CN114972317A - Square crystal grain placement planning method - Google Patents
Square crystal grain placement planning method Download PDFInfo
- Publication number
- CN114972317A CN114972317A CN202210714903.0A CN202210714903A CN114972317A CN 114972317 A CN114972317 A CN 114972317A CN 202210714903 A CN202210714903 A CN 202210714903A CN 114972317 A CN114972317 A CN 114972317A
- Authority
- CN
- China
- Prior art keywords
- crystal grain
- row
- placement
- image
- frames
- 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
- 239000013078 crystal Substances 0.000 title claims abstract description 185
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 230000000877 morphologic effect Effects 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000012163 sequencing technique Methods 0.000 claims abstract description 9
- 238000005260 corrosion Methods 0.000 claims abstract description 7
- 230000007797 corrosion Effects 0.000 claims abstract description 7
- 230000010339 dilation Effects 0.000 claims description 7
- 230000001174 ascending effect Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 101100328886 Caenorhabditis elegans col-2 gene Proteins 0.000 claims description 3
- 101100328884 Caenorhabditis elegans sqt-3 gene Proteins 0.000 claims description 3
- 235000002566 Capsicum Nutrition 0.000 claims description 3
- 239000006002 Pepper Substances 0.000 claims description 3
- 235000016761 Piper aduncum Nutrition 0.000 claims description 3
- 235000017804 Piper guineense Nutrition 0.000 claims description 3
- 235000008184 Piper nigrum Nutrition 0.000 claims description 3
- 238000005530 etching Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 150000003839 salts Chemical class 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 2
- 244000203593 Piper nigrum Species 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 3
- 241000722363 Piper Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate 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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/30148—Semiconductor; IC; Wafer
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a square crystal grain placement planning method, which comprises the steps of sequentially carrying out median filtering and binarization threshold segmentation on an image to be processed, carrying out morphological operation of corrosion and expansion, carrying out contour detection on the processed image, judging whether the contour of the image meets the requirements, and finally carrying out the steps of existing crystal grain arrangement detection, placement frame central point arrangement and sequencing, placement frame inspection and the like to obtain a final crystal grain placement planning result image. The square crystal grain placement planning method is simple and efficient, can realize arrangement planning of the positions of the crystal grains to be placed aiming at the existing crystal grains, and has the characteristics of high detection and judgment speed, high efficiency, good accuracy, strong stability, simplicity, convenience and high efficiency.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a square crystal grain placement planning method.
Background
In recent years, the integrated circuit industry is vigorously developed by the nation, and the problem of 'neck clamping' is solved. In the manufacturing process of the integrated circuit assembly, the crystal grains are sorted by using a crystal grain sorting machine, the crystal grains are picked from the picking platform and are transferred to the crystal bonding position of the circuit substrate on the crystal bonding platform in a classification mode, and the placing position is required to be free from other crystal grains and dirt.
At present, the known die placement methods are all used for planning the die placement positions by calculation for a platform without dies, but an effective die placement planning method is not available for the existing dies on the platform. Therefore, it is necessary to develop a method for planning the positions of the dies to be placed according to the arrangement of the existing dies.
Disclosure of Invention
The invention aims to: a method for planning the placement of square dies is provided to solve the above drawbacks.
In order to achieve the above purpose, the invention provides the following technical scheme:
a square crystal grain placement planning method is characterized by comprising the following steps:
s1, image preprocessing: the method comprises the steps that an industrial camera is used for shooting a crystal grain image on an existing crystal grain platform, then the shot image to be processed is input, and median filtering and binarization threshold segmentation processing are carried out on the image to be processed in sequence; then carrying out morphological operation of firstly corroding and then expanding; finally, carrying out contour detection on the processed image to obtain the center point coordinates of each suspected crystal grain, and detecting whether the length and width of the contour of the processed image of the suspected crystal grain are within a limited range, if so, carrying out the next step; if not, the image contour is not considered as a crystal grain, and the image contour does not enter the approved arrangement detection of the existing crystal grain;
s2, detecting the existing crystal grain arrangement: under an image coordinate system, firstly finding out a crystal grain with the minimum row coordinate minRow and a crystal grain with the maximum row coordinate maxRow of a center point; setting the standard height of crystal grains as H, detecting from minRow to maxRow by taking H/2 as a step length, and considering a plurality of crystal grains in the same range as crystal grains in the same row, wherein the crystal grains in the same row are sorted according to the ascending order of column coordinates;
s3, arranging and sequencing the center points of the placement frames:
(1) finding the last crystal grain and the serial number thereof of the existing crystal grains in each row according to the row-column coordinates of the existing crystal grains, and calculating the number of the crystal grains in each row;
(2) finding a row with the largest number of the existing crystal grains, arranging placing frames in the row, wherein the placing frames with the largest number are arranged among the existing crystal grains, on the left side of the first crystal grain in the row and on the right side of the tail crystal grain in the row, and calculating the center point coordinate of each placing frame;
(3) taking a plurality of placing frames in a row with the largest number of existing crystal grains as a standard, respectively arranging detection frames upwards and downwards, and obtaining coordinates of center points of the placing frames in other rows;
(4) after the arrangement of the central points of the placing frames is finished, the placing frames are sequenced in sequence or in an S shape;
s4, placing box checking: after the arrangement of the central points of all the placing frames is finished, the arrangement of the placing frames is finished according to the coordinates of the central points and the set widths and heights of the placing frames, the placing frames are checked one by one, and whether crystal grains can be placed in the placing frames is judged according to the set placing conditions and the set precision levels, so that a final crystal grain placing planning result graph is obtained.
Preferably, in step S1, the contour detection specifically includes: and detecting the contour on the image by using a contour detection function FindContours in an EmguCV image processing library, wherein the function can return all detected contours and information such as corresponding center point coordinates, length and width, and the like, sequentially and preliminarily screening the detected contours, comparing the length and width of the contour to be detected with the length and width of a standard crystal grain according to the set precision grade, and if the length and width of the contour to be detected are in a limited range, determining that the contour to be detected is an approved shot crystal grain and then carrying out next processing on the contour to be detected.
Preferably, in step (1) of S3, the specific steps are: subtracting the row coordinate of each existing crystal grain from the row coordinate of the existing crystal grain before the existing crystal grain, wherein if the result is less than 0, the existing crystal grain is the last crystal grain in the row where the existing crystal grain is located, and thus the last crystal grain in each row and the serial number of the existing crystal grain are obtained; and subtracting the serial number of the last crystal grain in the last row from the serial number of the last crystal grain in each row to obtain the number of the crystal grains in the row.
Preferably, in step (2) of S3, the specific steps are:
setting row-column coordinates of the first crystal grain in the row as (row1, col1), setting the transverse distance between the central points of two adjacent crystal grains at the left and right as space X, setting the image edge to leave space X/2 vacant space, calculating the number n1 of the placement frames which can be arranged at the left side of the first crystal grain,
then n1 ═ Round ((col1-space x/2)/(space x) (1);
wherein Round is an integer function; thereby calculating the coordinates of the center point of each placing frame on the left side of the first crystal grain;
secondly, detecting crystal grains one by one, adding each existing crystal grain position to the row placing frame list, calculating the interval between the two crystal grains as interval according to the coordinates of the central points of the adjacent crystal grains, judging whether a spare position is arranged between the two crystal grains to arrange a placing frame,
then n ═ Round (interval/space x) (2);
if n is more than or equal to 2, n-1 placing frames can be arranged between the two crystal grains, and the coordinates of the center points of the n-1 placing frames are calculated; if n <2, it indicates that the gap between the two dies cannot be arranged with a placement frame;
thirdly, setting the coordinates of the last crystal grain in the line as (row2, col2) and the width of the image as width, calculating the number n2 of the placement frames which can be arranged on the right side of the last crystal grain,
then n2 ═ Round ((width-col2-space x/2)/space x) (3);
from this, the coordinates of the center point of each placement box to the right of the last die are calculated.
Preferably, in step (3) of S3, the specific steps are: after the arrangement of the placement frames in one row with the most crystal grains is finished, setting the row to have N placement frames in total, setting the longitudinal distance between the central points of two vertically adjacent crystal grains as space Y, and respectively arranging the placement frames upwards and downwards frame by taking the placement frames in the row as a standard;
nUp＝Round((row(i)-spaceY)/spaceY),i＝1,2,...,N (4)，
nDown＝Round((height-row(i)-spaceY)/spaceY),i＝1,2,...,N (5)，
where row (i) represents the line coordinates of the center point of the standard placement frames one by one, height represents the height of the image, nUp placement frames can be placed upwards, and nwown placement frames can be placed downwards, and the center point coordinates of the other line placement frames are obtained accordingly.
Preferably, in step S4, the placement conditions include whether the placement frame contains existing crystal grains, whether the placement frame contains dirt, the number of white dots contained, and the number of edge black dots contained.
Preferably, in step S1, the industrial camera has a camera system capable of clearly imaging the existing die and has a resolution of 1280 × 960.
Preferably, in step S1, the median filtering process includes: setting the gray value of each pixel point as the median of the gray values of all the pixel points in a certain neighborhood window of the point, thereby protecting the edge information and removing the salt and pepper noise; the point is typically a 3 x 3 or 5 x 5 region in some neighborhood.
Preferably, in step S1, the binarization threshold dividing process specifically includes: a user self-defines a binary threshold, and sets the pixel with the gray value larger than the threshold as white, wherein the gray value of the white is 255; pixels smaller than or equal to the threshold are set to black, and the gray value of black is 0, whereby the image is processed into a binary image having only two values.
Preferably, in step S1, the morphological operation of erosion and then expansion includes:
(1) firstly, etching operation is carried out, 5 multiplied by 5 structural elements are used, the central points of the structural elements are used for scanning each pixel of the image, and the structural elements and the covered parts are subjected to AND operation, if the results are all 1, the pixel value is kept as the original pixel value; otherwise, the value becomes 0; corroding to eliminate noise points smaller than structural elements on the image;
(2) then, performing a dilation operation, using a 5 × 5 structural element, scanning each pixel of the image by using a central point of the structural element, and performing an and operation on the structural element and a part covered by the structural element, wherein if the results are all 0, the pixel value is 0; otherwise, it is 255; the dilation operation fills holes smaller than the structural elements in the image; through morphological operation of corrosion before expansion, the aims of eliminating noise points and removing redundant details can be achieved.
The invention has the beneficial effects that:
according to the square crystal grain placement planning method, the median filtering processing is performed on the image to be processed in sequence, so that stray noise points are eliminated, the noise is effectively suppressed, and the details of the image can be kept; the binarization threshold segmentation processing and the morphological operation of corrosion first and then expansion are carried out, so that small redundant points in an image can be eliminated, bright details smaller than structural elements are inhibited, tiny connection among individual adjacent grains is eliminated, and grain boundaries are smoothed without changing the area of the grain boundaries; and carrying out contour detection on the processed image, judging whether the image contour meets the requirements or not, and obtaining the specific position coordinates of the existing crystal grains. And then, realizing the maximum planning of the placing quantity of the placing frames in the platform image range by the existing crystal grain arrangement detection, the placing frame central point arrangement and sequencing and the placing frame inspection, and judging whether the crystal grains can be placed in the placing frames. The square crystal grain placement planning method is simple and efficient, can realize arrangement planning of the positions of the crystal grains to be placed aiming at the existing crystal grains, and has the characteristics of high detection and judgment speed, high efficiency, good accuracy, strong stability, simplicity, convenience and high efficiency.
Drawings
FIG. 1: the method comprises the steps of obtaining an image to be processed;
FIG. 2: the image after median filtering processing of the embodiment of the invention;
FIG. 3: the image after the binarization threshold segmentation processing of the embodiment of the invention is carried out;
FIG. 4: the image after morphological operation processing of the embodiment of the invention;
FIG. 5: the finally formed crystal grain placement planning result graph in the embodiment of the invention.
Detailed Description
The present invention is further described with reference to the following examples, which are intended to be illustrative and illustrative only, and various modifications, additions and substitutions for the specific embodiments described herein may be made by those skilled in the art without departing from the spirit of the invention or exceeding the scope of the claims.
Example 1:
in an actual industrial production line, parameters such as the standard size (mum), the standard gap (mum), the pixel equivalent (mum/pixel) and the like of crystal grains are known.
As shown in fig. 1-5, the square die placement planning method of the present invention specifically includes the following steps:
s1, image preprocessing: the method comprises the steps of utilizing an industrial camera with a resolution of 1280 x 960 and a shooting system capable of clearly imaging existing crystal grains to shoot crystal grain images on an existing crystal grain platform, and inputting shot images to be processed. Fig. 1 is a diagram of an image to be processed acquired in the present embodiment.
Then, carrying out median filtering processing on the image to be processed in sequence, wherein the specific process of the median filtering processing is as follows: setting the gray value of each pixel point as the median of the gray values of all the pixel points in a certain neighborhood window of the point, thereby protecting edge information and removing salt and pepper noise; the point is typically a 3 x 3 or 5 x 5 region in some neighborhood. Fig. 2 is an image after the median filtering processing of the present embodiment, and as shown in fig. 2, after the median filtering processing, stray noise points can be eliminated, so that the details of the image can be maintained while the noise is effectively suppressed.
Then, the image after the median filtering processing is subjected to binarization threshold segmentation processing and morphological operation of corrosion first and expansion second.
The specific process of the binarization threshold segmentation processing is as follows: a user self-defines a binary threshold, and sets the pixel with the gray value larger than the threshold as white, wherein the gray value of the white is 255; pixels smaller than or equal to the threshold are set to black, and the gray value of black is 0, whereby the image is processed into a binary image having only two values.
The specific process of morphological operation of corrosion first and then expansion is as follows: (1) firstly, etching operation is carried out, 5 multiplied by 5 structural elements are used, the central points of the structural elements are used for scanning each pixel of the image, and the structural elements and the covered parts are subjected to AND operation, if the results are all 1, the pixel value is kept as the original pixel value; otherwise, the value becomes 0; corroding to eliminate noise points smaller than structural elements on the image; (2) then, performing a dilation operation, using a 5 × 5 structural element, scanning each pixel of the image by using a central point of the structural element, and performing an and operation on the structural element and a part covered by the structural element, wherein if the results are all 0, the pixel value is 0; otherwise, it is 255; the dilation operation fills holes smaller than the structural elements in the image; through morphological operation of corrosion before expansion, the aims of eliminating noise and removing redundant details can be achieved
Fig. 3 is an image after the binarization threshold segmentation processing of the present embodiment, and fig. 4 is an image after the morphological operation processing of the present embodiment. As shown in fig. 3 and 4, after the binarization threshold segmentation and the morphological operation processing, small redundant points can be eliminated, bright details smaller than structural elements can be suppressed, micro-connection between individual adjacent grains can be eliminated, and grain boundaries can be smoothed without changing the area.
And finally, carrying out contour detection on the processed image, detecting the contour of the image by using a contour detection function FindContours in an EmguCV image processing library, returning all detected contours and corresponding information such as center point coordinates, length and width and the like by the function, sequentially carrying out primary screening on the detected contours, comparing the length and width of the contour to be detected with the length and width of a standard crystal grain according to the set precision level, and if the length and width of the contour to be detected are within a limited range, considering the contour to be the approved shot crystal grain and carrying out next processing on the contour to be detected.
S2, detecting the existing crystal grain arrangement:
under an image coordinate system, firstly finding out a crystal grain with the minimum row coordinate (minRow) and a crystal grain with the maximum row coordinate (maxRow) of a central point; and setting the standard height of the crystal grains as H (pixel), detecting from minRow to maxRow by taking H/2 as a step length, wherein a plurality of crystal grains in the same range are regarded as the same line of crystal grains, and the same line of crystal grains are sorted according to the ascending order of column coordinates, so that the integral serial number of the detected existing crystal grains is obtained.
S3, arranging and sequencing the center points of the placement frames:
(1) and finding the last crystal grain and the serial number thereof of the existing crystal grains in each row according to the row and column coordinates of the existing crystal grains, and calculating the number of the crystal grains in each row. The method comprises the following specific steps: subtracting the row coordinate of each existing crystal grain from the row coordinate of the existing crystal grain before the existing crystal grain, wherein if the result is less than 0, the existing crystal grain is the last crystal grain in the row where the existing crystal grain is located, and thus the last crystal grain in each row and the serial number of the existing crystal grain are obtained; and subtracting the serial number of the last crystal grain in the last row from the serial number of the last crystal grain in each row to obtain the number of the crystal grains in the row.
(2) Finding a row with the largest number of the existing crystal grains, arranging the placement frames in the row, including arranging the largest number of the placement frames among the existing crystal grains, on the left side of the first crystal grain in the row and on the right side of the end crystal grain in the row, and calculating the center point coordinate of each placement frame. The method comprises the following specific steps:
firstly, setting row and column coordinates of the first crystal grain in the row as (row1, col1) (row and column coordinates in an image coordinate system), setting the transverse distance between the central points of two adjacent crystal grains at the left and the right as space X (pixel), setting the margin of the image as space X/2, calculating the number n1 of placing frames which can be arranged at the left side of the first crystal grain,
then n1 ═ Round ((col1-space x/2)/(space x) (1);
wherein Round is an integer function; thereby calculating the coordinates of the center point of each placement frame on the left side of the first die.
Secondly, detecting crystal grains one by one, adding each existing crystal grain position to the row placing frame list, calculating the interval between the two crystal grains as interval according to the coordinates of the central points of the adjacent crystal grains, judging whether a spare position is arranged between the two crystal grains to arrange a placing frame,
then n ═ Round (int erval/space x) (2);
if n is more than or equal to 2, n-1 placing frames can be arranged between the two crystal grains, and the coordinates of the center points of the n-1 placing frames are calculated; if n <2, it means that the gap between the two grains cannot be arranged with the placement frame.
Let the last crystal grain row-column coordinate of the row be (row2, col2) (row-column coordinate under image coordinate system), the width of the image be width (pixel), and calculate the number n2 of the placement frames that can be arranged on the right side of the last crystal grain,
then n2 ═ Round ((width-col2-space x/2)/space x) (3);
from this, the coordinates of the center point of each placement box to the right of the last die are calculated.
(3) And respectively arranging the detection frames upwards and downwards by taking a plurality of placing frames in a row with the largest number of the existing crystal grains as a standard, and obtaining the coordinates of the center points of the placing frames in other rows. The method comprises the following specific steps: after the arrangement of the placement frame in the row with the most crystal grains is finished, setting the row to have N placement frames, wherein the longitudinal distance between the central points of the two adjacent crystal grains is space Y (pixel), and the placement frames are respectively arranged upwards and downwards frame by taking the row placement frame as a standard;
nUp＝Round((row(i)-spaceY)/spaceY),i＝1,2,...,N (4)，
nDown＝Round((height-row(i)-spaceY)/spaceY),i＝1,2,...,N (5)，
where row (i) represents the row coordinates of the center point of the standard placement frame by standard, height represents the height of the image, nUp placement frames can be placed upward, and nwown placement frames can be placed downward, and thereby the coordinates of the center points of the other row placement frames are obtained.
(4) And after the arrangement of the center points of the placing frames is finished, sequencing the placing frames in sequence or S-shaped sequencing. If the sequential sorting is required, each row is sorted according to the ascending coordinates of the central point columns of the placement boxes. And if S-shaped sorting is required, sorting the odd rows in an ascending order according to the central point column coordinates of the placing frame, and sorting the even rows in a descending order according to the central point column coordinates of the placing frame.
S4, placing box checking:
after the arrangement of the central points of all the placing frames is finished, the arrangement of the placing frames is finished according to the coordinates of the central points and the set widths (unit pixel) and heights (unit pixel), the placing frames are checked one by one, whether crystal grains can be placed in the placing frames is judged according to the set placing conditions and the set precision levels, and therefore a final crystal grain placing planning result graph is obtained. The placing conditions comprise whether the placing frame contains the existing crystal grains or not, whether the placing frame contains dirt or not, the number of white points contained in the placing frame and the number of edge black points contained in the placing frame. Fig. 5 is a diagram illustrating the result of the placement planning of the die finally formed in the present embodiment. As shown in fig. 5, the figure visually shows a placement box that is planned on a platform of existing dice. The serial numbers of the placing frames, the coordinates of the corresponding central points, whether the crystal grains can be placed and other information can be conveniently counted.
According to the square crystal grain placement planning method, the maximum planning of the placement number of the placement frames in the platform image range is realized through image preprocessing, existing crystal grain arrangement detection, placement frame central point arrangement and sequencing and placement frame inspection, and whether crystal grains can be placed in the placement frames is judged. The square crystal grain placement planning method is simple and efficient, can realize arrangement planning of the positions of the crystal grains to be placed aiming at the existing crystal grains, and has the characteristics of high detection and judgment speed, high efficiency, good accuracy, strong stability, simplicity, convenience and high efficiency.
The foregoing is an illustrative description of the invention, and it is clear that the specific implementation of the invention is not restricted to the above-described manner, but it is within the scope of the invention to apply the inventive concept and solution to other applications without substantial or direct modification.
Claims (10)
1. A square crystal grain placement planning method is characterized by comprising the following steps:
s1, image preprocessing:
the method comprises the steps that an industrial camera is used for shooting a crystal grain image on an existing crystal grain platform, then the shot image to be processed is input, and median filtering and binarization threshold segmentation processing are carried out on the image to be processed in sequence; then carrying out morphological operation of firstly corroding and then expanding; finally, carrying out contour detection on the processed image to obtain the center point coordinates of each suspected crystal grain, and detecting whether the length and width of the contour of the processed image of the suspected crystal grain are within a limited range, if so, carrying out the next step; if not, the image contour is not considered as a crystal grain, and the image contour does not enter the approved arrangement detection of the existing crystal grain;
s2, detecting the existing crystal grain arrangement:
under an image coordinate system, firstly finding out a crystal grain with the minimum row coordinate minRow and a crystal grain with the maximum row coordinate maxRow of a center point; setting the standard height of crystal grains as H, detecting from minRow to maxRow by taking H/2 as step length, and considering a plurality of crystal grains in the same range as crystal grains in the same row, wherein the crystal grains in the same row are sorted according to the ascending order of column coordinates;
s3, arranging and sequencing the center points of the placement frames:
(1) finding the last crystal grain and the serial number thereof of the existing crystal grains in each row according to the row-column coordinates of the existing crystal grains, and calculating the number of the crystal grains in each row;
(2) finding a row with the maximum number of the existing crystal grains, and arranging the placement frames in the row, wherein the placement frames with the maximum number are arranged among the existing crystal grains, on the left side of the first crystal grain in the row and on the right side of the crystal grain at the tail end of the row, so that the center point coordinate of each placement frame is calculated;
(3) taking a plurality of placing frames in a row with the largest number of existing crystal grains as a standard, respectively arranging detection frames upwards and downwards, and obtaining coordinates of center points of the placing frames in other rows;
(4) after the arrangement of the central points of the placing frames is finished, sequencing the placing frames in sequence or S shape;
s4, placing box checking:
after the arrangement of the central points of all the placing frames is finished, the arrangement of the placing frames is finished according to the coordinates of the central points and the set widths and heights of the placing frames, the placing frames are checked one by one, and whether crystal grains can be placed in the placing frames is judged according to the set placing conditions and the set precision levels, so that a final crystal grain placing planning result graph is obtained.
2. The method for square die placement planning according to claim 1, wherein in step S1, the contour detection specifically comprises: and detecting the contour on the image by using a contour detection function FindContours in an EmguCV image processing library, wherein the function can return all detected contours and information such as corresponding center point coordinates, length and width, and the like, sequentially and preliminarily screening the detected contours, comparing the length and width of the contour to be detected with the length and width of a standard crystal grain according to the set precision grade, and if the length and width of the contour to be detected are in a limited range, determining that the contour to be detected is an approved shot crystal grain and then carrying out next processing on the contour to be detected.
3. The method for planning square die placement according to claim 1, wherein in step (1) of S3, the specific steps are as follows: subtracting the row coordinate of each existing crystal grain from the row coordinate of the existing crystal grain before the existing crystal grain, wherein if the result is less than 0, the existing crystal grain is the last crystal grain in the row where the existing crystal grain is located, and thus the last crystal grain in each row and the serial number of the existing crystal grain are obtained; and subtracting the serial number of the last crystal grain in the last row from the serial number of the last crystal grain in each row to obtain the number of the crystal grains in the row.
4. The method for planning square die placement according to claim 1, wherein in step (2) of S3, the specific steps are as follows:
firstly, setting row and column coordinates of the first crystal grain in the row as (row1, col1), setting the transverse distance between the central points of two adjacent crystal grains at the left and the right as spaceX, setting the image edge to leave spaceX/2 vacant space, calculating the number n1 of placing frames which can be arranged at the left side of the first crystal grain,
then n1 ═ Round ((col1-space x/2)/(space x) (1);
wherein Round is an integer function, thereby calculating the coordinates of the center point of each placing frame on the left side of the first crystal grain;
secondly, detecting crystal grains one by one, adding each existing crystal grain position to the row placing frame list, calculating the interval between the two crystal grains as interval according to the coordinates of the central points of the adjacent crystal grains, judging whether a spare position is arranged between the two crystal grains to arrange a placing frame,
then n ═ Round (interval/space x) (2);
if n is more than or equal to 2, n-1 placing frames can be arranged between the two crystal grains, and the coordinates of the center points of the n-1 placing frames are calculated; if n <2, it indicates that the gap between the two dies cannot be arranged with a placement frame;
thirdly, setting the coordinates of the last crystal grain in the line as (row2, col2) and the width of the image as width, calculating the number n2 of the placement frames which can be arranged on the right side of the last crystal grain,
then n2 ═ Round ((width-col2-space x/2)/space x) (3);
from this, the coordinates of the center point of each placement box to the right of the last die are calculated.
5. The method according to claim 1, wherein in step (3) of S3, the method comprises the following steps:
after the arrangement of the placement frames in one row with the most crystal grains is finished, setting the row to have N placement frames in total, setting the longitudinal distance between the central points of two vertically adjacent crystal grains as space Y, and respectively arranging the placement frames upwards and downwards frame by taking the placement frames in the row as a standard;
nUp＝Round((row(i)-spaceY)/spaceY),i＝1,2,...,N (4)，
nDown＝Round((height-row(i)-spaceY)/spaceY),i＝1,2,...,N (5)，
where row (i) represents the row coordinates of the center point of the standard placement frame by standard, height represents the height of the image, nUp placement frames can be placed upward, and nwown placement frames can be placed downward, and thereby the coordinates of the center points of the other row placement frames are obtained.
6. The method for planning placement of square die as claimed in claim 1, wherein in step S4, the placement conditions include whether the placement frame contains existing die, whether the placement frame contains dirt, the number of white dots contained, and the number of edge black dots contained.
7. The method for planning square die placement according to claim 1, wherein in step S1, the industrial camera has a camera system capable of clearly imaging the existing die and has a resolution of 1280 x 960.
8. The method according to claim 1, wherein in step S1, the median filtering process includes: setting the gray value of each pixel point as the median of the gray values of all the pixel points in a certain neighborhood window of the point, thereby protecting the edge information and removing the salt and pepper noise; the point is typically a 3 x 3 or 5 x 5 region in some neighborhood.
9. The method for planning placement of square grains according to claim 1, wherein in step S1, the binary threshold segmentation process comprises the following specific steps: a user self-defines a binary threshold, and the pixel with the gray value larger than the threshold is set to be white, and the gray value of the white is 255; pixels smaller than or equal to the threshold are set to black, and the gradation value of black is 0, whereby the image is processed into a binary image having only two values.
10. The method for planning square die placement according to claim 1, wherein in step S1, the morphological operation of erosion and then dilation comprises:
(1) firstly, etching operation is carried out, 5 multiplied by 5 structural elements are used, the central points of the structural elements are used for scanning each pixel of the image, and the structural elements and the covered parts are subjected to AND operation, if the results are all 1, the pixel value is kept as the original pixel value; otherwise, the value becomes 0; corroding to eliminate noise points smaller than structural elements on the image;
(2) then, performing a dilation operation, using a 5 × 5 structural element, scanning each pixel of the image by using a central point of the structural element, and performing an and operation on the structural element and a part covered by the structural element, wherein if the results are all 0, the pixel value is 0; otherwise, it is 255; the dilation operation fills holes smaller than the structural elements in the image; through morphological operation of corrosion before expansion, the aims of eliminating noise points and removing redundant details can be achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210714903.0A CN114972317B (en) | 2022-06-22 | 2022-06-22 | Square grain placement planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210714903.0A CN114972317B (en) | 2022-06-22 | 2022-06-22 | Square grain placement planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114972317A true CN114972317A (en) | 2022-08-30 |
| CN114972317B CN114972317B (en) | 2024-04-05 |
Family
ID=82966427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210714903.0A Active CN114972317B (en) | 2022-06-22 | 2022-06-22 | Square grain placement planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114972317B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661148A (en) * | 2022-12-26 | 2023-01-31 | 视睿（杭州）信息科技有限公司 | Wafer crystal grain arrangement detection method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201417195A (en) * | 2012-10-23 | 2014-05-01 | Wecon Automation Corp | Circular type die placing method |
| CN103794517A (en) * | 2012-11-01 | 2014-05-14 | 威控自动化机械股份有限公司 | Circular type crystal grain placement method |
| JP2015203643A (en) * | 2014-04-15 | 2015-11-16 | Ｊｆｅスチール株式会社 | Grain diameter measuring method, grain diameter measuring apparatus and grain diameter measuring program |
| CN110286126A (en) * | 2019-06-17 | 2019-09-27 | 浙江大学 | A kind of wafer surface defects subregion area detecting method of view-based access control model image |
-
2022
- 2022-06-22 CN CN202210714903.0A patent/CN114972317B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201417195A (en) * | 2012-10-23 | 2014-05-01 | Wecon Automation Corp | Circular type die placing method |
| CN103794517A (en) * | 2012-11-01 | 2014-05-14 | 威控自动化机械股份有限公司 | Circular type crystal grain placement method |
| JP2015203643A (en) * | 2014-04-15 | 2015-11-16 | Ｊｆｅスチール株式会社 | Grain diameter measuring method, grain diameter measuring apparatus and grain diameter measuring program |
| CN110286126A (en) * | 2019-06-17 | 2019-09-27 | 浙江大学 | A kind of wafer surface defects subregion area detecting method of view-based access control model image |
Non-Patent Citations (1)
| Title |
|---|
| 薛维华;王浩;刘国权;冯敏楠;齐琳;陈展鹏;: "基于图像序列间相似性的晶粒组织图像分割方法", 中国体视学与图像分析, no. 04, 25 December 2015 (2015-12-25), pages 400 - 407 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661148A (en) * | 2022-12-26 | 2023-01-31 | 视睿（杭州）信息科技有限公司 | Wafer crystal grain arrangement detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114972317B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4562126B2 (en) | Defect detection apparatus and defect detection method | |
| CN108629775B (en) | Thermal state high-speed wire rod surface image processing method | |
| US6047893A (en) | Method of locating an object-applied optical code | |
| KR19990072314A (en) | Color image processing apparatus and pattern extracting apparatus | |
| CN113109368A (en) | Glass crack detection method, device, equipment and medium | |
| CN114972317B (en) | Square grain placement planning method | |
| US20110164129A1 (en) | Method and a system for creating a reference image using unknown quality patterns | |
| CN104331695A (en) | Robust round identifier shape quality detection method | |
| JP4062987B2 (en) | Image area dividing method, image area dividing apparatus, and image area dividing program | |
| JP2014164528A (en) | Character recognition device, character recognition method, and program | |
| CN110288619B (en) | Vision-based sunflower module surface screw hole position detection method | |
| CN100489885C (en) | Method for identifying image and device for realizing same | |
| JPH11337498A (en) | Apparatus and method for inspecting printed circuit board | |
| CN113192094A (en) | Ghost outline extraction method, electronic device and storage medium | |
| US6181437B1 (en) | Image processing apparatus capable of producing images without jaggies at edges | |
| CN114494165A (en) | Clustering-based light bar extraction method and device | |
| JPH06288738A (en) | Wiring pattern inspection device | |
| KR102156488B1 (en) | Method of detecting car number plate | |
| CN110232709B (en) | Method for extracting line structured light strip center by variable threshold segmentation | |
| CN108242059B (en) | Image boundary searching method and device | |
| JPH0735532A (en) | Method of measuring length of crack on road surface | |
| CN117218184B (en) | Quick image positioning and extracting method | |
| JPH05300372A (en) | High speed sorting method for median filter | |
| JP2710685B2 (en) | Defect detection method by visual inspection | |
| JP2972516B2 (en) | Print pattern inspection device for inkjet printer |
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 |