Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F18/00—Pattern recognition
  • G06F18/20—Analysing
  • G06F18/24—Classification techniques
  • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
  • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T7/00—Image analysis
  • G06T7/10—Segmentation; Edge detection
  • G06T7/12—Edge-based segmentation
• • H—ELECTRICITY
  • H10—SEMICONDUCTOR DEVICES; ELECTRIC SOLID-STATE DEVICES NOT OTHERWISE PROVIDED FOR
  • H10P—GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
  • H10P74/00—Testing or measuring during manufacture or treatment of wafers, substrates or devices
  • H10P74/23—Testing or measuring during manufacture or treatment of wafers, substrates or devices characterised by multiple measurements, corrections, marking or sorting processes
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; 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
  • G06T2207/10061—Microscopic image from scanning electron microscope
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/20—Special algorithmic details
  • G06T2207/20081—Training; Learning
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/20—Special algorithmic details
  • G06T2207/20084—Artificial neural networks [ANN]
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; 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

Definitions

• This disclosure relates to measuring overlay (i.e., overlay offsets) for semiconductor devices, and more specifically to measuring overlay offsets using machine learning.
• overlay metrology In semiconductor fabrication, misalignment between process layers causes unwanted shi fts in the positions of structures in one process layer as compared to the positions of structures in another process layer. Such a shift (i.e., displacement) is referred to as overlay, or equivalently, as an overlay offset. Measuring these shifts is referred to as overlay metrology. Accurate overlay metrology is important for measuring process drift and thus for establishing and maintaining process control, especially during the ramp-up period for a new semiconductor process and/or device.
• Scanning electron microscopes are useful tools for overlay metrology because they have high resolution and can image a .structure regardless of its shape or size. Identifying structures (e.g.. patterns of interest ) in SEM images for overlay measurements presents significant challenges, however. Process variation can cause the shape, size, and orientation of structures to vary considerably, especially during the ramp-up period. As a result, traditional object-recognition algorithms may be unable to align on two structures for which overlap is to be measured.
• Overlay metrology may be performed by using machine learning to define regions corresponding to respective structures (or groups of structures) in respective process layers of a semiconductor die and using the regions to calculate an overlay offset between the structures.
• a method includes obtaining an image of a portion of a semiconductor die showing one or more structures in a first process layer and one or more structures in a second process layer. The method also includes using machine learning to define a first region on the image that at least partially includes the one or more structures in the first process layer and to define a second region on the image that at least partially includes the one or more structures in the second process layer. The method further includes using the first region and the second region to calculate an overlay offset between the one or more structures in the first process layer and the one or more structures in the second process layer.
• a non-transitory computer-readable storage medium stores one or more programs for execution by one or more processors.
• the one or more programs include instructions for performing the above method.
• a system includes a scanning electron microscope (SEM), one or more processors, and memory' storing one or more programs for execution by the one or more processors.
• the one or more programs include instructions for performing the above method.
• Figure 1 A is an illustration of a SEM image of a portion of a semiconductor die, showing a first structure in a first process layer and a plurality of second structures in a second process layer.
• Figure 1B is an illustration of the SEM image of Figure 1 A with a first region, defined using machine learning, that bounds the first structure in the first process layer and a second region, defined using machine learning, that bounds the plurality of second structures in the second process layer, in accordance with some embodiments.
• Figure 2A is an illustration of another SEM image of a portion of a semiconductor die, showing structures in a first process layer and a structure in a second process layer.
• Figure 2B is an illustration of the SEM image of Figure 2A with a first region, defined using machine learning, that bounds one of the structures in the first process layer and a second region, defined using machine learning, that partially includes the structure in the second process layer, in accordance with some embodiments.
• Figure 3 A is an illustration of yet another SEM image of a portion of a semiconductor die, showing a structure in a first process layer and a pair of structures in a second process layer.
• Figure 3B is an illustration of the SEM image of Figure 3B with a first region, defined using machine learning, that partially includes the structure in the first process layer and a second region, defined using machine learning, that partially includes a respective structure of the pair of structures in the second process layer, in accordance with some embodiments.
• Figure 4A is an illustration of still another SEM image of a portion of a semiconductor die, showing a plurality of structures in a first process layer and a structure in a second process layer.
• Figure 4B is an illustration of the SEM image of Figure 4A with a first region, defined using machine learning, that bounds the plurality of structures in the first process layer and a second region, defined using machine learning, that bounds the structure in the second process layer.
• Figure 4C is an illustration of the SEM image of Figure 4A with multiple first regions, defined using machine learning, that partially include respective structures of the plurality of structures in the first process layer and multiple second regions, defined using machine learning, that partially include the structure in the second process layer.
• Figure 5 is a flowchart showing an overlay-metrology method in accordance with some embodiments.
• Figure 6 is a block diagram of a semiconductor inspection system in accordance with some embodiments.
• a machine-learning classifier may be trained to define regions corresponding to respective structures, or groups of structures, in an image of a semiconductor die.
• the image is a scanning-electron-microscope (SEM) image.
• SEM scanning-electron-microscope
• the structures and/or groups of structures are fabricated in different process layers on the die.
• the regions are used to calculate an overlay offset between the structures.
• FIG. 1A is an illustration of a scanning-electron-microscope (SEM) image 100 of a portion of a semiconductor die.
• the SEM image 100 includes a structure 102 and a plurality of structures 104.
• the structure 102 and/or the plurality of structures 104 may be conductive (e.g., metal).
• the structure 102 and/or the plurality of structures 104 may be conductive (e.g., metal) plugs.
• the structure 102 is a via that conductive!y connects a first pair of metal layers and the structures 104 are vias that conduct! vely connect a second pair of metal layers or are contacts that conduetively connect a conductive layer (e.g., metal layer) to silicon.
• a conductive layer e.g., metal layer
• T he structure 102 is in a different process layer of the semiconductor die than the plurality of structures 104, In some embodiments, the structure 102 is in a first via layer, while the plurality of structures 104 is in a second via layer (e.g., below the first via layer) or a contact layer. Other examples are possible.
• machine learning e.g., a machine-learning classifier, which may he trained in accordance with step 502 of the method 500, below
• the first region 106 bounds the structure 102 and/or the second region 108 hounds the plurality of structures 104.
• the first region 106 thus may surround and enclose the structure 102, such that it entirely includes the structure 102, and the second region 108 may surround and enclose the plurality of structures 104, such that it entirely includes the plurality ' of structures 104.
• the first region 106 may be a box (e.g., a rectangular box) that bounds the structure 102 and the second region 108 may be a box (e.g., a rectangular box) that bounds the plurality of structures 104.
• a box that is defined using machine learning to bound a structure or a plurality of structures is referred to as a bounding box.
• the first region 106 and/or second region 108 may alternatively be defined to have other shapes besides boxes.
• the first region 106 and second region 108 may be used to calculate an overlay offset between the structure 102 and the plurality of structures 104.
• a separation e.g., in two dimensions in the plane of the SEM image 100, or in either the horizontal or vertical dimension of the plane of the SEM image 100
• the overlay offset may be calculated as the distance between the center of the first region 106 and the center of the second region 108.
• FIG. 2A is an illustration of another SEM image 200 of a portion of a semiconductor die.
• the SEM image 200 includes a first structure 201 and a second structure 202 in a first process layer, along with a third structure 204 in a second process layer that is below the first process layer.
• the first structure 201 has an L-shape with horizontal and vertical arms
• the second structure 202 is rectangular
• the third structure 204 is a line that runs beneath the horizontal arm of the first structure 201 and parallel to the vertical arm of the first structure 201.
• the third structure 204 runs vertically between the second structure 202 and the vertical arm of the first structure 201, but in a lower process layer than the process layer of the first structure 201 and second structure 202.
• the first and second process layers are metal layers: the first structure 201 and second structure 202 are metal structures in a first metal layer, while the third structure 204 is a metal line in a second metal layer below the first metal layer. Other examples are possible.
• machine learning e.g., a machine-learning classifier, which may be trained in accordance with step 502 of the method 500, below
• first region 206 hounds the second structure 202 and/or the second region 208 includes a portion of the third structure 204 (i.e ⁇ , partially includes the third structure 204).
• the first region 206 is a bounding box (e.g., a rectangular bounding box) that bounds the second structure 202 and/or the second region 208 is a box (e.g., a rectangular box) that encloses part of the third structure 204.
• the first region 206 and/or second region 208 may alternatively be defined to have other shapes besides boxes.
• the first region 206 and second region 208 may be used to calculate an overlay offset between the second structure 202 and the third structure 204, In some embodiments, a separation (e.g., in the horizontal dimension of the SEM image 200) between the first region 206 and second region 208 is calculated to determine the overlay offset.
• the overlay offset may be calculated as the distance (e.g., the horizontal distance) between the center of the first region 206 and the center of the second region 208,
• Figures 1B and 2B show examples in which overlay offsets are calculated using the separation between regions that are defined using machine learning.
• regions that are defined using machine learning may be used as starting regions within which to detect the edges of structures, and overlay offsets are calculated using measured distances between detected edges,
• FIG 3 A is an illustration of yet another SEM image 300 of a portion of a semiconductor die.
• the SEM image 300 includes a structure 302 in a first process layer and a pair of structures 304-1 and 304-2 in a second process layer.
• the structure 302 is a line (e.g., a metal line) with rounded corners.
• the structures 304-1 and 304-2 may be conductive plugs (e.g., conductive vias or contacts, which may be metal) that contact the stmcture 302, in some embodiments, the structures 304-1 and 304-2 may be metal vias in a via layer immediately above (or immediately below) the first process layer, which is a metal layer. Other examples are possible.
• the structures 304-1 and 304-2 are substantially circular in shape, although they may be elliptical to a degree (e.g., due to process variation).
• machine learning e.g., a machine-learning classifier, which may be trained in accordance with step 502 of the method 500, below
• first region 306 that corresponds to and includes a portion of the structure 302 (i.e., partially includes the structure 302) and a second region 308 that corresponds to and includes a portion of the structure 304-1 (i.e., partially includes the structure 304-1).
• the first region 306 includes a portion of an edge 307 of the structure 302.
• the first region 306 includes an end of the structure 302, such that the portion of the edge 307 is at an end of the structure 302.
• the second region 308 includes a portion of an edge 309 of the structure 304-1.
• the second region 308 includes a portion of the circumference of the structure 304-1 (i.e., the portion of the edge 309 is a portion of the circumference of the structure 304-1).
• the first region 306 and the second region 308 are boxes (e.g., rectangular boxes).
• the first region 306 and/or second region 308 may alternatively be defined to have other shapes besides boxes.
• the first region 306 and second region 308 may be used to calculate an overlay offset between the structure 302 and the structure 304-1 by serving as starting regions within which to perform edge detection to detect the portions 307 and 309. Once the portions 307 and 309 have been respectively detected within the first region 306 and the second region 308, a distance 310 between them is calculated.
• the distance 310 gives the overlay offset between the structure 302 and the structure 304-1 (e.g., the overlay offset equals the distance 310 or equals the distance 310 plus a constant).
• FIG 4A is an illustration of stil l another SEM image 400 of a portion of a semiconductor die.
• the SEM image 400 includes a plurality' of structures 402 in a first process layer and a structure 404 in a second process layer.
• the structure 404 is a horizontal line (e.g., a metal line).
• the structures 402, which are arranged in an array, may be conductive plugs (e.g., conductive vias or contacts, which may be metal). In some embodiments, the structures 402 may be vias in a via layer or contacts in a contact layer. Other examples are possible.
• the structures 402 are substantially circular in shape, although they may be elliptical to a degree (e.g,, due to process variation).
• the structures 402 are substantially evenly spaced, although their positions may vary to a degree from ideal evenly-spaced positions (e.g., due to process variation).
• machine learning e.g., a machine-learning classifier, which may be trained in accordance with step 502 of the method 500, below
• first region 406 bounds the plurality of structures 402, such that all of the structures 402 are within the first region 406 (i.e., the first region 406 includes all of the structures 402).
• second region 408 bounds the structure 404, such that the entirety of the structure 404 is within the second region 408 (i.e., the second region 408 includes the structure 404).
• the first region 406 is a bounding box (e.g., a rectangular bounding box) that bounds the plurality of structures 402 and/or the second region 408 is a bounding box (e.g., a rectangular bounding box) that bounds the structure 404.
• the first region 406 and/or second region 408 may alternatively be defined to have other shapes besides boxes.
• the first region 406 and second region 408 may be used to calculate an overlay offset between the plurality of structures 402 and the structure 404.
• a separation e.g., in two dimensions in the plane of the SEM image 400, or in either the vertical or horizontal dimension In the plane of the SEM image 400
• the overlay offset may be calculated as the distance (or the distance plus a constant) between the center of the first region 406 and the center of the second region 408.
• machine learning e.g., a machine-learning classifier, which may be trained in accordance with step 502 of the method 500, below
• first regions 410-1 through 410-4 that correspond to and include respective portions of respective structures 402 of the plurality of structures 402 (e.g., respective structures 402 in the bottom row of the plurali ty of structures 402).
• Machine learning e.g., the machine-learning classifier
• second regions 412-1 through 412-4 correspond to and include respective portions of the structure 404.
• Each of the first regions 410-1 through 410-4 includes a portion of au edge of a respective structure 402 (e.g., an edge portion facing the structure 404).
• Each of the second regions 412-1 through 412-4 includes a respective portion of an edge of the structure 404 (e.g., a portion of the top edge of the structure 402 across from a respective structure 402).
• the first regions 410-1 through 410-4 and the second regions 412-1 through 412-4 are boxes (e.g., rectangular boxes).
• the first regions 410-1 through 410-4 and/or the second regions 412-1 through 412-4 may alternatively be defined to have other shapes besides boxes.
• Edge detection is performed to detect the edge portions in the first regions 410-1 through 410-4 and the second regions 412-1 through 412-4. Once these edge portions have been detected, distances between them are calculated: a first distance is calculated between the edge portion of a structure 402 in the first region 410-1 and the edge portion of the structure 404 in the second region 412-1 , a second distance is calculated between the edge portion of a structure 402 in the first region 410-2 and the edge portion of the structure 404 in the second region 410-2, a third distance is calculated between the edge portion of a structure 402 in the first, region 410-3 and the edge portion of the structure 404 in the second region 412-3, and a fourth distance is calculated between the edge portion of a structure 402 in the first region 410-4 and the edge portion of the structure 404 in the second region 412-4.
• first regions 410 and four second regions 412 are shewn in the example of Figure 4C, other numbers of regions are possible.
• These distances which may be calculated by analogy to the distance 310 ( Figure 3B), give respective overlay offsets between respective structures 402 and the structure 404 (e.g., the overlay offsets equal respective distances or equal respective distances plus a constant).
• An average overlay offset between the plurality of structures 402 and the structure 404 may be determined using an a verage of these distances.
• FIG 5 is a flowchart showing an. overlay-metrology method 500 in accordance with some embodiments.
• the method 500 may be performed by a computer system (e.g., the computer system of the semiconductor inspection sy stem 600, Figure 6).
• a machine-learning classifier is trained (502) using images of respective instances of a die portion from respective semiconductor die.
• the images are annotated with respecti ve instances of a first region and a second region.
• the images have been annotated by a user using a graphical drawing program to indicate the respecti ve instances of the first region and the second region.
• the machine-learning classifier is a neural network.
• the machine-learning classifier is a convolutional neural network (CNN) (e.g., a Mask-R-CNN).
• CNN convolutional neural network
• the machine- learning classifier may be a different type of neural network or a different type of machine- learning classifier besides a neural network.
• An image is obtained (504) of a portion of a semiconductor die showing one or more structures in a first process layer and one or more structures in a second process layer.
• the image is (506) a SEM image.
• the image may be obtained directly from an imaging tool (e.g., the SEM 632, Figure 6) or may be obtained from a memory in which the image was previously stored. Examples of the image include, without limitation, the image 100 ( Figure 1 A), the image 200 ( Figure 2A), the image .300 ( Figure 3 A), or the image 400 ( Figure 4A).
• a first region is defined (508) on the image that at least partially includes the one or more structures in the first process layer.
• the first region is defined using (510) the machine-learning classifier trained in step 502.
• the first region may be (512) a first box (e.g., a rectangular box).
• the first box is a bounding box (e.g., region 106, Figure 1 B; region 206, Figure 2B; region 406, Figure 4B) that bounds the one or more structures in the first process layer.
• the first region may include a portion of an edge (i.e., only the portion of the edge, and not the entire edge) of a first structure that is one of the one or more structures in the first process layer.
• the first region may be a first box (e.g., a rectangular box) (e.g., region 306, Figure 3B; one of the regions 410-1 through 410-4, Figure 4C ) that includes the portion of the edge of the first structure.
• a second region is defined (514) on the image that at least partially includes the one or more structures in the second process layer.
• the second region is defined using (516) the machine-learning classifier trained in step 502.
• the second region may be (518) a second box (e.g., a rectangular box).
• the second box is a bounding box (e.g., region 108, Figure 1B; region 408, Figure 4B) that bounds the one or more structures in the second process layer.
• the second region may include a portion of an edge (i.e., only the portion of the edge, and not the entire edge) of a second structure that is one of the one or more structures in the second process layer.
• the second region may be a second box (e.g., a rectangular box) that includes the portion of the edge of the second structure.
• the machine-learning of steps 508 and 514 is implemented using a neural network.
• a convolutional neural network e.g., a Mask-R- CNN
• a different type of machine-learning classifier is used to implement the machine-learning of steps 508 and 514.
• an overlay offset between the one or more structures in the first process layer and the one or more structures in the second process layer is calculated (520),
• a separation is calculated
• a distance between the center of the first region and the center of the second region is calculated (524).
• the distance may be in a particular direction (e.g., may be a vector difference).
• the distance may be in two dimensions in the plane of the image, or in either the vertical or horizontal dimension in the plane of the image.
• a portion of an edge of a first structure i n the first region and a portion of an edge of a second structure in the second region are detected (526).
• T he first structure is one of the one or more structures in the first process layer and the second structure is one of the one or more structures in the second process layer.
• These edge portions are detected by applying an edge-detection algorithm to the first region and the second region.
• the first region and the second region thus may serve as respective search regions within which to perform edge detection (i.e., within which to search for edges).
• a distance (e.g., distance 310, Figure 3B) between the portion of the edge of the first structure in the first region and the portion of the edge of the second structure in the second region is calculated (528) (e.g,, as described for Figures 3B and 4C),
• the method 500 provides a more robust approach to overlay metrology than techniques that use traditional object- recognition algorithms.
• the method 500 thus allows overlay metrology to be performed successfully and accurately in situations in which process variations causes techniques that use traditional object-recognition algorithms to fail,
• the overlay offset may be used to identify process changes for establishing or improving process control.
• the overlay offset may also, or alternatively, be used to disposition a wafer, For example, the decision whether to continue to process, rework, or scrap a wafer may be based in whole or in part on overlay offsets for semiconductor die on the wafer.
• FIG. 6 is a block diagram of a semiconductor inspection system 600 in accordance with some embodiments.
• the semiconductor inspection system 600 may be used for overlay metrology (e.g., for performing the overlay-metrology method 500, Figure 5).
• the semiconductor inspection system 600 includes a SEM 632 (or other imaging tool) and a computer system with one or more processors 602 (e.g,, CPUs and/or GPUs), user interfaces 606, memory 610, and communication bus(es) 604 interconnecting these components.
• the SEM 632 is communicatively coupled to the computer system through one or more wired and/or wireless networks 630.
• the semiconductor inspection system 600 includes multiple SEMs 632 (or other imaging tools) communicatively coupled with the computer system (e.g,, through the one or more wired and/or wireless networks 630).
• the user interfaces 606 may include a display 607 and one or more input devices
• the display 607 may display results, including overlay offsets and/or regions defined using machine learning (e.g., the first and second regions defined in the method 500, Figure 5).
• Memory 610 includes volatile and/or non-volatile memory.
• Memory 610 (e.g., the non-volatile memory within memory 610) includes a non-transitory computer-readable storage medium.
• Memory 610 optionally includes one or more storage devices remotely located from the processors 602 and/or a non-transitory computer-readable storage medium that is removably inserted into the computer system of the semiconductor inspection system 600.
• memory 610 (e.g., the non-transitory computer-readable storage medium of memory 610) stores the following modules and data, or a subset or superset thereof: an operating system 612 that includes procedures for handling various basic system sendees and for performing hardware-dependent tasks, images 614 (e.g,, SEM images) for which overlay offsets are to be calculated, a training module 616 for training a machine-learning classifier (e.g., per step 502 of the method 500, Figure 5), a machine-learning module 620 for defining regions on the images 614 (e.g., per steps 508 and 514 of the method 500, Figure 5) (e.g., using the machine-learning classifier trained by the training module 616), an overlay calculation module 622 for calculating overlay offsets (e.g., per step 520 of the method 500, Figure 5), and a reporting module 628 for reporting results (e.g., for displaying results on the display 607).
• an operating system 612 that includes procedures for handling various basic system sende
• the training module 616 includes annotated images 618 (e.g., annotated SEM images) that are used to train the machine-learning classifier.
• the training module 616 is absent and the machine-learning module 620 uses a machine-learning classifier trained on a different computer system.
• the overlay calculation module 622 includes an edge-detection module 624 for detecting edges in defined regions (e.g., per step 526 of the method 500, Figure 5) and/or a separation-calculation module 626 for calculating separations between defined regions (e.g., per step 522 of the method 500, Figure 5) and/or distances between detected edges (e.g., per step 528 of the method 500, Figure 5),
• the memory 610 e.g., the noil-transitory computer-readable storage medium of the memoy 610) may inc lude instructions for performing all or a portion of the method 500 ( Figure 500).
• Each of the modules stored in the memory 610 corresponds to a set of instructions for performing one or more functions described herein. Separate modules need not be implemented as separate software programs. The modules and various subsets of the modules may be combined or otherwise re-arranged, in some embodiments, the memory 610 stores a subset or superset of the modules and/or data structures identified above.
• Figure 6 is intended more as a functional description of various features that may be present in a semiconductor inspection system than as a structural schematic.
• the functionality of the computer system in the semiconductor inspection system 600 may be split between multiple devices.
• a portion of the modules stored in the memory 610 may alternatively be stored in one or more other computer systems communicatively coupled with the computer system of the semiconductor inspection system 600 through one or more networks.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Data Mining & Analysis (AREA)
• Quality & Reliability (AREA)
• Bioinformatics & Cheminformatics (AREA)
• Evolutionary Computation (AREA)
• Evolutionary Biology (AREA)
• General Engineering & Computer Science (AREA)
• Bioinformatics & Computational Biology (AREA)
• Artificial Intelligence (AREA)
• Life Sciences & Earth Sciences (AREA)
• Image Analysis (AREA)
• Testing Or Measuring Of Semiconductors Or The Like (AREA)
• Exposure And Positioning Against Photoresist Photosensitive Materials (AREA)
• Optical Radar Systems And Details Thereof (AREA)

Priority Applications (5)

Applications Claiming Priority (6)

Publications (1)

Family

ID=79031289

Family Applications (1)

Country Status (8)

Cited By (1)

Families Citing this family (1)

Citations (7)

Family Cites Families (12)

• 2020
  • 2020-12-29 US US17/135,998 patent/US11967058B2/en active Active
• 2021
  • 2021-06-07 TW TW110120546A patent/TWI864292B/zh active
  • 2021-06-23 CN CN202180042124.4A patent/CN115699282A/zh active Pending
  • 2021-06-23 EP EP21830308.9A patent/EP4150662A4/en active Pending
  • 2021-06-23 IL IL298625A patent/IL298625B2/en unknown
  • 2021-06-23 KR KR1020227045264A patent/KR102797875B1/ko active Active
  • 2021-06-23 WO PCT/US2021/038563 patent/WO2021262778A1/en not_active Ceased
  • 2021-06-23 JP JP2022579815A patent/JP7490094B2/ja active Active

Patent Citations (7)

Non-Patent Citations (1)

Also Published As

Similar Documents

Legal Events