CN116779465B - Nano-imprinting wafer defect detection method - Google Patents
Nano-imprinting wafer defect detection method Download PDFInfo
- Publication number
- CN116779465B CN116779465B CN202311080244.0A CN202311080244A CN116779465B CN 116779465 B CN116779465 B CN 116779465B CN 202311080244 A CN202311080244 A CN 202311080244A CN 116779465 B CN116779465 B CN 116779465B
- Authority
- CN
- China
- Prior art keywords
- contour
- area
- pixel point
- spraying
- value
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 title claims abstract description 6
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000005507 spraying Methods 0.000 claims description 62
- 239000003292 glue Substances 0.000 claims description 16
- 239000007921 spray Substances 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 10
- 239000003086 colorant Substances 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000001127 nanoimprint lithography Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
Abstract
The invention discloses a method for detecting defects of a nano-imprinting wafer, which belongs to the technical field of image defect detection.
Description
Technical Field
The invention relates to the technical field of image defect detection, and provides a method for detecting defects of a nanoimprint wafer.
Background
Nanoimprint lithography uses nanoimprint techniques to spray a droplet of nanoimprint resist onto a wafer at a location where an electronic circuit pattern is to be imprinted. Therefore, the quality of all circuits and devices of the chip is determined by the sprayed position of the nano-imprinting glue, but as all circuits and device structures in the chip are smaller, whether the voltage and the current on the chip are normal or not can be detected only after the chip is manufactured, so that whether the quality of the chip is qualified or not is determined. However, quality detection is performed after the chip is generated, which causes waste of production data.
Disclosure of Invention
Aiming at the defects in the prior art, the method for detecting the defects of the nano-imprinting wafer solves the problem that the existing method for detecting the defects of the nano-imprinting wafer is lacking.
In order to achieve the aim of the invention, the invention adopts the following technical scheme: a method for detecting the defects of a nanoimprint wafer comprises the following steps:
s1, acquiring an image in a nanoimprint process to obtain an imprint image;
s2, extracting an image of a nano imprinting glue spraying area in the imprinting image;
s3, performing gray scale treatment on the image of the nano imprinting glue spraying area to obtain a gray scale image;
s4, extracting a spraying contour from the gray level map;
s5, determining the defect type according to the contour characteristics of the spraying contour.
Further, the step S2 includes the following sub-steps:
s21, calculating a color distance value between a color value of a pixel point in the imprinting image and a color value of the wafer;
s22, classifying the corresponding pixel points into wafer areas when the color distance value is smaller than the distance threshold value;
s23, removing the wafer area from the imprinting image to obtain an image of the nano imprinting glue spraying area.
The beneficial effects of the above further scheme are: the colors of the nano imprinting glue spraying area and the exposed area of the wafer are different, so that the color value of each pixel point in the imprinting image is compared with the color value of the wafer, the color distance value is calculated, the approximate condition of the color is determined, when the color distance value is smaller than the distance threshold value, the color is similar, the similar pixel points are classified as the wafer area, and the rest of the pixel points are classified as the nano imprinting glue spraying area.
Further, the calculation formula of the color distance value in S21 is:
wherein C d For colour distance value, C i For the ith color value of the wafer, C i,c The i color value of any pixel point in the embossed image is the absolute value.
The beneficial effects of the above further scheme are: when i=1, C 1 For red colour value, C 2 For blue colour value, C 3 For green color value, the color approximation is determined by comparing the three primary colors of each pixel point, and the index coefficient is designedMeasure the degree of phase difference of each color, +.>The larger the color phase difference degree is, the larger the index coefficient is, the color distance is further increased, and therefore the amorphous wafer area is found out to the greatest extent.
Further, the step S4 includes the following sub-steps:
s41, setting 33, a contour window;
s42, moving on the gray scale by adopting a contour window;
s43, calculating the gray level similarity between any non-central pixel point and other central pixel points under the contour window when the contour window moves once;
s44, when the gray level similarity is greater than a similarity threshold, the central pixel point is a non-contour point;
s45, eliminating non-contour points on the gray level map to obtain a spraying contour.
The beneficial effects of the above further scheme are: in the invention is provided with 33, the contour window moves on the gray level graph, the gray level similarity between non-center pixel points is calculated, when the gray level similarity is larger than the similarity threshold value, the center pixel points are non-contour points, the surrounding center pixel points are non-contour points under the condition that the surrounding center pixel points are similar, meanwhile, the determination of the non-contour points is not influenced when the center pixel points are noise points, and in step S43, in order to avoid the condition that the surrounding pixel points have noise points, the gray level similarity between any non-center pixel point and other center pixel points is larger than the similarity threshold value.
Further, the formula for calculating the gray level similarity in S43 is:
wherein h is si Is the gray level similarity, h o Is the gray value of any non-central pixel point, h j Dividing the gray value h for the contour window o And a j-th gray value other than the gray value of the center pixel point.
The beneficial effects of the above further scheme are: in the invention, when the gray level similarity of any non-central pixel point and other central pixel points is larger than a similarity threshold value, the central pixel points are non-contour points, if a noise point exists in the peripheral pixel points, only one cosine similarity calculation is influenced in a gray level similarity formula in the invention, and the gray level similarity in the invention adopts a mode of adding a plurality of cosine similarities, so that the influence of the noise point on the gray level similarity in the invention is reduced.
Further, the step S5 includes the following sub-steps:
s51, constructing an area characteristic sequence according to the area of each closed contour on the spraying contour;
s52, segmenting the spraying contour, extracting contour fluctuation features, and constructing a contour fluctuation feature sequence;
s53, inputting the area characteristic sequence and the contour fluctuation characteristic sequence into a defect prediction model to obtain a defect type.
The beneficial effects of the above further scheme are: in the invention, the defect type is determined by two parts, namely the area surrounded by the closed contour and the shape of the contour, wherein the area surrounded by the closed contour represents the size of a device or a wire in the chip, and the shape of the contour represents the shape of the device or the wire in the chip.
Further, the step S51 specifically includes: calculating the area difference characteristic of each closed contour on the spraying contour according to the area enclosed by each closed contour on the spraying contour and the label area enclosed by the corresponding closed contour, and forming an area characteristic sequence by all the area difference characteristics;
the calculation formula of the area gap characteristic is as follows:
wherein E is n E, the area difference characteristic of the nth closed contour on the spraying contour n E is the area enclosed by the nth closed contour on the spraying contour b,n For the label area enclosed by the nth closed contour on the spraying contour, d n,max D, the distance between the two furthest pixel points in the enclosed area of the nth closed contour on the spraying contour b,n,max Distance of two pixel points at the farthest in label area of nth closed contour；
The area characteristic sequence isWherein E is 1 For the area gap feature of the 1 st closed contour on the spray contour E N For the area gap feature of the nth closed contour on the spray contour, N is the number of elements in the sequence of area features.
The beneficial effects of the above further scheme are: according to the method, the area difference characteristics of the area surrounded by each closed contour on the spraying contour and the label area are calculated, the difference value of the whole area is considered in the area difference characteristic calculation, meanwhile, the distance difference of the two farthest pixel points in the closed contour is considered, the similarity of the area on the closed contour to be identified and the label area in the area size and shape is guaranteed to the greatest extent, and dissimilar closed contours are represented through the area difference characteristics.
Further, the step S52 includes the following sub-steps:
s521, segmenting the spraying profile to obtain a plurality of sub-segment profiles;
s522, calculating the direction angle of the pixel point in each subsection contour;
s523, extracting contour fluctuation characteristics of each subsection contour according to the direction angle of the pixel point;
s524, taking the contour fluctuation characteristics of all the sub-segment contours as elements, and constructing a contour fluctuation characteristic sequence.
The beneficial effects of the above further scheme are: according to the invention, the spraying contour is segmented, and the direction angle of the pixel points in each sub-segment contour is calculated, so that the trend of each pixel point is determined, and the structural forms of devices and wires in a chip are determined.
Further, the calculation formula of the direction angle of the pixel point in S522 is as follows:
wherein r is k The direction angle of the kth pixel point is arctan, x k,l Is the abscissa, y, of the pixel point on the left side of the kth pixel point k,l Is the ordinate, x of the pixel point at the left side of the kth pixel point k,r Is the abscissa, y, of the pixel point on the right side of the kth pixel point k,r Is the ordinate of the pixel point on the right side of the kth pixel point, the absolute value is the absolute value, and x is the absolute value k,o Is the abscissa of the kth pixel point, y k,o Is the ordinate of the kth pixel point;
the calculation formula of the profile fluctuation feature is as follows:
wherein V is the contour fluctuation feature, and K is the number of pixels for calculating the direction angle.
The beneficial effects of the above further scheme are: the method and the device take the pixel points on the left side and the right side of the direction angle of the pixel point to be calculated, so that the direction angle of each pixel point is determined. The contour fluctuation feature subtracts the average direction angle from the direction angle of each pixel point, so that the fluctuation condition of the direction angle in a subsection contour is obtained, and the flatness of the contour is represented.
Further, the defect prediction model in S53 is:
wherein y is the output of the defect prediction model, sigmoid is the activation function, N is the number of elements in the area feature sequence, E n Is the area difference feature of the nth element in the area feature sequence, namely the nth closed contour on the spraying contour, a E,n For E n Weights of b E,n For E n V is offset of m For the m-th element, a in the profile fluctuation feature sequence V,m Is V (V) m Weights of b V,m Is V (V) m M is the number of elements in the profile fluctuation feature sequence.
The beneficial effects of the above further scheme are: according to the method, the area difference features in the area feature sequence are weighted, and the contour fluctuation features in the contour fluctuation feature sequence are weighted, so that different weights can be conveniently given according to different features, and the accuracy of detecting defect types is improved.
The beneficial effects of the invention are as follows: the method comprises the steps of collecting images in a nanoimprinting process, extracting images of a nanoimprinting glue spraying area in the imprinted images, carrying out graying treatment to obtain a gray scale image, extracting spraying contours from the gray scale image, and judging the types of nanoimprinting wafer defects according to contour features of the spraying contours.
Drawings
FIG. 1 is a flow chart of a method for detecting defects on a nanoimprint wafer.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, a method for detecting defects of a nanoimprint wafer includes the following steps:
s1, acquiring an image in a nanoimprint process to obtain an imprint image;
s2, extracting an image of a nano imprinting glue spraying area in the imprinting image;
the step S2 comprises the following sub-steps:
s21, calculating a color distance value between a color value of a pixel point in the imprinting image and a color value of the wafer;
s22, classifying the corresponding pixel points into wafer areas when the color distance value is smaller than the distance threshold value;
s23, removing the wafer area from the imprinting image to obtain an image of the nano imprinting glue spraying area.
The colors of the nano imprinting glue spraying area and the exposed area of the wafer are different, so that the color value of each pixel point in the imprinting image is compared with the color value of the wafer, the color distance value is calculated, the approximate condition of the color is determined, when the color distance value is smaller than the distance threshold value, the color is similar, the similar pixel points are classified as the wafer area, and the rest of the pixel points are classified as the nano imprinting glue spraying area.
The calculation formula of the color distance value in S21 is:
wherein C d For colour distance value, C i For the ith color value of the wafer, C i,c The i color value of any pixel point in the embossed image is the absolute value.
When i=1, C 1 For red colour value, C 2 For blue colour value, C 3 For green color value, the color approximation is determined by comparing the three primary colors of each pixel point, and the index coefficient is designedMeasure the degree of phase difference of each color, +.>The larger the color phase difference degree is, the larger the index coefficient is, the color distance is further increased, and therefore the amorphous wafer area is found out to the greatest extent.
S3, performing gray scale treatment on the image of the nano imprinting glue spraying area to obtain a gray scale image;
s4, extracting a spraying contour from the gray level map;
the step S4 comprises the following substeps:
s41, setting 33, a contour window;
s42, moving on the gray scale by adopting a contour window;
s43, calculating the gray level similarity between any non-central pixel point and other central pixel points under the contour window when the contour window moves once;
s44, when the gray level similarity is greater than a similarity threshold, the central pixel point is a non-contour point;
s45, eliminating non-contour points on the gray level map to obtain a spraying contour.
In the invention is provided with 33, the contour window moves on the gray level graph, the gray level similarity between non-center pixel points is calculated, when the gray level similarity is larger than the similarity threshold value, the center pixel points are non-contour points, the surrounding center pixel points are non-contour points under the condition that the surrounding center pixel points are similar, meanwhile, the determination of the non-contour points is not influenced when the center pixel points are noise points, and in step S43, in order to avoid the condition that the surrounding pixel points have noise points, the gray level similarity between any non-center pixel point and other center pixel points is larger than the similarity threshold value.
The formula for calculating the gray level similarity in S43 is:
wherein h is si Is the gray level similarity, h o Is the gray value of any non-central pixel point, h j Dividing the gray value h for the contour window o And a j-th gray value other than the gray value of the center pixel point.
In the invention, when the gray level similarity of any non-central pixel point and other central pixel points is larger than a similarity threshold value, the central pixel points are non-contour points, if a noise point exists in the peripheral pixel points, only one cosine similarity calculation is influenced in a gray level similarity formula in the invention, and the gray level similarity in the invention adopts a mode of adding a plurality of cosine similarities, so that the influence of the noise point on the gray level similarity in the invention is reduced.
S5, determining the defect type according to the contour characteristics of the spraying contour.
The step S5 comprises the following substeps:
s51, constructing an area characteristic sequence according to the area of each closed contour on the spraying contour;
s52, segmenting the spraying contour, extracting contour fluctuation features, and constructing a contour fluctuation feature sequence;
s53, inputting the area characteristic sequence and the contour fluctuation characteristic sequence into a defect prediction model to obtain a defect type.
In the invention, the defect type is determined by two parts, namely the area surrounded by the closed contour and the shape of the contour, wherein the area surrounded by the closed contour represents the size of a device or a wire in the chip, and the shape of the contour represents the shape of the device or the wire in the chip.
The step S51 specifically includes: calculating the area difference characteristic of each closed contour on the spraying contour according to the area enclosed by each closed contour on the spraying contour and the label area enclosed by the corresponding closed contour, and forming an area characteristic sequence by all the area difference characteristics;
in this embodiment, the label area is the standard area that it should be.
The calculation formula of the area gap characteristic is as follows:
wherein E is n E, the area difference characteristic of the nth closed contour on the spraying contour n E is the area enclosed by the nth closed contour on the spraying contour b,n For the label area enclosed by the nth closed contour on the spraying contour, d n,max D, the distance between the two furthest pixel points in the enclosed area of the nth closed contour on the spraying contour b,n,max The distance between the two farthest pixel points in the label area of the nth closed contour;
the area characteristic sequence isWherein E is 1 For the area gap feature of the 1 st closed contour on the spray contour E N For the area gap feature of the nth closed contour on the spray contour, N is the number of elements in the sequence of area features.
According to the method, the area difference characteristics of the area surrounded by each closed contour on the spraying contour and the label area are calculated, the difference value of the whole area is considered in the area difference characteristic calculation, meanwhile, the distance difference of the two farthest pixel points in the closed contour is considered, the similarity of the area on the closed contour to be identified and the label area in the area size and shape is guaranteed to the greatest extent, and dissimilar closed contours are represented through the area difference characteristics.
The step S52 includes the following sub-steps:
s521, segmenting the spraying profile to obtain a plurality of sub-segment profiles;
s522, calculating the direction angle of the pixel point in each subsection contour;
s523, extracting contour fluctuation characteristics of each subsection contour according to the direction angle of the pixel point;
s524, taking the contour fluctuation characteristics of all the sub-segment contours as elements, and constructing a contour fluctuation characteristic sequence.
According to the invention, the spraying contour is segmented, and the direction angle of the pixel points in each sub-segment contour is calculated, so that the trend of each pixel point is determined, and the structural forms of devices and wires in a chip are determined.
The calculation formula of the direction angle of the pixel point in S522 is as follows:
wherein r is k The direction angle of the kth pixel point is arctan, x k,l Is the abscissa, y, of the pixel point on the left side of the kth pixel point k,l Is the ordinate, x of the pixel point at the left side of the kth pixel point k,r Is the abscissa, y, of the pixel point on the right side of the kth pixel point k,r Is the ordinate of the pixel point on the right side of the kth pixel point, the absolute value is the absolute value, and x is the absolute value k,o Is the abscissa of the kth pixel point, y k,o Is the ordinate of the kth pixel point;
the calculation formula of the profile fluctuation feature is as follows:
wherein V isAnd the contour fluctuation characteristic, K, is the number of pixels for calculating the direction angle.
The method and the device take the pixel points on the left side and the right side of the direction angle of the pixel point to be calculated, so that the direction angle of each pixel point is determined. The contour fluctuation feature subtracts the average direction angle from the direction angle of each pixel point, so that the fluctuation condition of the direction angle in a subsection contour is obtained, and the flatness of the contour is represented.
The defect prediction model in S53 is:
wherein y is the output of the defect prediction model, sigmoid is the activation function, N is the number of elements in the area feature sequence, E n Is the area difference feature of the nth element in the area feature sequence, namely the nth closed contour on the spraying contour, a E,n For E n Weights of b E,n For E n V is offset of m For the m-th element, a in the profile fluctuation feature sequence V,m Is V (V) m Weights of b V,m Is V (V) m M is the number of elements in the profile fluctuation feature sequence.
According to the method, the area difference features in the area feature sequence are weighted, and the contour fluctuation features in the contour fluctuation feature sequence are weighted, so that different weights can be conveniently given according to different features, and the accuracy of detecting defect types is improved.
The method comprises the steps of collecting images in a nanoimprinting process, extracting images of a nanoimprinting glue spraying area in the imprinted images, carrying out graying treatment to obtain a gray scale image, extracting spraying contours from the gray scale image, and judging the types of nanoimprinting wafer defects according to contour features of the spraying contours.
Claims (5)
1. The nano-imprint wafer defect detection method is characterized by comprising the following steps of:
s1, acquiring an image in a nanoimprint process to obtain an imprint image;
s2, extracting an image of a nano imprinting glue spraying area in the imprinting image;
s3, performing gray scale treatment on the image of the nano imprinting glue spraying area to obtain a gray scale image;
s4, extracting a spraying contour from the gray level map;
s5, determining the defect type according to the contour characteristics of the spraying contour;
the step S5 comprises the following substeps:
s51, constructing an area characteristic sequence according to the area of each closed contour on the spraying contour;
s52, segmenting the spraying contour, extracting contour fluctuation features, and constructing a contour fluctuation feature sequence;
s53, inputting the area characteristic sequence and the contour fluctuation characteristic sequence into a defect prediction model to obtain a defect type;
the step S51 specifically includes: calculating the area difference characteristic of each closed contour on the spraying contour according to the area enclosed by each closed contour on the spraying contour and the label area enclosed by the corresponding closed contour, and forming an area characteristic sequence by all the area difference characteristics;
the calculation formula of the area gap characteristic is as follows:
，
wherein E is n E, the area difference characteristic of the nth closed contour on the spraying contour n E is the area enclosed by the nth closed contour on the spraying contour b,n For the label area enclosed by the nth closed contour on the spraying contour, d n,max D, the distance between the two furthest pixel points in the enclosed area of the nth closed contour on the spraying contour b,n,max The distance between the two farthest pixel points in the label area of the nth closed contour;
the area characteristic sequence isWherein E is 1 For the area gap feature of the 1 st closed contour on the spray contour E N For sprayingThe area difference feature of the Nth closed contour on the contour, wherein N is the number of elements in the area feature sequence;
the step S52 includes the following sub-steps:
s521, segmenting the spraying profile to obtain a plurality of sub-segment profiles;
s522, calculating the direction angle of the pixel point in each subsection contour;
s523, extracting contour fluctuation characteristics of each subsection contour according to the direction angle of the pixel point;
s524, taking the contour fluctuation characteristics of all the subsection contours as elements to construct a contour fluctuation characteristic sequence;
the calculation formula of the direction angle of the pixel point in S522 is as follows:
，
wherein r is k The direction angle of the kth pixel point is arctan, x k,l Is the abscissa, y, of the pixel point on the left side of the kth pixel point k,l Is the ordinate, x of the pixel point at the left side of the kth pixel point k,r Is the abscissa, y, of the pixel point on the right side of the kth pixel point k,r Is the ordinate of the pixel point on the right side of the kth pixel point, the absolute value is the absolute value, and x is the absolute value k,o Is the abscissa of the kth pixel point, y k,o Is the ordinate of the kth pixel point;
the calculation formula of the profile fluctuation feature is as follows:
，
v is the contour fluctuation characteristic, K is the number of pixels for calculating the direction angle;
the defect prediction model in S53 is:
，
wherein y is defect pre-determinedOutput of the test model, sigmoid is an activation function, N is the number of elements in the area feature sequence, E n Is the area difference feature of the nth element in the area feature sequence, namely the nth closed contour on the spraying contour, a E,n For E n Weights of b E,n For E n V is offset of m For the m-th element, a in the profile fluctuation feature sequence V,m Is V (V) m Weights of b V,m Is V (V) m M is the number of elements in the profile fluctuation feature sequence.
2. The method for detecting defects of a nanoimprint wafer according to claim 1, wherein the S2 includes the sub-steps of:
s21, calculating a color distance value between a color value of a pixel point in the imprinting image and a color value of the wafer;
s22, classifying the corresponding pixel points into wafer areas when the color distance value is smaller than the distance threshold value;
s23, removing the wafer area from the imprinting image to obtain an image of the nano imprinting glue spraying area.
3. The method for detecting a nano-imprint wafer defect according to claim 2, wherein the calculation formula of the color distance value in S21 is:
，
wherein C is d For colour distance value, C i For the ith color value of the wafer, C i,c The i color value of any pixel point in the embossed image is the absolute value.
4. The method for detecting defects of a nanoimprint wafer according to claim 1, wherein the S4 includes the sub-steps of:
s41, setting 33 outline of 3A window;
s42, moving on the gray scale by adopting a contour window;
s43, calculating the gray level similarity between any non-central pixel point and other central pixel points under the contour window when the contour window moves once;
s44, when the gray level similarity is greater than a similarity threshold, the central pixel point is a non-contour point;
s45, eliminating non-contour points on the gray level map to obtain a spraying contour.
5. The method for detecting a defect in a nanoimprint wafer according to claim 4, wherein the formula for calculating the gray scale similarity in S43 is:
，
wherein h is si Is the gray level similarity, h o Is the gray value of any non-central pixel point, h j Dividing the gray value h for the contour window o And a j-th gray value other than the gray value of the center pixel point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311080244.0A CN116779465B (en) | 2023-08-25 | 2023-08-25 | Nano-imprinting wafer defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311080244.0A CN116779465B (en) | 2023-08-25 | 2023-08-25 | Nano-imprinting wafer defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116779465A CN116779465A (en) | 2023-09-19 |
| CN116779465B true CN116779465B (en) | 2023-10-31 |
Family
ID=88008525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311080244.0A Active CN116779465B (en) | 2023-08-25 | 2023-08-25 | Nano-imprinting wafer defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116779465B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117115161B (en) * | 2023-10-24 | 2024-01-02 | 四川新康意众申新材料有限公司 | Plastic defect inspection method |
| CN117250208B (en) * | 2023-11-20 | 2024-02-06 | 青岛天仁微纳科技有限责任公司 | Machine vision-based nano-imprint wafer defect accurate detection system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR200301148Y1 (en) * | 2002-10-02 | 2003-01-15 | 아남반도체 주식회사 | Device for confirming bad coating in Spin On Glass Line |
| JP2011197120A (en) * | 2010-03-17 | 2011-10-06 | Toppan Printing Co Ltd | Pattern evaluation method and pattern evaluation device |
| CN107111226A (en) * | 2014-12-22 | 2017-08-29 | 皇家飞利浦有限公司 | Patterned stamp manufacture method, patterned stamp and method for stamping |
| CN108335990A (en) * | 2018-01-31 | 2018-07-27 | 中国科学院微电子研究所 | A kind of method and device of positioning process defect |
| CN111142338A (en) * | 2018-11-01 | 2020-05-12 | 爱思开海力士有限公司 | Method for detecting printing defects on photoresist pattern |
| CN112010258A (en) * | 2020-09-04 | 2020-12-01 | 南京邮电大学 | Preparation method of composite film with micro-nano structure array |
| CN115087930A (en) * | 2020-02-10 | 2022-09-20 | Asml荷兰有限公司 | Multi-step process inspection method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11164302B2 (en) * | 2019-08-08 | 2021-11-02 | Canon Kabushiki Kaisha | Systems and methods for classifying images of an imprinted film |
-
2023
- 2023-08-25 CN CN202311080244.0A patent/CN116779465B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR200301148Y1 (en) * | 2002-10-02 | 2003-01-15 | 아남반도체 주식회사 | Device for confirming bad coating in Spin On Glass Line |
| JP2011197120A (en) * | 2010-03-17 | 2011-10-06 | Toppan Printing Co Ltd | Pattern evaluation method and pattern evaluation device |
| CN107111226A (en) * | 2014-12-22 | 2017-08-29 | 皇家飞利浦有限公司 | Patterned stamp manufacture method, patterned stamp and method for stamping |
| CN108335990A (en) * | 2018-01-31 | 2018-07-27 | 中国科学院微电子研究所 | A kind of method and device of positioning process defect |
| CN111142338A (en) * | 2018-11-01 | 2020-05-12 | 爱思开海力士有限公司 | Method for detecting printing defects on photoresist pattern |
| CN115087930A (en) * | 2020-02-10 | 2022-09-20 | Asml荷兰有限公司 | Multi-step process inspection method |
| JP2023513667A (en) * | 2020-02-10 | 2023-04-03 | エーエスエムエル ネザーランズ ビー．ブイ． | Multi-step process inspection method |
| CN112010258A (en) * | 2020-09-04 | 2020-12-01 | 南京邮电大学 | Preparation method of composite film with micro-nano structure array |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116779465A (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116779465B (en) | Nano-imprinting wafer defect detection method | |
| CN106127779B (en) | The defect inspection method and system of view-based access control model identification | |
| CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
| CN107967695B (en) | A kind of moving target detecting method based on depth light stream and morphological method | |
| US6961466B2 (en) | Method and apparatus for object recognition | |
| CN111735524B (en) | Tire load obtaining method based on image recognition, vehicle weighing method and system | |
| US20220309637A1 (en) | Electronic substrate defect detection | |
| CN110175649B (en) | Rapid multi-scale estimation target tracking method for re-detection | |
| CN111209858B (en) | Real-time license plate detection method based on deep convolutional neural network | |
| CN111738342A (en) | Pantograph foreign matter detection method, storage medium and computer equipment | |
| CN107944354B (en) | Vehicle detection method based on deep learning | |
| CN109887273B (en) | Bridge live load optimization identification method based on multi-source redundant information | |
| CN111079640A (en) | Vehicle type identification method and system based on automatic amplification sample | |
| CN117094909B (en) | Nanometer stamping wafer image acquisition processing method | |
| CN113591967A (en) | Image processing method, device and equipment and computer storage medium | |
| CN110926339A (en) | Real-time three-dimensional measurement method based on one-time projection structured light parallel stripe pattern | |
| CN106056078B (en) | Crowd density estimation method based on multi-feature regression type ensemble learning | |
| CN112766056B (en) | Method and device for detecting lane lines in low-light environment based on deep neural network | |
| CN111339830A (en) | Target classification method based on multi-modal data features | |
| CN109241870B (en) | Coal mine underground personnel identity identification method based on gait identification | |
| CN112560717A (en) | Deep learning-based lane line detection method | |
| Do et al. | Dynamic background modeling based on radial basis function neural networks for moving object detection | |
| CN104200226B (en) | Particle filter method for tracking target based on machine learning | |
| CN111833353A (en) | Hyperspectral target detection method based on image segmentation | |
| CN114708532A (en) | Monitoring video quality evaluation method, system and storage medium |
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 |