtains a fin detection area on the motion correction binary image BW1, and performs determination by using a method of the size of the area of the connected domain, and the detailed flowchart is shown in fig. 6, and includes:
step S401, reading the binary image BW1 after the motion correction processing as a base image for determining the warping;
step S402, acquiring a sub-image coordinate RECT of each inspection area according to the array C and the configuration parameters, wherein the sub-image coordinate RECT is an area array and comprises coordinates and length and width in the image; the configuration parameters are obtained by calibrating the cameras installed in the system and are changed by the relative position of each group of cameras and the relative position change of the cameras and the graphite boat;
step S403, obtaining a detection sub-image BW2 according to the sub-image coordinate RECT of the inspection area and the correction image BW 1; BW2 is a set of small images, specifically in numbers equal to or greater than the number of graphite boat slots in rows, which are essentially sub-images of the edge regions of each wafer.
In step S404, connected component processing, which is a general algorithm for image processing, is performed on the sub-image BW2 in order to obtain a shape area of an object. And performing on-off operation to obtain a connected domain area array S, and selecting the maximum value S in the array SmaxJudging by using a threshold value Door3, wherein the situation that the fin exists when the threshold value Door3 is larger than the threshold value is judged, and the situation that the fin does not exist is judged if the threshold value Door3 is not judged;
Smaxdoor3 warped piece
Smax< Door3 without fin
And S405, looping the step S403 and the step S404, finishing judging the fin states of all the slots of the graphite boat, and outputting the result.
The foregoing detailed description is given by way of example only, and is provided to better enable one skilled in the art to understand the patent, and is not intended to limit the scope of the patent; any modification or modification that is substantially the same or equivalent to the technical content of the technical means disclosed in the present patent is included in the scope of the present patent.
Claims (1)
1. An image processing method for detecting full-boat image warping of a graphite boat is characterized by comprising the following steps: the method comprises a graphite boat connecting rod positioning method (101), an in-out furnace detection method (102), an image motion correction method (103) and a warping detection method (104);
the method for positioning the graphite boat connecting rod comprises the following steps:
step S101, reading a whole boat image on a hard disk according to a command message, and storing the whole boat image as original data in a memory;
step S102, accumulating according to pixel values of each row of images to obtain a numerical value A, wherein the numerical value A is a one-dimensional array, and the size of the numerical value A is the height of the images;
step S103, carrying out mean filtering on the array A to obtain an array B with the same size;
step S104, scanning the array B to obtain local peak data to form an array C, wherein the value C is a one-dimensional array and the number of the connecting columns of the graphite boat is increased by 1;
the method for detecting the furnace charging and discharging comprises the following steps:
step S201, reading a result array C of the positioning method of the graphite boat connecting column;
step S202, solving the difference of the array C to obtain a displacement array D;
step S203, accumulating the first three items of the displacement array D, judging whether the state is a furnace entrance state or not through a DoorlnOut threshold value, wherein the state is a furnace entrance state if the value is larger than the DoorlnOut value, and the other states are furnace exit states;
the image motion correction method comprises the following steps:
step S301, reading an original Image0 of the memory;
step S302, carrying out Gaussian filtering on an original Image lmage0 to obtain an Image 1;
step S303, performing Sobel filtering on the Image1 to obtain an Image 2;
step S304, carrying out binarization processing by using a threshold value Door2 to obtain a BW0 image;
step S305, scanning BW0 images according to lines, obtaining the numerical value of a first white point, and forming an array D;
step S306, solving the difference of the array D to obtain a difference array C;
step 307, moving each line of images according to the arrays C and D to form an image BW 1;
the method for detecting the warped piece comprises the following steps:
step S401, reading the binary image BW1 after the motion correction processing as a base image for determining the warping;
step S402, acquiring a sub-image coordinate RECT of each inspection area according to the array C and the configuration parameters, wherein the sub-image coordinate RECT is an area array and comprises coordinates and length and width in the image; the configuration parameters are obtained by calibrating the cameras installed in the system and are changed by the relative position of each group of cameras and the relative position change of the cameras and the graphite boat;
step S403, obtaining a detection sub-image BW2 according to the sub-image coordinate RECT of the inspection area and the correction image BW 1;
step S404, processing a connected domain aiming at the sub-image BW2, carrying out opening and closing operation to obtain a connected domain area array, judging by using a threshold Door3, wherein the condition that the fin exists when the threshold is larger than the threshold, and otherwise, the condition that the fin does not exist;
and S405, looping the step S403 and the step S404, finishing judging the fin states of all the slots of the graphite boat, and outputting the result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952592.7A CN113643264A (en) | 2021-08-18 | 2021-08-18 | Image processing method for graphite boat whole boat image warping detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952592.7A CN113643264A (en) | 2021-08-18 | 2021-08-18 | Image processing method for graphite boat whole boat image warping detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113643264A true CN113643264A (en) | 2021-11-12 |
Family
ID=78422812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110952592.7A Pending CN113643264A (en) | 2021-08-18 | 2021-08-18 | Image processing method for graphite boat whole boat image warping detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643264A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116538918A (en) * | 2023-04-07 | 2023-08-04 | 钛玛科（北京）工业科技有限公司 | Lithium battery material measurement correction method and device |
| CN116740073A (en) * | 2023-08-16 | 2023-09-12 | 江苏森标科技有限公司 | Solar cell defect detection method and system based on visual image of graphite boat |
-
2021
- 2021-08-18 CN CN202110952592.7A patent/CN113643264A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116538918A (en) * | 2023-04-07 | 2023-08-04 | 钛玛科（北京）工业科技有限公司 | Lithium battery material measurement correction method and device |
| CN116740073A (en) * | 2023-08-16 | 2023-09-12 | 江苏森标科技有限公司 | Solar cell defect detection method and system based on visual image of graphite boat |
| CN116740073B (en) * | 2023-08-16 | 2023-10-20 | 江苏森标科技有限公司 | Solar cell defect detection method and system based on visual image of graphite boat |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113643264A (en) | Image processing method for graphite boat whole boat image warping detection | |
| US8483476B2 (en) | Photovoltaic cell manufacturing | |
| KR101716817B1 (en) | Image creation method, substrate inspection method, storage medium for storing program for executing image creation method and substrate inspection method, and substrate inspection apparatus | |
| US7248732B2 (en) | Pattern inspection method and inspection apparatus | |
| JP2006200972A (en) | Image defect inspection method, image defect inspection device, and external appearance inspection device | |
| JPH0722166B2 (en) | Pellet recognition method for die bonder etc. | |
| JP2007218638A (en) | Crack inspection device of polycrystalline semiconductor wafer and crack inspection method | |
| US20150254827A1 (en) | Image inspection apparatus and image inspection method | |
| JP2000131240A (en) | Pattern comparing method, and device for visual inspection | |
| CN112635346B (en) | Wafer inspection method, semiconductor inspection apparatus, and storage medium | |
| US7697130B2 (en) | Apparatus and method for inspecting a surface of a wafer | |
| CN113034435A (en) | Defect detection method | |
| JP2010043941A (en) | Image inspection apparatus and image inspection method | |
| CN109698139A (en) | The real-time acquisition system of wafer defect optical photograph and acquisition method | |
| JP5917492B2 (en) | Appearance inspection method and apparatus | |
| KR101448967B1 (en) | Methods and apparatus for simultaneously inspecting multiple array regions having different pitches | |
| CN104319246A (en) | Detection method and system for surface of silicon slice in product manufacturing process | |
| CN117805126A (en) | In-boat defect online detection system and detection method of graphite boat for silicon wafer | |
| CN110927064B (en) | Intelligent efficient sagger detection device based on visual system | |
| CN115360133A (en) | Multi-stage automatic wafer alignment method for semiconductor equipment and semiconductor equipment | |
| TW447052B (en) | Method for recognizing minute work piece and pickup apparatus using the same | |
| CN101092034A (en) | Adjusting device for facility of handling wafers, and adjusting method for facility of handling wafers | |
| CN112038248A (en) | Method and system for establishing semiconductor defect scanning program | |
| EP0494635A2 (en) | Pattern recognition method | |
| KR102178869B1 (en) | Apparatus and method for inspecting substrates, and apparatus for treating substrates using the same |
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 |