WO2023046637A1 - Procede de classification de defauts d'un reseau a analyser - Google Patents
Procede de classification de defauts d'un reseau a analyser Download PDFInfo
- Publication number
- WO2023046637A1 WO2023046637A1 PCT/EP2022/075982 EP2022075982W WO2023046637A1 WO 2023046637 A1 WO2023046637 A1 WO 2023046637A1 EP 2022075982 W EP2022075982 W EP 2022075982W WO 2023046637 A1 WO2023046637 A1 WO 2023046637A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- series
- pattern
- patterns
- correlation coefficient
- analyzed
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000000737 periodic effect Effects 0.000 claims abstract description 40
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims abstract description 29
- 230000007547 defect Effects 0.000 claims description 22
- 239000002070 nanowire Substances 0.000 claims description 9
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 description 8
- 239000002086 nanomaterial Substances 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000005314 correlation function Methods 0.000 description 3
- 238000000407 epitaxy Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 229910003460 diamond Inorganic materials 0.000 description 2
- 239000010432 diamond Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000007847 structural defect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Definitions
- the invention relates to the technical field of the analysis of defects in a network of periodic patterns by image processing.
- the invention finds its application in particular when the periodic patterns are nanostructures, such as nanowires formed by epitaxy.
- Nanostructure defects such as nanowires or nanopyramids
- a substrate e.g. a wafer or "wafer”
- the person skilled in the art seeks to identify the nanostructures presenting morphological defects (size, geometry), and to have a quantitative feedback on the quality of the epitaxies in order to determine if the nanowires of the substrate are of sufficient quality to undergo technological steps. additions of an industrial process in production mode.
- Such a state-of-the-art method whose approach is based on a threshold, is not entirely satisfactory for detecting defects on nanostructures.
- the nanostructures present a dispersion in particular in size, shape, contrast, luminosity, which makes extremely complex the precise determination of a threshold allowing a reliable detection of defects.
- such a process of the state of the art is likely to wrongly consider that nanostructures do not contain defects, or to wrongly consider that nanostructures contain defects.
- the subject of the invention is a method for classifying faults of a grating to be analyzed comprising periodic patterns, the method comprising the steps: a) providing a digital image of a reference grating, showing a first series periodic patterns; b) defining a reference pattern from the patterns of the first series; c) providing a digital image of the grating to be analyzed, showing a second series of periodic patterns; d) calculating a correlation coefficient between each pattern of the second series and the reference pattern; e) classifying, in a first category, each pattern of the second series whose correlation coefficient, in absolute value, is less than a predetermined threshold; f) extracting a characteristic dimension for each pattern of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; g) calculating an arithmetic mean and a standard deviation of the characteristic dimensions extracted during step f); h) classifying, in a second category,
- peripheral patterns are meant patterns spaced according to a regular interval of distance (spatial period). In a perfect lattice, the periodic patterns reproduce identically. In practice, the expression “identical” means within the usual tolerances linked to the experimental conditions of manufacture, and not in the literal sense of the term.
- reference grating is meant a grating whose periodic patterns have previously known geometric characteristics (e.g. by measurements), and satisfying given industrial specifications.
- reference pattern is meant a pattern having previously known geometric characteristics (e.g. by measurements) and which satisfy given industrial specifications.
- characteristic dimension is meant a specific dimension (spatial extent) allowing a distinction between the patterns of the second series of which each correlation coefficient, in absolute value, is greater than the predetermined threshold.
- Step e) makes it possible to detect the patterns of the second series which are the least similar in terms of overall morphology with respect to the reference pattern, and are considered as structural defects, classified in the first category.
- Step h) allows a finer analysis by detecting the patterns of the second series, resembling in terms of morphology overall with respect to the reference pattern, but which present a disparity for at least one specific dimension with respect to the reference pattern. These detected patterns of the second series are considered as size defects, classified in the second category.
- Such a method according to the invention therefore makes it possible to greatly limit detection errors wrongly establishing that nanostructures do not contain defects.
- This double analysis of defects makes it possible to specify the nature of the defects detected, and to facilitate the determination of the origin of these defects, by distinguishing for example the influence of epitaxy and the influence of other technological steps in the case of a network of epitaxial nanowires, in order to improve the homogeneity and the reproducibility of the periodic patterns.
- the invention also relates to a method for classifying faults of a set of gratings to be analyzed each comprising periodic patterns, the method comprising the steps: a) providing a digital image of a reference grating, showing a first series periodic patterns; b) defining a reference pattern from the patterns of the first series; c) provide at least one digital image of each grating to be analyzed in the set, showing a second series of periodic patterns; the method iterating the following steps, for each digital image of each network to be analyzed of the set: d) calculating a correlation coefficient between each pattern of the second series and the reference pattern; e) classifying, in a first category, each pattern of the second series whose correlation coefficient, in absolute value, is less than a predetermined threshold; f) extracting a characteristic dimension for each pattern of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; g) calculating an arithmetic mean and a standard deviation of the characteristic dimensions extracted during step f);
- Such a method according to the invention has the same advantages as those mentioned above.
- An additional advantage is to be able to iterate the double analysis of the faults for each network of the set before engaging additional technological steps of an industrial process in production mode.
- the method according to the invention may comprise one or more of the following characteristics.
- step f) comprises the steps: fi) performing a cutting line for each pattern of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; fz) extract the characteristic dimension from the section line.
- an advantage obtained is to be able to easily measure the characteristic dimension from an image processing operation.
- step b) consists in selecting a pattern from among the patterns of the first series, the selected pattern defining the reference pattern.
- an advantage obtained is to authorize a manual selection of the reference pattern.
- step b) comprises the steps: bi) selecting an initial pattern from among the patterns of the first series; bz) calculating a correlation coefficient between each pattern of the first series and the initial pattern; bs) identifying each pattern of the first series whose correlation coefficient, in absolute value, is greater than a predetermined threshold; b 4 ) defining the reference pattern from a combination of the patterns of the first series identified during step bs).
- an advantage obtained is to improve the reliability and the representativeness of the reference pattern.
- the reference pattern is defined during step b) by performing an average of the patterns of the first series.
- an advantage obtained is to improve the reliability and the representativeness of the reference pattern, when the digital image of the reference grating is of good quality (low rate of defects).
- the term “average” is understood as an average of the intensities of the pixels of the patterns of the first series.
- the digital images of the reference grating and of the grating to be analyzed, provided respectively during steps a) and c), each comprise a set of pixels, each pixel possessing an intensity; the correlation coefficient is calculated during step d) between the intensity of the pixels of each pattern of the second series and the intensity of the pixels of the reference pattern.
- the correlation coefficient is calculated during step d) according to the Bravais-Pearson formula.
- step d) is preceded by the steps: doi) identifying the position of the patterns of the second series on the digital image of the grating to be analyzed; doz) scale the digital image of the network to be analyzed so that the patterns of the second series are in integer.
- an advantage obtained is to improve the reliability of the calculation of the correlation coefficient by eliminating the patterns of the second series which are on the edges of the digital image of the grating.
- step d O i) comprises a step consisting in calculating a correlation coefficient between the digital image of the grating to be analyzed and the reference pattern.
- an advantage obtained is to be able to precisely determine the position of the patterns of the second series on the digital image of the grating to be analyzed, and this in order to reliably count the number of patterns present on the digital image (with a maximum correlation in absolute value).
- step f) comprises a step P) consisting in extracting at least one additional characteristic dimension for each pattern of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold;
- - step g) comprises a step g′) consisting in calculating an additional arithmetic mean and an additional standard deviation of the additional characteristic dimensions extracted during step P);
- - step h) comprises a step h′) consisting in classifying, in the second category, each pattern of the second series whose additional characteristic dimension has a deviation from the additional arithmetic mean greater than the additional standard deviation.
- an advantage is to refine the analysis of potential defects for the patterns of the second series, resembling in terms of global morphology vis-à-vis the reference pattern, but which present a potential disparity for different specific dimensions (for example along different directions) with respect to the reference pattern, which allows a specific morphology analysis with respect to the reference pattern.
- the network to be analyzed comprises nanowires, forming periodic patterns, and having a cross section in the shape of a hexagon;
- the characteristic dimension extracted during step f) is the dimension of one side of the hexagon.
- transverse we mean a section that cuts perpendicularly to the longitudinal axis of the nanowires.
- the longitudinal axis is the axis extending along the height of the nanowires.
- the digital images of the reference grating and of the grating to be analyzed, provided respectively during steps a) and c), are digital images from an electron microscope, preferably scanning.
- step f) is preceded by the steps: faith) generating a histogram of the intensities of the pixels of the digital image of the grating to be analyzed; ffi) extracting an intensity threshold of the periodic patterns of the second series, from the histogram generated during step f O i).
- an advantage provided by such an image segmentation is to take into account the intensity threshold extracted during step ffi) in order to extract the characteristic dimension during step f) in a reliable manner.
- step d is followed by a step d') consisting in counting a total number of patterns of the second series of which each correlation coefficient, in absolute value, is greater than the predetermined threshold;
- Steps e) to h) are executed if the total number of patterns is greater than a predetermined value.
- an advantage obtained is to guarantee a minimum number of patterns to be analyzed during steps e) to h) to obtain a reliable and representative analysis from a statistical point of view.
- Figure 1 is a flowchart schematically representing a method according to the invention.
- Figure 2 is a flowchart schematically representing a method according to the invention, illustrating in particular an iteration of steps d) to h) in the case of a set of networks to be analyzed.
- Figure 3 is a flowchart schematically representing a method according to the invention, illustrating in particular steps f 1 ) and f 2 ).
- Figure 4 is a flowchart schematically representing a method according to the invention, illustrating in particular steps bi) to b ⁇ .
- Figure 5 is a flowchart schematically representing a method according to the invention, illustrating in particular the steps doi) and doz).
- Figure 6 is a flowchart schematically representing a method according to the invention, illustrating in particular steps f), g′) and h′).
- Figure 7 is a flowchart schematically representing a method according to the invention, illustrating in particular the steps f O i) and £ 02 )-
- Figure 8 is a flowchart schematically representing a method according to the invention, illustrating in particular the step d').
- Figure 9 is a partial schematic sectional view, representing patterns of the first series, and illustrating a first embodiment of step b).
- Figure 10 is a partial schematic sectional view, representing patterns of the first series, and illustrating a second embodiment of step b).
- Figure 11 is a partial cross-sectional diagram, representing patterns of the second series, and illustrating a mode of implementation of steps f) and P).
- an object of the invention is a method for classifying defects of a network to be analyzed 2 comprising periodic patterns 20, the method comprising the steps: a) providing a digital image of a network of reference 1, showing a first series of periodic patterns; b) defining a reference pattern 100 from the patterns 10 of the first series; c) providing a digital image of the grating 2 to be analyzed, showing a second series of periodic patterns 20; d) calculating a correlation coefficient between each pattern 20 of the second series and the reference pattern 100; e) classifying, in a first category, each pattern 20 of the second series whose correlation coefficient, in absolute value, is less than a predetermined threshold; f) extracting a characteristic dimension D for each pattern 20 of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; g) calculating an arithmetic mean and a standard deviation of the characteristic dimensions D extracted during step f); h) classifying, in a second category, each pattern 20 of the second series
- an object of the invention is a method for detecting faults in a network to be analyzed 2 comprising periodic patterns 20, the method comprising the steps: a) providing a digital image of a reference grating 1, showing a first series of periodic patterns 10; b) defining a reference pattern 100 from the patterns 10 of the first series; c) providing a digital image of the grating 2 to be analyzed, showing a second series of periodic patterns 20; d) calculating a correlation coefficient between each pattern 20 of the second series and the reference pattern 100; e) detecting each pattern 20 of the second series whose correlation coefficient, in absolute value, is less than a predetermined threshold; f) extracting a characteristic dimension D for each pattern 20 of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; g) calculating an arithmetic mean and a standard deviation of the characteristic dimensions D extracted during step f); h) detecting each pattern 20 of the second series whose characteristic dimension D has a deviation from the arithmetic mean
- the digital image of the reference network 1, provided during step a), comprises a set of pixels, each pixel having an intensity.
- the digital image of the reference network 1, provided during step a) may have a TIFF format (“Tag Image File Format” in English).
- the digital image of reference network 1 may be in grayscale.
- the digital image of the reference grating 1, provided during step a), can come from an electron microscope, preferably scanning.
- step b) can consist of selecting a pattern from among the patterns 10 of the first series, the selected pattern defining the reference pattern 100.
- the reference pattern 100 can be selected by a user via a graphical interface GUI (Graphical User Interface) having a selection window 3, for example square.
- GUI Graphic User Interface
- the selection window 3 can have a reframing function (“crop” in English).
- step b) can include the steps: bi) selecting an initial pattern from among the patterns 10 of the first series; bz) calculating a correlation coefficient between each pattern 10 of the first series and the initial pattern; bs) identifying each pattern 10 of the first series whose correlation coefficient, in absolute value, is greater than a predetermined threshold; b 4 ) defining the reference pattern 100 from a combination of the patterns 10 of the first series identified during step bs).
- the patterns 10 of the first series, identified during step bs), are represented inside selection windows 3 in FIG. 10. These patterns 10 are selected automatically, and not by the user. Step bi) is implemented by the user, but steps b 2 ) to b 4 ) are advantageously implemented by a computer.
- the initial pattern, selected during step bi) by the user, must be representative of a reference pattern.
- the patterns 10 of the first series, identified during step bs), can represent between 0.5% and 1% of the total number of patterns 10 of the first series.
- the reference pattern 100 can be defined during step b) by performing an average of the patterns 10 of the first series.
- Step b) can then consist in defining the reference pattern 100 from an average of the intensities of the pixels of the first series of periodic patterns 10 of the digital images of reference networks 1.
- the digital image of the network to be analyzed 2 comprises a set of pixels, each pixel having an intensity.
- the digital image of the network to be analyzed, provided during step c) may have a TIFF format (“ag lmage Eile Eormat” in English).
- the digital image of the network to be analyzed 2 can be in grayscale.
- the digital image of the network to be analyzed 2, provided during step c), can come from an electron microscope, preferably scanning.
- the network 2 to be analyzed can comprise nanowires, forming periodic patterns, and having a cross section in the shape of a hexagon.
- Step d) is advantageously implemented by a computer.
- the correlation coefficient is advantageously calculated during step d) between the intensity of the pixels of each pattern 20 of the second series and the intensity of the pixels of the reference pattern 100.
- the correlation coefficient is advantageously calculated during the step d) according to the Bravais-Pearson formula, known to those skilled in the art. More precisely, the correlation between the reference pattern 100 and each point of the digital image of the network to be analyzed 2 is carried out by an image correlation function.
- This image correlation function will compare the reference pattern 100, T(x t , y t ), where (x t , y t ) represents the coordinates of each pixel of the reference pattern, with the image of the network at analyze 2, S(x, y), where (x, y) represents the coordinates of each pixel of the network image to be analyzed 2.
- the image correlation function consists in calculating the sum of the products of the coefficients of S (x, y) and T(x t , y t ) for all the positions of the reference pattern 100 with respect to the image of the network to be analyzed 2.
- - X and Y correspond respectively to the matrix of the intensities of the pixels of the image of the grating to be analyzed 2, and to the matrix of the intensities of the pixels of the reference pattern 100.
- step d) is advantageously preceded by the steps: doi) identifying the position of the patterns 20 of the second series on the digital image of the grating 2 to be analyzed; doz) scale the digital image of the network to be analyzed 2 so that the 20 patterns of the second series are in integer.
- the doi) and doz) steps are implemented by computer.
- the step doi) advantageously comprises a step consisting in calculating a correlation coefficient between the digital image of the network to be analyzed 2 and the reference pattern 100.
- step d) is advantageously followed by a step d') consisting in counting a total number of patterns 20 of the second series, each correlation coefficient of which, in absolute value, is greater than the predetermined threshold .
- Step d') is advantageously implemented by a computer.
- Steps e) to h) are executed if the total number of patterns 20 is greater than a predetermined value.
- the connection conditional (symbolized by a diamond) of FIG. 8 tests whether the total number of patterns 20 is greater than said predetermined value.
- Step e) is advantageously implemented by a computer.
- the threshold may be between 0.6 and 0.7.
- the pattern 20a of the second series is classified in the first category.
- the correlation coefficient calculated during step d) between the pattern 20a of the second series and the reference pattern 100 is lower than the predetermined threshold.
- the defects of the first category, detected during step e), can be mapped on the digital image of the network to be analyzed 2.
- Step f) is advantageously implemented by a computer.
- step f) advantageously comprises the steps: f) performing a cutting line for each pattern 20 of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; f 2 ) extract the characteristic dimension D from the cutting line.
- the characteristic dimension D extracted during step f) can be the dimension of one side of the hexagon.
- the characteristic dimension D extracted during step f) can be a distance between two parallel sides of the hexagon, or between two opposite vertices of the hexagon.
- the characteristic dimension D extracted during step f) can also correspond to a diameter of a circle, when the patterns 20 of the second series have a circular section.
- the characteristic dimension D extracted during step f) can also correspond to the dimension of a diagonal, when the patterns 20 of the second series have a square section.
- step f) advantageously comprises a step f) consisting in extracting at least one additional characteristic dimension D′ for each pattern 20 of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold.
- step f) is advantageously preceded by the steps: faith) generating a histogram of the intensities of the pixels of the digital image of the network to be analyzed 2; foz) extract an intensity threshold of the periodic patterns of the second series, from the histogram generated during the step foz).
- step foz) can be performed by the Otsu method, known to those skilled in the art.
- the faith) and foz) steps are implemented by a computer.
- Step g) is advantageously implemented by a computer.
- step g) advantageously comprises a step g′) consisting in calculating an additional arithmetic mean and an additional standard deviation of the additional characteristic dimensions D′ extracted during step f).
- Step h) is advantageously implemented by a computer.
- step h) advantageously comprises a step h′) consisting in classifying, in the second category, each pattern 20 of the second series whose additional characteristic dimension D′ exhibits a deviation from the additional arithmetic mean greater than the additional standard deviation.
- Pattern 20b of the second series is classified in the second category.
- Pattern 20b of the second series has two additional characteristic dimensions D′ which exhibit a deviation from the additional arithmetic mean greater than the additional standard deviation.
- the defects of the second category, detected during step h), can be mapped on the digital image of the network to be analyzed 2.
- an object of the invention is a method for classifying defects in a set of gratings to be analyzed 2 each comprising periodic patterns 20, the method comprising the steps: a) providing a digital image of a reference grating 1, showing a first series of periodic patterns 10; b) defining a reference pattern 100 from the patterns 10 of the first series; c) providing at least one digital image of each grating 2 of the set to be analyzed, showing a second series of periodic patterns 20; the method iterating the following steps, for each digital image of each network to be analyzed 2 of the set: d) calculating a correlation coefficient between each pattern 20 of the second series and the reference pattern 100; e) classifying, in a first category, each pattern 20 of the second series whose correlation coefficient, in absolute value, is less than a predetermined threshold; f) extracting a characteristic dimension D for each pattern of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; g) calculating an arithmetic mean
- an object of the invention is a method for detecting faults in a set of gratings to be analyzed 2 each comprising periodic patterns, the method comprising the steps: a) providing a digital image of a reference grating 1, showing a first series of periodic patterns; b) defining a reference pattern 100 from the patterns 10 of the first series; c) providing at least one digital image of each grating 2 of the set to be analyzed, showing a second series of periodic patterns 20; the method iterating the following steps, for each digital image of each network to be analyzed 2 of the set: d) calculating a correlation coefficient between each pattern 20 of the second series and the reference pattern 100; e) detecting each pattern 20 of the second series whose correlation coefficient, in absolute value, is less than a predetermined threshold; f) extracting a characteristic dimension D for each pattern of the second series whose correlation coefficient, in absolute value, is greater than the predetermined threshold; g) calculating an arithmetic mean and a standard deviation of the characteristic dimensions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/694,790 US20240242479A1 (en) | 2021-09-23 | 2022-09-19 | Method for classifying faults in a network to be analysed |
EP22789217.1A EP4405919A1 (fr) | 2021-09-23 | 2022-09-19 | Procede de classification de defauts d'un reseau a analyser |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR2110018A FR3127319B1 (fr) | 2021-09-23 | 2021-09-23 | Procédé de classification de défauts d’un réseau à analyser |
FRFR2110018 | 2021-09-23 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023046637A1 true WO2023046637A1 (fr) | 2023-03-30 |
Family
ID=78483377
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2022/075982 WO2023046637A1 (fr) | 2021-09-23 | 2022-09-19 | Procede de classification de defauts d'un reseau a analyser |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240242479A1 (fr) |
EP (1) | EP4405919A1 (fr) |
FR (1) | FR3127319B1 (fr) |
WO (1) | WO2023046637A1 (fr) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2791775A1 (fr) * | 1999-01-08 | 2000-10-06 | Schlumberger Technologies Inc | Detection de defauts a base de particularites |
JP2004318488A (ja) * | 2003-04-16 | 2004-11-11 | Konica Minolta Photo Imaging Inc | 製品検査方法及び製品検査装置 |
US20120155740A1 (en) * | 2010-12-17 | 2012-06-21 | Samsung Electronics Co., Ltd. | Method of detecting defect in pattern and apparatus for performing the same |
US20130070078A1 (en) * | 2010-01-05 | 2013-03-21 | Yuji Takagi | Method and device for testing defect using sem |
US9311698B2 (en) | 2013-01-09 | 2016-04-12 | Kla-Tencor Corp. | Detecting defects on a wafer using template image matching |
-
2021
- 2021-09-23 FR FR2110018A patent/FR3127319B1/fr active Active
-
2022
- 2022-09-19 EP EP22789217.1A patent/EP4405919A1/fr active Pending
- 2022-09-19 US US18/694,790 patent/US20240242479A1/en active Pending
- 2022-09-19 WO PCT/EP2022/075982 patent/WO2023046637A1/fr active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2791775A1 (fr) * | 1999-01-08 | 2000-10-06 | Schlumberger Technologies Inc | Detection de defauts a base de particularites |
JP2004318488A (ja) * | 2003-04-16 | 2004-11-11 | Konica Minolta Photo Imaging Inc | 製品検査方法及び製品検査装置 |
US20130070078A1 (en) * | 2010-01-05 | 2013-03-21 | Yuji Takagi | Method and device for testing defect using sem |
US20120155740A1 (en) * | 2010-12-17 | 2012-06-21 | Samsung Electronics Co., Ltd. | Method of detecting defect in pattern and apparatus for performing the same |
US9311698B2 (en) | 2013-01-09 | 2016-04-12 | Kla-Tencor Corp. | Detecting defects on a wafer using template image matching |
Non-Patent Citations (1)
Title |
---|
OLIVER VAN KAICK ET AL: "A Survey on Shape Correspondence", COMPUTER GRAPHICS FORUM, vol. 30, no. 6, 11 September 2011 (2011-09-11), pages 1681 - 1707, XP055069658, ISSN: 0167-7055, DOI: 10.1111/j.1467-8659.2011.01884.x * |
Also Published As
Publication number | Publication date |
---|---|
EP4405919A1 (fr) | 2024-07-31 |
FR3127319B1 (fr) | 2023-09-29 |
FR3127319A1 (fr) | 2023-03-24 |
US20240242479A1 (en) | 2024-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114723701B (zh) | 基于计算机视觉的齿轮缺陷检测方法和系统 | |
EP3234913B1 (fr) | Procede de detection de defaut sur une surface de pneumatique | |
CN109685760B (zh) | 一种基于matlab的slm粉床铺粉图像凸包凹陷缺陷检测方法 | |
EP0115462A2 (fr) | Procédé de reconnaissance automatique d'une image, à partir d'une image correspondante de référence | |
FR2959046A1 (fr) | Methode de controle de l'aspect de la surface d'un pneumatique | |
CN117252882A (zh) | 一种气缸盖质量检测方法及系统 | |
US9189841B2 (en) | Method of checking the appearance of the surface of a tyre | |
EP3008445B1 (fr) | Methode de traitement de l'image numerique de la surface d'un pneumatique en vue de la detection d'une anomalie | |
CN114119603A (zh) | 基于图像处理的快餐盒短射缺陷检测方法 | |
FR3079617A1 (fr) | Methode de detection de cellules presentant au moins une anomalie dans un echantillon cytologique | |
WO2023046637A1 (fr) | Procede de classification de defauts d'un reseau a analyser | |
EP0769760B1 (fr) | Procédé de détection automatique des zones expertisables dans des images de pièces mécaniques | |
CN111882518B (zh) | 一种漏磁数据自适应伪彩色化方法 | |
FR3069079B1 (fr) | Procede de detection de fraude lors d'une reconnaissance d'iris | |
EP4405897A1 (fr) | Procede de caracterisation d'un reseau a analyser comportant des motifs périodiques | |
FR2769733A1 (fr) | Procede d'extraction automatique d'inscriptions imprimees ou manuscrites sur un fond, dans une image numerique multiniveaux | |
WO2012143199A1 (fr) | Analyse de l'image numerique de la surface interne d'un pneumatique - traitement des points de fausse mesure | |
EP1129432B1 (fr) | Procede de comparaison d'images enregistrees formees de pixels representant des equipotentielles d'au moins une puce de circuit integre | |
FR2978274A1 (fr) | Procede de traitement differencie de zones d'une image | |
FR3038760A1 (fr) | Detection d'objets par traitement d'images | |
EP3745350B1 (fr) | Procédé de détection de précipités dans un alliage par traitement d'image | |
EP4303811A1 (fr) | Procédé et dispositif de traitement de données multidimensionnelles de microscopie pour la localisation de déformations dans un échantillon | |
EP1873483B1 (fr) | Procédé de détermination d'au moins une caractéristique du format d'un fragment de pneumatique, et procédé d'examen d'un échantillon de fragments de pneumatiques | |
JP2004340978A (ja) | 色分類装置及び色分類方法並びに色むら検査装置 | |
Choi et al. | Defect extraction in photomask image using high order moment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22789217 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18694790 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022789217 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022789217 Country of ref document: EP Effective date: 20240423 |