Systems and methods for defect location barning in charged particle systems

By using machine learning models based on GDS layout data in charged particle beam systems to generate template images, the problems of low resolution and low efficiency of defect detection in traditional methods are solved, and defect detection and positioning with high accuracy and high efficiency are achieved.

CN118922859APending Publication Date: 2024-11-08ASML NETHERLANDS BV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380022131.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-02-17
Filing Date
2023-01-19
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing charged particle beam systems have limited resolution when detecting and positioning defects in integrated circuits, especially when the sample has multiple defects, making it difficult to accurately identify or index defect locations in image analysis, and the traditional methods are inefficient, Temporary and prone to errors.

Method used

Using a machine learning model based on GDS layout data to generate distortion-free, defect-free and noise-free template images. By comparing and checking the image with the template images, automatically identifying and defragment locations on the warehousing samples, improving the accuracy and throughput of defect detection .

Benefits of technology

Improves the accuracy and overall throughput of defect detection, reduces the dependence of manual labeling, enhances the compatibility and reliability of the system, and reduces spatial resolution losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118922859A_ABST
    Figure CN118922859A_ABST
Patent Text Reader

Abstract

Apparatus, systems, and methods for providing a beam for defect detection and defect location binning associated with a sample of a charged particle beam system. A method of image analysis may include obtaining an image of a sample, identifying features captured in the image of the sample, generating a template image according to a design layout of the identified features, comparing the image of the sample to the template image, and processing the image based on the comparison. In some embodiments, a method of image analysis may include obtaining an image of a sample, identifying features captured in the obtained image of the sample, mapping the obtained image to a template image generated according to a design layout of the identified features, and analyzing the image based on the mapping.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. application 63 / 311,414, filed on February 17, 2022, which is incorporated herein by reference in its entirety. Technical Field

[0003] The description herein relates to the field of charged particle beam systems, and more particularly, to systems and methods for detection and position binning of defects associated with samples inspected by charged particle beam systems. Background Art

[0004] In the manufacturing process of integrated circuits (ICs), unfinished or completed circuit components are inspected to ensure that they are manufactured according to design and are free of defects. Inspection systems that utilize optical microscopes typically have resolutions as low as a few hundred nanometers; and the resolution is limited by the wavelength of light. As the physical size of IC components continues to decrease to below 100 nanometers or even below 10 nanometers, there is a need for inspection systems that are capable of higher resolution than inspection systems that utilize optical microscopes.

[0005] Charged particle (e.g., electron) beam microscopes, such as scanning electron microscopes (SEMs) or transmission electron microscopes (TEMs), which are capable of resolutions down to less than a nanometer, are used as practical tools for inspecting IC components with feature sizes below 100 nanometers. Using an SEM, electrons from a single primary electron beam or electrons from multiple primary electron beams can be focused on a location of interest on a wafer being inspected. The primary electrons interact with the wafer and can be backscattered or can cause the wafer to emit secondary electrons. The intensity of the electron beam, including the backscattered electrons and the secondary electrons, can vary based on the properties of the internal and external structures of the wafer, thereby indicating whether the wafer is defective. Summary of the invention

[0006] Embodiments of the present disclosure provide apparatus, systems, and methods for defect detection and defect location binning associated with a sample of a charged particle beam system.

[0007] One aspect of the present disclosure relates to a method of image analysis. The method may include obtaining an image of a sample, identifying features captured in the image of the sample, generating a template image based on a design layout of the identified features, comparing the image of the sample to the template image, and processing the image based on the comparison.

[0008] Another aspect of the present disclosure relates to a system for image analysis. The system may include a controller including a circuit device configured to cause the system to perform a method of image analysis. The controller may cause the system to obtain an image of a sample, identify features captured in the image of the sample, generate a template image based on a design layout of the identified features, compare the image of the sample to the template image, and process the image based on the comparison.

[0009] Another aspect of the present disclosure relates to a non-transitory computer-readable medium storing a set of instructions executable by one or more processors of a computing device to cause the computing device to perform a method for image analysis. The method may include obtaining an image of a sample, identifying features captured in the image of the sample, generating a template image based on a designed layout of the identified features, comparing the image of the sample to the template image, and processing the image based on the comparison.

[0010] Another aspect of the present disclosure relates to a method of image analysis. The method may include obtaining an image of a sample, identifying features captured in the obtained image of the sample, mapping the obtained image to a template image generated according to a design layout of the identified features, and analyzing the image based on the mapping.

[0011] Another aspect of the present disclosure relates to a system for image analysis. The system may include a controller including a circuit device configured to cause the system to perform a method of image analysis. The controller may cause the system to obtain an image of a sample, identify features captured in the obtained image of the sample, map the obtained image to a template image generated according to a design layout of the identified features, and analyze the image based on the mapping.

[0012] Another aspect of the present disclosure relates to a non-transitory computer-readable medium storing a set of instructions executable by one or more processors of a computing device to cause the computing device to perform a method for image analysis. The method may include obtaining an image of a sample, identifying features captured in the obtained image of the sample, mapping the obtained image to a template image generated according to a design layout of the identified features, and analyzing the image based on the mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram illustrating an exemplary electron beam inspection (EBI) system consistent with embodiments of the present disclosure.

[0014] Figure 2 It is a diagram showing an embodiment consistent with the present disclosure. Figure 1 Schematic diagram of an exemplary multi-beam system that is a portion of an exemplary charged particle beam inspection system.

[0015] Figure 3The diagram shows a flow chart representing an exemplary method of image analysis.

[0016] Figure 4 The diagram represents a flow chart of an exemplary method of image analysis consistent with embodiments of the present disclosure.

[0017] Figure 5A A flow chart representing a process for generating an exemplary location template consistent with an embodiment of the present disclosure.

[0018] Figure 5B-5E The diagram is consistent with the embodiment of the present disclosure. Figure 5A A schematic diagram of the steps associated with a process for generating a position template is shown.

[0019] Figure 6 is a schematic diagram illustrating a simulation template image generated from a position template consistent with an embodiment of the present disclosure.

[0020] Figure 7 is a schematic diagram illustrating an exemplary layout of a mask pattern consistent with an embodiment of the present disclosure.

[0021] Figure 8 is a schematic diagram of an exemplary system for defect detection and defect location binning consistent with an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description relates to the accompanying drawings, in which the same numbers in different drawings represent the same or similar elements, unless otherwise indicated. The implementations set forth in the following description of the exemplary embodiments do not represent all implementations consistent with the present disclosure. On the contrary, they are merely examples of apparatus and methods consistent with aspects related to the subject matter recorded in the appended claims. For example, although some embodiments are described in the context of utilizing electron beams, the present disclosure is not limited thereto. Other types of charged particle beams may be similarly applied. In addition, other imaging systems such as optical imaging, photoelectric detection, x-ray detection, far ultraviolet inspection, deep ultraviolet inspection, etc. may be used.

[0023] Electronic devices are made up of circuits formed on a silicon wafer called a substrate. Many circuits can be formed together on the same silicon wafer and are called an integrated circuit, or IC. The size of these circuits has decreased dramatically so that more circuits can fit on a substrate. For example, an IC chip in a smartphone can be as small as a thumbnail but can include more than 2 billion transistors, each less than 1 / 1000 the size of a human hair.

[0024] Manufacturing these extremely small ICs is a complex, time-consuming, and expensive process that typically involves hundreds of individual steps. An error in even one step can result in a defect in the finished IC that renders it unusable. Therefore, one goal of the manufacturing process is to avoid such defects in order to maximize the number of functional ICs manufactured in the process, i.e., to improve the overall yield of the process.

[0025] An integral part of improving yields is monitoring the chip manufacturing process to ensure that it is producing sufficient numbers of functional integrated circuits. One way to monitor the process is to inspect the chip circuit structures at different stages of their formation. Inspection can be performed using a scanning electron microscope (SEM). The SEM can be used to image these extremely small structures, in effect taking a "photo" of the structure of the wafer. The image can be used to determine if the structure was formed correctly and if it was formed in the correct location. If the structure is defective, the process can be adjusted so that the defect is less likely to occur again. Defects can be generated during various stages of semiconductor processing. For the reasons stated above, it is important to detect defects accurately, efficiently, and as early as possible.

[0026] The working principle of SEM is similar to that of a camera. A camera takes pictures by receiving and recording the brightness and color of light reflected or emitted from a person or object. SEM takes "pictures" by receiving and recording the energy or number of electrons reflected or emitted from a structure. Before taking such "pictures", an electron beam can be provided to the structure, and when the electrons are reflected or emitted ("emitted") from the structure, the detector of the SEM can receive and record the energy or number of these electrons to generate an image. In order to take such "pictures", some SEMs use a single electron beam (referred to as "single-beam SEMs"), while some SEMs use multiple electron beams (referred to as "multi-beam SEMs") to take multiple "pictures" of the wafer. By using multiple electron beams, the SEM can provide more electron beams to the structure to obtain these multiple "pictures", thereby causing more electrons to be emitted from the structure. Therefore, the detector can receive more emitted electrons at the same time and generate images of the structure of the wafer with higher efficiency and faster speed.

[0027] For example, a voltage contrast inspection can be used as an early indicator of the electrical yield associated with a sample. SEM images including voltage contrast patterns typically show random occurrences of faults associated with features of the sample (e.g., different gray levels of the features). For example, grayscale intensity levels in a SEM inspection image may deviate from grayscale intensity levels in a defect-free SEM image, thereby indicating that the sample associated with the SEM inspection image includes one or more defects (e.g., electrical open or short faults). In some embodiments, other characteristics in the SEM inspection image (e.g., in addition to or in addition to the voltage contrast characteristics) may deviate from the defect-free SEM image (e.g., characteristics related to line edge roughness, line width roughness, local critical dimension uniformity, necking, bridging, edge placement errors, etc.), thereby indicating that the sample associated with the SEM inspection image includes one or more defects.

[0028] The system can perform distortion correction on the SEM inspection image and align the SEM inspection image with the template image to detect one or more defects on the inspected sample. For example, one or more defects on the inspected sample can be detected by comparing the aligned SEM image with a plurality of reference images (e.g., during die-to-die inspection, comparing the inspection image with two defect-free images of the sample).

[0029] However, even after performing distortion correction on the SEM inspection image, image analysis during inspection is limited. Because the sample can have many defects, the SEM inspection image can differ greatly from the template SEM image, resulting in misalignment of the SEM inspection image and the template image.

[0030] Additionally, multiple reference images may be used to detect one or more defects, assuming that defects are random and occur infrequently, thereby reducing the likelihood that a reference image includes the same defect as an inspection image. However, it is not uncommon for a reference image to include the same defect as an inspection image. When a reference image includes a defect (e.g., the same defect as the inspection image or another defect), the system may not be able to identify the true defect in the inspection image due to noisy data, or the system may not be able to use characteristics of the inspection image (e.g., physical features such as a bridge).

[0031] Due to the misalignment of the inspection image and the template image, the system may not be able to accurately identify or index the location of the defect on the sample (eg, the image analysis algorithm may fail during image alignment).

[0032] For the sake of clarity, the relative sizes of components in the drawings may be exaggerated. In the following description of the drawings, identical or similar reference numerals refer to identical or similar components or entities, and only the differences with respect to individual embodiments are described.

[0033] As used herein, unless otherwise specifically stated, the term "or" encompasses all possible combinations unless not feasible. For example, if it is specified that a component may include A or B, then unless otherwise specifically stated or not feasible, the component may include A, or B, or A and B. As a second example, if it is specified that a component may include A, B, or C, then unless otherwise specifically stated or not feasible, the component may include A, or B, or C, or A and B, or A and C, or B and C, or A and B and C.

[0034] Figure 1 An exemplary electron beam inspection (EBI) system 100 consistent with embodiments of the present disclosure is illustrated. The EBI system 100 may be used for imaging. Figure 1 As shown, the EBI system 100 includes a main chamber 101, a load / lock chamber 102, an electron beam tool 104, and an equipment front end module (EFEM) 106. The electron beam tool 104 is located in the main chamber 101. The EFEM 106 includes a first load port 106a and a second load port 106b. The EFEM 106 may include (one or more) additional load ports. The first load port 106a and the second load port 106b receive a wafer front opening transport box (FOUP) containing wafers (e.g., semiconductor wafers or wafers made of (one or more) other materials) or samples to be inspected (wafers and samples can be used interchangeably). A "batch" is a plurality of wafers that can be loaded as a batch for processing.

[0035] One or more robots (not shown) in the EFEM 106 can transport the wafer to the load / lock chamber 102. The load / lock chamber 102 is connected to a load / lock vacuum pump system (not shown) that removes gas molecules in the load / lock chamber 102 to reach a first pressure lower than atmospheric pressure. After reaching the first pressure, one or more robots (not shown) can transport the wafer from the load / lock chamber 102 to the main chamber 101. The main chamber 101 is connected to a main chamber vacuum pump system (not shown) that removes gas molecules in the main chamber 101 to reach a second pressure lower than the first pressure. After reaching the second pressure, the wafer is inspected by the electron beam tool 104. The electron beam tool 104 can be a single beam system or a multi-beam system.

[0036] The controller 109 is electrically connected to the electron beam tool 104. The controller 109 may be a computer configured to perform various controls of the EBI system 100. Figure 1 106 as being external to the structure including the main chamber 101, the load / lock chamber 102, and the EFEM 106, but it is understood that the controller 109 may be part of the structure.

[0037] In some embodiments, the controller 109 may include one or more processors (not shown). The processor may be a general or special electronic device capable of manipulating or processing information. For example, the processor may include any number of central processing units (or "CPUs"), graphics processing units (or "GPUs"), optical processors, programmable logic controllers, microcontrollers, microprocessors, digital signal processors, intellectual property (IP) cores, programmable logic arrays (PLAs), programmable array logic (PALs), general array logic (GALs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), systems on chips (SoCs), application specific integrated circuits (ASICs), and any combination of any type of circuit capable of data processing. The processor may also be a virtual processor, which includes one or more processors distributed on multiple machines or devices coupled via a network.

[0038] In some embodiments, the controller 109 may also include one or more memories (not shown). The memory may be a general or special electronic device capable of storing code and data accessible by a processor (e.g., via a bus). For example, the memory may include any number of random access memories (RAM), read-only memories (ROM), optical disks, magnetic disks, hard drives, solid-state drives, flash drives, secure digital (SD) cards, memory sticks, compact flash (CF) cards, or any combination of any type of storage device. The code may include an operating system (OS) and one or more application programs (or "applications") for a specific task. The memory may also be a virtual memory, which includes one or more memories distributed on multiple machines or devices coupled via a network.

[0039] Reference now Figure 2 , which is a schematic diagram illustrating an exemplary electron beam tool 104 consistent with an embodiment of the present disclosure, the electron beam tool including as Figure 1 In some embodiments, the electron beam tool 104 can be operated as a single beam inspection tool. Figure 1The multi-beam electron beam tool 104 (also referred to herein as the apparatus 104) includes an electron source 201, a Coulomb aperture plate (or "gun aperture plate") 271, a converging lens 210, a source conversion unit 220, a primary projection system 230, a motorized stage 209, and a sample holder 207, which is supported by the motorized stage 209 to hold a sample 208 to be inspected (e.g., a wafer or a photomask). The multi-beam electron beam tool 104 may also include a secondary projection system 250 and an electronic detection device 240. The primary projection system 230 may include an objective lens 231. The electronic detection device 240 may include a plurality of detection elements 241, 242, and 243. The beam splitter 233 and the deflection scanning unit 232 may be located inside the primary projection system 230.

[0040] The electron source 201, the Coulomb aperture plate 271, the converging lens 210, the source conversion unit 220, the beam splitter 233, the deflection scanning unit 232, and the primary projection system 230 may be aligned with the primary optical axis 204 of the apparatus 104. The secondary projection system 250 and the electron detection device 240 may be aligned with the secondary optical axis 251 of the apparatus 104.

[0041] The electron source 201 may include a cathode (not shown) and an extractor or an anode (not shown), wherein during operation, the electron source 201 is configured to emit primary electrons from the cathode and the primary electrons are extracted or accelerated by the extractor and / or the anode to form a primary electron beam 202, which forms a primary beam cross (virtual or real) 203. The primary electron beam 202 can be visualized as being emitted from the primary beam cross 203.

[0042] The source conversion unit 220 may include an image forming element array (not shown), an aberration compensator array (not shown), a beam limiting aperture array (not shown), and a pre-bent micro-deflector array (not shown). In some embodiments, the pre-bent micro-deflector array deflects multiple primary beam waves 211, 212, 213 of the primary electron beam 202 to orthogonally enter the beam limiting aperture array, the image forming element array, and the aberration compensator array. In some embodiments, the device 104 can be operated as a single beam system so that a single primary beam wave is generated. In some embodiments, the converging lens 210 is designed to focus the primary electron beam 202 into a parallel beam and orthogonally impinge on the source conversion unit 220. The image forming element array may include a plurality of micro-deflectors or micro-lenses to affect the multiple primary beam waves 211, 212, 213 of the primary electron beam 202 and form multiple (virtual or real) parallel images of the primary beam cross 203, one parallel image for each primary beam wave 211, 212, and 213. In some embodiments, the aberration compensator array may include a field curvature compensator array (not shown) and an astigmatism compensator array (not shown). The field curvature compensator array may include a plurality of micro lenses to compensate for the field curvature aberration of the primary beam waves 211, 212, and 213. The astigmatism compensator array may include a plurality of micro stigmators to compensate for the astigmatism aberration of the primary beam waves 211, 212, and 213. The beam limiting aperture array may be configured to limit the diameter of each of the primary beam waves 211, 212, and 213. Figure 2 Three primary beams 211, 212, and 213 are shown as an example, and it should be understood that the source conversion unit 220 can be configured to form any number of primary beams. The controller 109 can be connected to Figure 1 The controller 109 may be used to control various parts of the EBI system 100, such as the source conversion unit 220, the electronic detection device 240, the primary projection system 230, or the motorized stage 209. In some embodiments, as explained in additional detail below, the controller 109 may perform various image and signal processing functions. The controller 109 may also generate various control signals to manage the operation of the charged particle beam inspection system.

[0043] The converging lens 210 is configured to focus the primary electron beam 202. The converging lens 210 may also be configured to adjust the current of the primary beam waves 211, 212, and 213 downstream of the source conversion unit 220 by changing the focusing power of the converging lens 210. Alternatively, the current may be changed by changing the radial size of the beam limiting apertures corresponding to the individual primary beam waves within the beam limiting aperture array. The current may be changed by changing the radial size of the beam limiting apertures and the focusing power of the converging lens 210. The converging lens 210 may be an adjustable converging lens, which may be configured so that the orientation of its first principal plane is movable. The adjustable converging lens may be configured magnetically, which may cause the off-axis beam waves 212 and 213 to illuminate the source conversion unit 220 at a rotation angle. The rotation angle varies with the focusing power of the adjustable converging lens or the orientation of the first principal plane. The converging lens 210 may be an anti-rotation converging lens, which may be configured to keep the rotation angle unchanged when the focusing power of the converging lens 210 changes. In some embodiments, the converging lens 210 may be an adjustable anti-rotation converging lens, wherein the rotation angle does not change when its focusing power and the orientation of its first principal plane vary.

[0044] The objective lens 231 can be configured to focus the beams 211, 212, and 213 onto the sample 208 for inspection, and in the current embodiment, three detection points 221, 222, and 223 can be formed on the surface of the sample 208. The Coulomb aperture 271 is configured to block peripheral electrons of the primary electron beam 202 in operation to reduce the Coulomb effect. The Coulomb effect can expand the size of each of the detection points 221, 222, and 223 of the primary beams 211, 212, 213, and thus reduce the inspection resolution.

[0045] The beam splitter 233 may be, for example, a Wien filter, which includes an electrostatic deflector ( Figure 2 ). In operation, the beam splitter 233 can be configured to exert an electrostatic force on individual electrons of the primary beams 211, 212, and 213 via an electrostatic dipole field. The electrostatic force is equal in magnitude but opposite in direction to the magnetic force exerted on the individual electrons by the magnetic dipole field of the beam splitter 233. Thus, the primary beams 211, 212, and 213 can pass at least substantially straight through the beam splitter 233 with a deflection angle that is at least substantially zero.

[0046] The deflection scanning unit 232 is configured in operation to deflect the primary beam waves 211, 212 and 213 to scan the detection points 221, 222 and 223 on the separate scanning areas in a portion of the surface of the sample 208. In response to the incidence of the primary beam waves 211, 212 and 213 or the detection points 221, 222 and 223 on the sample 208, electrons are ejected from the sample 208 and three secondary electron beams 261, 262 and 263 are generated. Each of the secondary electron beams 261, 262 and 263 typically includes secondary electrons (electron energy ≤ 50 eV) and backscattered electrons (electron energy is between 50 eV and the landing energy of the primary beam waves 211, 212 and 213). The beam splitter 233 is configured to deflect the secondary electron beams 261, 262 and 263 toward the secondary projection system 250. The secondary projection system 250 then focuses the secondary electron beams 261, 262, and 263 onto the detection elements 241, 242, and 243 of the electron detection device 240. The detection elements 241, 242, and 243 are arranged to detect the corresponding secondary electron beams 261, 262, and 263 and generate corresponding signals, which are sent to the controller 109 or a signal processing system (not shown) to, for example, construct an image of the corresponding scan area of ​​the sample 208.

[0047] In some embodiments, the detection elements 241, 242, and 243 detect the corresponding secondary electron beams 261, 262, and 263, respectively, and generate corresponding intensity signal outputs (not shown) to an image processing system (e.g., controller 109). In some embodiments, each detection element 241, 242, and 243 may include one or more pixels. The intensity signal output of a detection element may be the sum of the signals generated by all pixels within the detection element.

[0048] In some embodiments, the controller 109 may include an image processing system, which includes an image collector (not shown), a storage device (not shown). The image collector may include one or more processors. For example, the image collector may include a computer, a server, a mainframe, a terminal, a personal computer, any kind of mobile computing device, or the like, or a combination thereof. The image collector may be communicatively coupled to the electronic detection device 240 of the device 104 through a medium such as an electrical conductor, a fiber optic cable, a portable storage medium, IR, Bluetooth, the Internet, a wireless network, radio, or the like, or a combination thereof. In some embodiments, the image collector may receive a signal from the electronic detection device 240 and may construct an image. Thus, the image collector may collect an image of the sample 208. The image collector may also perform various post-processing functions, such as generating contours, superimposing indicators on the collected image, and the like. The image collector may be configured to perform adjustments to the brightness and contrast of the collected image, and the like. In some embodiments, the storage device may be a storage medium, such as a hard disk, a flash drive, a cloud storage device, a random access memory (RAM), other types of computer-readable memory, and the like. The storage device may be coupled to the image collector and may be used to save the scanned raw image data as raw images and post-processed images.

[0049] In some embodiments, the image collector can collect one or more images of the sample based on the imaging signal received from the electronic detection device 240. The imaging signal can correspond to a scanning operation for performing charged particle imaging. The collected image can be a single image including multiple imaging areas. The single image can be stored in a storage device. The single image can be an original image that can be divided into multiple regions. Each of the regions can include an imaging area containing features of the sample 208. The collected image can include multiple images of a single imaging area of ​​the sample 208 sampled multiple times in a time series. Multiple images can be stored in a storage device. In some embodiments, the controller 109 can be configured to perform image processing steps on multiple images of the same position of the sample 208.

[0050] In some embodiments, the controller 109 may include a measurement circuit device (e.g., an analog-to-digital converter) to obtain the distribution of the detected secondary electrons. The electron distribution data collected during the detection time window, combined with the corresponding scan path data of each of the primary beam waves 211, 212, and 213 incident on the wafer surface, can be used to reconstruct an image of the inspected wafer structure. The reconstructed image can be used to reveal various features of the internal or external structure of the sample 208, and thus can be used to reveal any defects that may exist in the wafer.

[0051] In some embodiments, the controller 109 may control the motorized stage 209 to move the sample 208 during inspection of the sample 208. In some embodiments, the controller 109 may enable the motorized stage 209 to continuously move the sample 208 in one direction at a constant speed. In other embodiments, the controller 109 may enable the motorized stage 209 to change the movement speed of the sample 208 over time according to the steps of the scanning process.

[0052] although Figure 2 The apparatus 104 is shown using three primary electron beams, but it should be understood that the apparatus 104 may use two or more primary electron beams. The present disclosure does not limit the number of primary electron beams used in the apparatus 104. In some embodiments, the apparatus 104 may be a SEM for lithography, defect inspection, or a combination thereof.

[0053] Compared to a single charged particle beam imaging system ("single beam system"), a multiple charged particle beam imaging system ("multi-beam system") can be designed to optimize throughput for different scanning modes. Embodiments of the present disclosure provide a multi-beam system having the ability to optimize throughput for different scanning modes by using beam arrays with different geometries to accommodate different throughput and resolution requirements.

[0054] A non-transitory computer-readable medium may be provided that stores information for use by a processor (e.g., Figure 1-Figure 2 The processor of the controller 109 of the memory 100 (the processor of the memory 100) performs instructions for image processing, data processing, beam scanning, database management, graphic display, operation of a charged particle beam device or another imaging device, etc. Common forms of non-transitory media include, for example, floppy disks, flexible disks, hard disks, solid-state drives, magnetic tapes or any other magnetic data storage media, CD-ROMs, any other optical data storage media, any physical media with a pattern of holes, RAM, PROM and EPROM, FLASH-EPROM or any other flash memory, NVRAM, cache, registers, any other memory chip or cassette, and network versions thereof.

[0055] Reference now Figure 3 , which illustrates a flow chart representing an exemplary image analysis method. Figure 3 As shown, the image analysis process 300 is generally used to detect one or more defects and identify the locations of the detected defects on a sample.

[0056] At step 310, the system (e.g., Figure 1The EBI system 100 of the present invention can obtain an inspection image 302 (e.g., a SEM image generated during inspection of a sample) and a template image 304. For example, the template image can be a defect-free SEM image of the sample. The template image can include one or more regions of the sample in a field of view (FOV). The template image 304 can include one or more manually labeled high-resolution reference SEM images 304. i-n For example, a user may use an inspection system to capture multiple high-resolution SEM images of an area of ​​a sample and manually mark the locations of features based on the mask information.

[0057] At step 320, the inspection image 302 is aligned with a template image 304 that includes a marking of at least one or more features of the inspection image. In some cases, a processor of the inspection system may perform the alignment of the images to identify the location of one or more defects on the inspected sample.

[0058] At step 330 , the inspection system detects one or more defects on the inspection sample by comparing the aligned image to a plurality of reference images (eg, during die-to-die inspection, comparing the inspection image to two defect-free images of the sample).

[0059] At step 340, the inspection system performs distortion correction on the inspection image 302. Distortion in the inspection image 302 may occur for a variety of reasons including, but not limited to, system operating conditions, tool factors, calibration, sample processing history, and other factors. However, even after performing distortion correction on the inspection image, image analysis using process 300 is limited. Because the sample may have many defects, the inspection image may differ greatly from the template image to which the inspection image is compared, resulting in misalignment of the inspection image and the template image.

[0060] Furthermore, under the assumption that defects are random and occur rarely, multiple reference images (eg, reference image 304) may be used. i-n ) to detect one or more defects, thereby reducing the likelihood that the reference image includes the same defects as the inspection image. However, it is not uncommon for the reference image to include the same defects as the inspection image. When the reference image includes defects (e.g., the same defects as the inspection image or other defects), the system may not be able to identify the true defects in the inspection image due to noisy data, or the system may not be able to use characteristics of the inspection image (e.g., physical features such as bridges).

[0061] At step 350, the position binning module of the inspection system may index one or more positions of the identified defect on the sample (e.g., by binning or categorizing the location or position of the defect on the sample). For example, indexing the one or more positions of the identification of the defect on the sample may include marking the position of the feature having the defect relative to the sample (e.g., row index, column index, row number, column number, etc.).

[0062] There may be several challenges in identifying and binning defects using manually labeled template images 304 in process 300, such as generating a representative template image, misalignment of the inspection image and the template image, etc. Generating a labeled representative template image may include several steps, such as, but not limited to, collecting multiple high-resolution SEM images of the region of interest, drawing mask information associated with the region of interest, counting column and row numbers, and marking features accordingly. One or more of these steps are performed manually by a user or a group of users, which makes the process inefficient, cumbersome, and prone to error. In some cases, the region of interest may not be covered by a single SEM reference image, and one or more reference images may be "stitched" or combined to fully represent the region of interest. This can make the process less efficient and inconsistent. In addition, once imaged, the inspection area, scan width, scan rate, inspection mode, etc. of the captured reference SEM image cannot be changed. In addition, one or more reference SEM images may be subject to drift and distortion aberrations caused in part by surface charging, which can severely affect spatial resolution and critical dimension measurements. Although digital image correction techniques may be employed to address drift and distortion artifacts, such techniques are time consuming and may also introduce variability and negatively impact inspection throughput. It would therefore be desirable to provide a system and method for image analysis that includes a template image and a substantially distortion-free reference image that are automatically generated based on a predetermined mask design layout.

[0063] Reference now Figure 4 , which illustrates a flow chart representing an exemplary image analysis method consistent with embodiments of the present disclosure. In some embodiments, one or more steps of image analysis process 400 (also referred to herein as process 400) may be performed by Figure 1 The process is performed by the EBI system 100, the processor associated with the EBI system 100, and the location bin module associated with the EBI system 100. Figure 4 One or more steps not shown in the drawings may be added, deleted, edited, or ordered differently as desired.

[0064] In step 410, a detection system or device such as EBI system 100 may collect a sample (e.g., Figure 2The inspection image 402 may include a portion of the sample 208 or a defect of interest (DOI) or a region of interest (ROI) of the sample. The inspection image 402 may include a low-resolution SEM image, a high-resolution SEM image, or a backscattered electron image acquired using the EBI system 100. In some embodiments, the inspection image 402 may be acquired in a continuous scanning mode (CS mode), a hot spot mode (HS mode), or a link scanning mode (LS mode), or other appropriate inspection modes.

[0065] In some embodiments, process 400 may include determining one or more attributes of inspection image 402. Determining the attributes may include identifying features of the image of the sample based on the location of the features, the size of the features, the pattern, or other characteristics. In some embodiments, identifying the features may involve knowledge of process steps, equipment types, process conditions, and other factors. In some embodiments, the attributes of inspection image 402 may also include, but are not limited to, magnification, scan width, scan area, scan rate, resolution, and the like.

[0066] Step 410 of process 400 may also include generating a trained template image 404. In some embodiments, the trained template image 404 may include, for example, a reference image simulated using a machine learning model. The trained template image 404 may be generated based on the identified features corresponding to the inspection image 402 or the mask layout information corresponding to the identified region of interest represented by the inspection image 402. In some embodiments, the trained template image 404 image may include one or more regions of the sample in the FOV. In some embodiments, the trained template image 404 may include user-defined data (e.g., the location of the feature on the sample). In some embodiments, the trained template image 404 may be rendered from the layout design data. For example, the layout design of the sample may be stored in a layout file of the wafer design. The layout file may be a graphic database system (GDS) format, a graphic database system II (GDS II) format, an open artwork system exchange standard (OASIS) format, a Caltech intermediate format (CIF), etc. The wafer design may include a pattern or structure for inclusion on the wafer. The pattern or structure may be a mask pattern for transferring features from a lithography mask or mask to a wafer. In some embodiments, a layout in a GDS or OASIS format, etc., may include feature information stored in a binary file format, representing plane geometry, text, and other information related to the wafer design. In some embodiments, the layout design may correspond to the FOV of the inspection system. In some embodiments, the layout design may be selected based on the sample being inspected (e.g., based on the layout identified on the sample).

[0067] In some embodiments, generating the trained template image 404 may include generating a position template in a GDS mask layout or a design layout, such as Figure 4 The position templates in the GDS mask layout can be automatically generated. In the context of the present disclosure, "automatic" refers to a method of performing operations with minimal or no manual intervention and is primarily controlled or implemented using a machine. In this example, automatically generating a position template refers to identifying a position template within the GDS design layout based on the identified features of the inspection image without user input and using a software-implemented algorithm.

[0068] Generating a trained template image 404 may also include generating a trained template SEM image based on the position template using a combination of the GDS layout data and one or more reference SEM images, such as Figure 4 . In some embodiments, at least one reference SEM image or a set of reference SEM images may be used to train the machine learning model. For example, training the model may include mapping the GDS mask information to corresponding features in the SEM reference image. In some embodiments, the SEM reference image may be a substantially defect-free, high-resolution image obtained using an inspection device such as the EBI system 100. When training, the machine learning model may be configured to generate a template SEM image from the GDS mask information data. The trained template image 404 may be an image that is substantially noise-free, substantially defect-free, or substantially distortion-free. In the context of the present disclosure, a "substantially noise-free image" refers to an image with a negligible level of noise, a "substantially defect-free image" refers to an image with a negligible, undetectable small number of defects, and a "substantially distortion-free image" refers to a negligible amount of distortion that results in minimal to no loss in spatial resolution of the entire image.

[0069] Step 420 of process 400 may include aligning an inspection image (eg, inspection image 402) with a template image (eg, trained template image 404). A processor or system (eg, Figure 1 The EBI 100 of the present invention can be configured to align the inspection image 402 and the trained template image 404 so that the location of the features of the inspection image 402 corresponds to the location of the features on the template image 404 based on the GDS layout data. In some embodiments, performing the alignment of the inspection image and the template image can be used to verify the location, size, or other properties of one or more features of the identified area of ​​the inspection image 402. For example, a comparison or alignment of an inspection image of an area of ​​interest of a sample with a corresponding template image generated based on the GDS layout data can determine whether the feature exists at an expected location, or whether the size of the feature is within a tolerance range, or other characteristics associated with the feature.

[0070] Step 430 of process 400 may include detecting defects and identifying the location of the defects in inspection image 402 relative to template image 404. In some embodiments, inspection image 402 may include one or more defects, including but not limited to electrical defects such as electrical opens, electrical shorts, leakage paths, or physical defects such as necking, bridging, edge placement errors, holes, broken wires, etc. In some embodiments, for example, defects in the inspection image may have certain intensity levels (e.g., "brightness" or "darkness" grayscale levels of a voltage contrast image) that are different from non-defective features identified as "bright" features. Although defects may be identified as "dark" features, it should be understood that defects may be illustrated as various grayscale levels or other characteristics (e.g., line edge roughness, line width roughness, local critical dimension uniformity, necking, bridging, edge placement errors, holes, broken wires, etc.).

[0071] Step 440 of process 400 may include binning the locations of the one or more defects identified in step 430. In some embodiments, binning the locations of the defects of inspection image 402 may include indexing the identified one or more locations of the defects on the sample. Indexing may include marking the location of the feature with the defect relative to the sample with a column index and a row index or a column number and a row number.

[0072] An image analysis process using a trained template image based on GDS layout data (e.g., process 400) can have many advantages over existing image analysis processes (e.g., process 300) in terms of improving the accuracy and throughput of defect detection. An image analysis process using a template SEM image trained with a machine learning model can have some or all of the advantages discussed herein:

[0073] 1. Undistorted template images - A trained machine learning model configured to generate template SEM images based on GDS layout data allows for distortion-free template images. In the proposed image analysis method, a trained machine learning or neural network model is used to simulate a GDS-based template image that is unaffected by operating tool conditions and aberrations associated with the inspection device.

[0074] 2. Enhanced template image compatibility - GDS-based simulation template images can be compatible with various inspection systems with different scan widths, scan lengths, and multiple scan modes. For example, the location template in the GDS layout data can be configured by the user and can be generated based on the identified region of interest. On the other hand, in traditional image analysis methods, the scan area, scan rate, or scan mode of the template image is fixed and cannot be adjusted.

[0075] 3. Defect-free and noise-free template images - In addition to being distortion-free, GDS-based template images or trained template images can also be defect-free and noise-free, which can allow accurate detection and location identification of defects.

[0076] 4. Higher defect inspection throughput - Traditional image analysis methods using manually labeled template images require collecting a large number of high-resolution images of the area of ​​interest under different conditions and scanning parameters. Position binning requires manual drawing of templates in the inspection image and manual marking of defects or features of interest. Such process steps are inefficient and prone to errors. On the other hand, image analysis based on comparison of inspection images with template images trained by machine learning based on GDS layout information can enhance overall throughput and accuracy.

[0077] Reference now Figure 5A , which illustrates a flow chart of a process 500 for generating an exemplary location template in a GDS design layout consistent with an embodiment of the present disclosure. The process for generating the location template may include the following steps: obtaining GDS layout information (step 510), grouping features (e.g., polygons) of the GDS layout information (step 520), forming boundary coordinates (step 530), and generating a location template (step 540). It should be understood that one or more of the steps of process 500 can be implemented by a processor (e.g., a processor of controller 109), a system, or a module of the system, so that the location template is automatically generated without human intervention.

[0078] In step 510, the processor or system may obtain layout information such as GDS layout information from a database or storage module configured to store mask layout information. In some embodiments, the processor or system may be configured to obtain GDS layout information or data for an area corresponding to one or more features identified in the inspection image 402. The GDS layout information may include data associated with the location coordinates of the feature, the mask ID, the process ID, and other data that can be used to identify the feature or an area of ​​the sample containing the feature. In some embodiments, the processor or system may be configured to obtain a GDS layout or GDS pattern including at least one identified feature of the inspection image 402. An exemplary GDS pattern 512 obtained by the system or processor is shown in FIG. Figure 5B Shown in.

[0079] like Figure 5BAs illustrated, the GDS pattern 512 may include features 514. Although the features 514 are illustrated as polygons and the GDS pattern 512 shows a polygon pattern, it should be understood that the GDS pattern 512 may include hole patterns, line patterns, and other patterns. In some embodiments, the GDS pattern may represent a mask pattern associated with an identified region of a sample in an inspection image. In some embodiments, the GDS pattern 512 may include a plurality of features arranged in an array of cell structures 516, each cell structure 516 including an array of features 514. In some embodiments, the cell structure 516 may include one or more different features, such as holes, lines, polygons, or combinations thereof. The GDS pattern 512 may include a one-dimensional or two-dimensional array of cell structures 516.

[0080] In step 520, the processor or system may group the features 514 (e.g., the polygons in Figure 5A ) as repeating patterns based on the distance between adjacent features 514 in the X direction, the Y direction, or both. As illustrated, the gap or distance between cell structures 516 in the Y direction may be represented as c, d, or e. In some embodiments, the distance between adjacent cell structures 516 in the Y direction may be uniform or non-uniform. Although not shown, in a two-dimensional array of cell structures in the GDS pattern 512, the distance between adjacent cell structures in the X direction may be uniform or non-uniform.

[0081] In some embodiments, the distance between adjacent features 514 in the X direction, represented as "a i ", and the distance between adjacent features 514 in the Y direction, represented as "b i ", may be uniform or non-uniform. In this case, "adjacent features" in the Y direction refer to features that are directly and vertically above or below a feature, while "adjacent features" in the X direction refer to the immediately adjacent features to the left or right of a feature.

[0082] In some embodiments, the features 514 may be grouped based on the distance between the features and the cell structures to form grouped repeating patterns 526, as Figure 5C shown. In some embodiments, the distance between the features and the cell structures may be user-defined. For example, the user may define the values of a i , b i , c, d, or e, and may also define the relationship between one or more of these parameters. In a two-dimensional array of cell structures 516, the user may define the gap-distance relationship for one or more images or regions of interest. As an example, the user may set boundary conditions to form a set of features where a i < c and b i < c, or a i < d and bi <d, or a i <e and b i <e, or a i <c and b i = c or d or e. It should be understood that although not shown or mentioned, other configurations and user-defined configurations are also possible.

[0083] In step 530, the processor or system may determine the boundary coordinates and boundary profile 532 of the grouped repeating pattern 526, as Figure 5D illustrated. The grouped repeating pattern 526 may include a plurality of features 514 that satisfy boundary conditions defined by the user based on the inspection image, or a predefined set of boundary conditions. In some embodiments, the boundary profile 532 of the grouped repeating pattern 526 may be determined using computational geometry algorithms such as, but not limited to, the convex hull algorithm. It should be understood that other algorithms may also be used as needed.

[0084] In some embodiments, the processor or system may index the positions of the features 514 in the grouped repeating pattern 526, also referred to herein as blocks. Indexing may include tagging the features with feature identifiers or layer index identifiers. As an example, layer index 18 may be located in column number 6 and row number 2, or column index 6 and row index 2. Figure 5D An enlarged view of block 526 is shown, including indexed features arranged in 12 columns and 4 rows. In some embodiments, the features of block 526 or the positions within block 526 may be indexed based on the distance from one or more edges of the boundary profile 532 or defined mask edges, which may be obtained from GDS layout information. In some embodiments, the features of block 526 may be identified by position coordinates on the x-axis and y-axis. The position coordinates may be based on the relative distance from a predefined edge of the boundary profile 532.

[0085] In some embodiments, the system or processor may index one or more of the identified positions of the features on the sample (e.g., bin or classify the positions or orientations of the features on the sample). For example, indexing the one or more identified positions may assist in identifying the orientation of a defect on the sample based on a comparison of the inspection image (e.g., inspection image 402) and a trained template image (e.g., trained template image 404). If a defect is detected on the inspection image relative to the trained template image, then a tag (e.g., group identifier, block identifier, first via in the first row, fourteenth via in the third row, etc.) of the orientation of the features from the trained template image corresponding to the defect may be stored for position binning.

[0086] In step 540, the system or processor may generate a position template 546 based on the GDS layout information after grouping and indexing. The position template 546 may include N arranged grouping repeating patterns 526, such as Figure 5E As previously described, the characteristics of the group repeating pattern 526 may be configured or predetermined by a user. The position template 546 may include an area of ​​the GDS mask layout that includes at least one feature of the inspection image 402. In some embodiments, information associated with the position template 546 may be stored in a storage device such as Figure 1 The information associated with the position template 546 may include coordinate data, size and orientation of features, size and orientation of grouped repeating patterns, spacing between features, spacing between unit structures, spacing between grouped repeating patterns, number of grouped repeating patterns, number of features, feature shapes, and other data.

[0087] Reference now Figure 6 , which illustrates a schematic diagram of an exemplary simulation template image generated from a GDS location template consistent with an embodiment of the present disclosure.

[0088] Figure 6 A schematic diagram of an exemplary automatically generated location template 610 in a GDS layout is shown. The location template 610 may be substantially similar to Figure 5E The position template 546 and can be obtained by, for example Figure 5A The process 500 is generated by the process 500. It should be understood that the process 500 is an exemplary process, and steps may be added, deleted, reordered, or modified as needed. In some embodiments, the position template 610 may include at least one or more features of the inspection image 402, or may represent a region of interest based on the inspection image 402. In some embodiments, the region of interest may include one or more defects, and the position index or binning of the position template may be used to bin the one or more defects identified in the inspection image.

[0089] like Figure 6 As illustrated, a region of interest 620 may be determined by a system or processor. A machine learning model or deep convolutional neural network model may be trained to generate a simulated SEM image 630 from the identified region of interest 620. The machine learning model may be trained by mapping one or more features from the GDS layout information to corresponding one or more features of an inspected image, such as an image obtained using an inspection system (e.g., Figure 2 A high-resolution SEM reference image 640 obtained by the device 104 of FIG. 104. Compared with conventional image analysis techniques, a smaller set of inspected reference images may be required to train the machine learning model because the machine learning model is trained based on a combination of GDS layout information and corresponding reference images.

[0090] When training a machine learning model, a reference image of a mask pattern or a mask plate pattern can be used as a model input, and the real information can include an aligned SEM image. Features of the mask such as a hole pattern, a line pattern, or a polygon can be represented by a "bright" area, and the non-patterned area of ​​the mask can be represented by a "dark" area. Training of the machine learning model can include feeding multiple SEM images of one or more mask areas from a GDS layout pattern to create a database of reference simulated SEM images. In some alternative embodiments, features of the mask can be represented by a "dark" area, and non-patterned areas of the mask can be represented by a "bright" area. It should be understood that detectable differences in the grayscale of patterned and non-patterned areas of the mask can also be used to train a machine learning model using SEM images of the mask.

[0091] Reference now Figure 7 , which illustrates a schematic diagram of an exemplary GDS layout of a mask consistent with an embodiment of the present disclosure. The GDS layout 700 may include a mask pattern 705, a location template 720 including one or more grouped repeating patterns 726, and each grouped repeating pattern 726 including a plurality of features. It should be understood that although the mask pattern 705 illustrates a hole pattern, other patterns may also exist.

[0092] In some embodiments, a machine learning model may be trained using one or more SEM images of the mask pattern 705 and corresponding GDS layout information. The machine learning model may be trained to generate a template SEM image of one or more regions of the mask pattern 705. In some embodiments, one or more grouped repeating patterns 726 may include a feature of interest 734 identified by the system based on one or more attributes of the inspection image. As an example, the feature of interest 734 may be indexed as column 5, row 2 in the grouped repeating pattern 726-1. When aligned with the inspection image, such as Figure 4 As described in step 420 of , if defects are identified in the region of the inspection image 402 corresponding to the region of interest 734 , the defects may be binned accordingly.

[0093] Figure 8 8 is a schematic diagram of a system for defect detection and defect location binning consistent with an embodiment of the present disclosure. System 800 may include an inspection system 810, a GDS-based template image generation component 820, an alignment component 830, and an indexing component 840. Inspection system 810, repair and defect detection component 820, alignment component 830, and indexing component 840 may be electrically coupled to each other (directly or indirectly) physically (e.g., via a cable) or remotely. Inspection system 810 may be about Figure 1 and 2 The system described is used to acquire an image of a wafer (see, for example, Figure 2 In some embodiments, components of system 800 may be implemented as one or more servers (e.g., where each server includes its own processor). In some embodiments, components of system 800 may be implemented as software that can obtain data from one or more databases of system 800. In some embodiments, system 800 may include one server or multiple servers. In some embodiments, system 800 may include a controller (e.g., Figure 1 Controller 109, Figure 2 One or more modules implemented by the controller 109).

[0094] Inspection system 810 may include a sample (e.g., Figure 2 Data of an inspection image of sample 208) is transmitted to one or more components of system 800.

[0095] The GDS-based template image generation 820 may include a processor 822 and a storage device 824. The component 820 may also include a communication interface 826 for sending data to the alignment component 830. The processor 822 may be configured to perform one or more functions, including but not limited to identifying one or more features of the inspection image, training a machine learning model based on the GDS layout information, generating a position template in the GDS layout information, etc. In some embodiments, the processor 822 may be configured to generate a position template that includes at least one or more identified regions of interest from the inspection image. The processor 822 may also be configured to generate a grouped repeating pattern, or to generate a boundary contour, or to index a grouped repeating pattern.

[0096] The alignment component 830 may include a processor 832 and a storage device 834. The alignment component 830 may also include a communication interface 826 that sends data to the index component 840. The processor 832 may be configured to index the trained template image (e.g., Figure 4 The trained template image 404) and the inspection image (e.g., Figure 4 The processor 832 may be configured to align the inspection image with the machine learning model simulated reference image. Using the alignment, the processor 832 may be configured to identify one or more locations of one or more defects in the inspection image based on the GDS-based template image simulated by the machine learning model. The identified locations of the one or more defects may be binned based on an index of the location template in the GDS file.

[0097] For example, the reference image can be a defect-free image of the sample. In some embodiments, the reference image can include one or more regions of the sample in the FOV. In some embodiments, the reference image can include user-defined data (e.g., the location of features on the sample). In some embodiments, the reference image can be a gold image (e.g., a high-resolution, defect-free image). In some embodiments, the reference image can be rendered based on layout design data or a simulated image from a trained machine learning model.

[0098] The alignment component 830 may send data including the identified locations of the inspection images to the indexing component 840 .

[0099] The indexing component 840 may include a processor 842 and a storage device 844. The indexing component 840 may also include a communication interface 846 that receives data from the alignment component 830. The processor 842 may be configured to index one or more locations of the identified defects on the sample (e.g., bin or categorize the locations or orientations of the defects on the sample). For example, indexing the one or more locations of the identification of the defect on the sample may include marking the orientation of the feature having the defect relative to the sample (e.g., the first via in the first row, the fourteenth via in the third row, etc.).

[0100] Advantageously, due to the alignment of the inspection image and the template image, the processor 842 may be configured to accurately identify and index the location of defects on the sample.

[0101] A non-transitory computer-readable medium consistent with embodiments of the present disclosure may be provided that stores a controller for controlling an electron beam tool (e.g., Figure 1 The instructions may include instructions for a processor of a controller 109 of the controller 109. For example, the instructions may include obtaining an inspection image of the sample, identifying features or attributes of the inspection image, generating a template image based on GDS layout information, generating a position template in the GDS layout, or aligning the template image with the inspection image. Common forms of non-temporary media include, for example, floppy disks, flexible disks, hard disks, solid-state drives, tapes or any other magnetic data storage media, compact disk read-only memories (CD-ROMs), any other optical data storage media, any physical media with a pattern of holes, random access memories (RAMs), programmable read-only memories (PROMs) and erasable programmable read-only memories (EPROMs), FLASH-EPROMs or any other flash memories, non-volatile random access memories (NVRAMs), caches, registers, any other memory chips or cassettes, and network versions thereof.

[0102] The embodiments may also be described using the following terms:

[0103] 1. A method for image analysis, the method comprising:

[0104] obtaining an image of the sample;

[0105] identifying features captured in the image of the sample;

[0106] generating a template image according to the design layout of the identified features;

[0107] comparing the image of the sample to the template image; and

[0108] The image is processed based on the comparison.

[0109] 2. The method according to clause 1, wherein generating the template image comprises:

[0110] generating a location template in the design layout, the location template representing a portion of the acquired image; and

[0111] A template image is generated based on the position template.

[0112] 3. The method of any of clauses 1 and 2, wherein generating the template image further comprises: training a machine learning model by mapping information associated with the design layout to information associated with the reference image; and

[0113] Generate simulated template images using the trained machine learning model.

[0114] 4. The method according to any one of clauses 2 and 3, wherein generating the location template comprises:

[0115] identifying an area of ​​the design layout corresponding to a portion of the obtained image; and

[0116] The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent features in the plurality of features.

[0117] 5. The method according to clause 4, wherein generating the position template further comprises determining boundary coordinates of one or more repeating patterns.

[0118] 6. A method according to clause 5, wherein the boundary coordinates of one or more repeating patterns are configurable.

[0119] 7. The method of any of clauses 4-6, further comprising indexing the positions of a plurality of features in the one or more repeating patterns.

[0120] 8. The method of clause 7, further comprising storing information associated with boundary coordinates of the one or more repeating patterns and information associated with index locations of a plurality of features in the one or more repeating patterns.

[0121] 9. A method according to any one of clauses 1 to 8, wherein comparing the image of the sample to the template image comprises:

[0122] aligning the image of the sample with the template image; and

[0123] A set of locations of any one or more defects are identified in an acquired image of the sample.

[0124] 10. The method of clause 9, wherein any one or more defects indicate any of necking, bridging, edge placement error, holes, or wire breaks.

[0125] 11. The method of any of clauses 9 and 10, wherein processing the image based on the comparison further comprises binning a set of locations of any one or more defects based on the locations of one or more corresponding features on the template image.

[0126] 12. A method according to any of clauses 2 to 11, wherein the template image comprises a simulated scanning electron microscope (SEM) image of an area of ​​the positional template corresponding to the obtained image.

[0127] 13. The method according to clause 12, wherein the simulated SEM image is substantially free of distortion.

[0128] 14. A method according to any of clauses 3 to 13, wherein the reference image comprises a scanning electron microscope (SEM) image of the inspection.

[0129] 15. A system for image analysis, comprising:

[0130] A controller comprising a circuit arrangement configured to cause the system to:

[0131] obtaining an image of the sample;

[0132] identifying features captured in the image of the sample;

[0133] generating a template image according to the design layout of the identified features;

[0134] comparing the image of the sample to the template image; and

[0135] The image is processed based on the comparison.

[0136] 16. The system of clause 15, wherein generating the template image comprises:

[0137] generating a location template in the design layout, the location template representing a portion of the obtained image; and

[0138] A template image is generated based on the position template.

[0139] 17. The system of any of clauses 15 and 16, wherein generating the template image further comprises: training a machine learning model by mapping information associated with the design layout to information associated with the reference image; and

[0140] Generate simulated template images using the trained machine learning model.

[0141] 18. The system of any of clauses 16 and 17, wherein generating the location template comprises: identifying an area of ​​the design layout corresponding to a portion of the obtained image; and

[0142] The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent features in the plurality of features.

[0143] 19. The system of clause 18, wherein generating the position template further comprises determining boundary coordinates of the one or more repeating patterns.

[0144] 20. The system of clause 19, wherein the boundary coordinates of one or more repeating patterns are configurable.

[0145] 21. The system of any of clauses 18-20, wherein the controller is configured to cause the system to further perform indexing positions of a plurality of features in one or more repeating patterns.

[0146] 22. The system of clause 21, wherein the controller is configured to cause the system to further perform storing information associated with boundary coordinates of the one or more repeating patterns and information associated with index locations of the plurality of features in the one or more repeating patterns.

[0147] 23. A system according to any of clauses 15-22, wherein comparing the image of the sample to the template image comprises:

[0148] aligning the image of the sample with the template image; and

[0149] A set of locations of any one or more defects are identified in the acquired image of the sample.

[0150] 24. A system according to clause 23, wherein any one or more defects indicate any of necking, bridging, edge placement error, holes or wire breaks.

[0151] 25. The system of any of clauses 23 and 24, wherein processing the image based on the comparison further comprises binning a set of locations of any one or more defects based on the locations of one or more corresponding features on the template image.

[0152] 26. A system according to any of clauses 16-25, wherein the template image comprises a simulated scanning electron microscope (SEM) image of an area of ​​the positional template corresponding to the obtained image.

[0153] 27. The system according to clause 26, wherein the simulated SEM image is substantially free of distortion.

[0154] 28. A system according to any of clauses 17-27, wherein the reference image comprises a scanning electron microscope (SEM) image of the inspection.

[0155] 29. A non-transitory computer readable medium storing a set of instructions executable by one or more processors of a computing device to cause the computing device to perform a method for image analysis, the method comprising:

[0156] obtaining an image of the sample;

[0157] identifying features captured in the image of the sample;

[0158] generating a template image according to the design layout of the identified features;

[0159] comparing the image of the sample to the template image; and

[0160] The image is processed based on the comparison.

[0161] 30. The non-transitory computer-readable medium of clause 29, wherein generating the template image comprises:

[0162] generating a location template in the design layout, the location template representing a portion of the acquired image; and

[0163] A template image is generated based on the position template.

[0164] 31. The non-transitory computer-readable medium of any of clauses 29 and 30, wherein generating the template image further comprises:

[0165] training a machine learning model by mapping information associated with the design layout to information associated with the reference image; and

[0166] Generate simulated template images using the trained machine learning model.

[0167] 32. The non-transitory computer-readable medium of any of clauses 30 and 31, wherein generating the location template comprises:

[0168] identifying an area of ​​the design layout corresponding to a portion of the obtained image; and

[0169] The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent ones of the plurality of features.

[0170] 33. The non-transitory computer-readable medium of clause 32, wherein generating the position template further comprises determining boundary coordinates of the one or more repeating patterns.

[0171] 34. The non-transitory computer-readable medium of clause 33, wherein boundary coordinates of one or more repeating patterns are configurable.

[0172] 35. The non-transitory computer-readable medium of any of clauses 32-34, wherein the set of instructions executable by one or more processors of a computing device causes the computing device to further perform indexing positions of a plurality of features in one or more repeating patterns.

[0173] 36. A non-transitory computer-readable medium according to clause 35, wherein a set of instructions capable of being executed by one or more processors of a computing device causes the computing device to further perform storage of information associated with boundary coordinates of one or more repeating patterns and information associated with index positions of multiple features in the one or more repeating patterns.

[0174] 37. The non-transitory computer-readable medium of any of clauses 29-36, wherein comparing the image of the sample to the template image comprises:

[0175] aligning the image of the sample with the template image; and

[0176] A set of locations of any one or more defects are identified in an acquired image of the sample.

[0177] 38. The non-transitory computer-readable medium of clause 37, wherein any one or more defects indicate any of necking, bridging, edge placement error, holes, or wire breaks.

[0178] 39. The non-transitory computer-readable medium of any of clauses 37 and 38, wherein processing the image based on the comparison further comprises binning a set of locations of any one or more defects based on the locations of one or more corresponding features on the template image.

[0179] 40. The non-transitory computer-readable medium of any of clauses 30-39, wherein the template image comprises a simulated scanning electron microscope (SEM) image of an area of ​​the positional template corresponding to the obtained image.

[0180] 41. The non-transitory computer readable medium of clause 40, wherein the simulated SEM image is substantially free of distortion.

[0181] 42. The non-transitory computer-readable medium of any of clauses 31-41, wherein the reference image comprises a scanning electron microscope (SEM) image of the inspection.

[0182] 43. A method for image analysis, the method comprising:

[0183] obtaining an image of the sample;

[0184] identifying features captured in the acquired image of the sample;

[0185] mapping the obtained image to a template image generated according to the design layout of the identified features; and

[0186] The image is analyzed based on the mapping.

[0187] 44. The method of clause 43, wherein the template image is generated by:

[0188] generating a location template in the design layout, the location template representing a portion of the acquired image; and

[0189] A template image is generated based on the position template.

[0190] 45. The method of clause 44, wherein generating the location template comprises:

[0191] identifying an area of ​​the design layout corresponding to a portion of the obtained image; and

[0192] The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent features in the plurality of features.

[0193] 46. ​​The method of any of clauses 43-45, wherein analyzing the image based on the mapping comprises: aligning the image of the sample with the template image; and

[0194] A set of locations of any one or more defects are identified in the acquired image of the sample.

[0195] 47. The method of clause 46, wherein any one or more defects indicate any of necking, bridging, edge placement error, holes, or wire breaks.

[0196] 48. A method according to any of clauses 43-47, wherein mapping the acquired image to the template image comprises correlating a set of locations of any one or more defects in the acquired image with locations of one or more corresponding features on the template image.

[0197] 49. A method according to any of clauses 43-48, further comprising storing information associated with a mapping of the obtained image to the template image.

[0198] 50. The method of any of clauses 43-49, further comprising storing information associated with the analysis based on the mapping.

[0199] 51. A system for image analysis, comprising:

[0200] A controller comprising a circuit device configured to cause the system to perform the following:

[0201] obtaining an image of the sample;

[0202] identifying features captured in the acquired image of the sample;

[0203] mapping the obtained image to a template image generated from a design layout of the identified features; and

[0204] The image is analyzed based on the mapping.

[0205] 52. The system of clause 51, wherein generating the template image comprises:

[0206] generating a location template in the design layout, the location template representing a portion of the obtained image; and

[0207] A template image is generated based on the position template.

[0208] 53. The system of clause 52, wherein generating the location template comprises:

[0209] identifying an area of ​​the design layout corresponding to a portion of the obtained image; and

[0210] The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent features in the plurality of features.

[0211] 54. The system of any of clauses 51-53, wherein analyzing the image based on the mapping comprises: aligning the image of the sample with the template image; and

[0212] A set of locations of any one or more defects are identified in the acquired image of the sample.

[0213] 55. A system according to clause 54, wherein any one or more defects indicate any of necking, bridging, edge placement error, holes, or wire breaks.

[0214] 56. A system according to any of clauses 51-55, wherein mapping the acquired image to the template image comprises correlating a set of locations of any one or more defects in the acquired image with locations of one or more corresponding features on the template image.

[0215] 57. The system of any of clauses 51-56, wherein the controller is configured to cause the system to further perform storing information associated with a mapping of the acquired image to the template image.

[0216] 58. The system of any of clauses 51-57, wherein the controller is configured to cause the system to further perform storing information associated with the analysis based on the mapping.

[0217] 59. A non-transitory computer readable medium storing a set of instructions executable by one or more processors of a computing device to cause the computing device to perform a method for image analysis, the method comprising:

[0218] obtaining an image of the sample;

[0219] identifying features captured in the acquired image of the sample;

[0220] mapping the obtained image to a template image generated from a design layout of the identified features; and

[0221] The image is analyzed based on the mapping.

[0222] 60. The non-transitory computer-readable medium of clause 59, wherein generating the template image comprises:

[0223] generating a location template in the design layout, the location template representing a portion of the acquired image; and

[0224] A template image is generated based on the position template.

[0225] 61. The non-transitory computer-readable medium of clause 60, wherein generating the location template comprises:

[0226] identifying an area of ​​the design layout corresponding to a portion of the obtained image; and

[0227] The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent features in the plurality of features.

[0228] 62. The non-transitory computer-readable medium of any of clauses 59-61, wherein analyzing the image based on the mapping comprises:

[0229] aligning the image of the sample with the template image; and

[0230] A set of locations of any one or more defects are identified in the acquired image of the sample.

[0231] 63. The non-transitory computer-readable medium of clause 62, wherein any one or more defects indicate any of necking, bridging, edge placement error, holes, or wire breaks.

[0232] 64. A non-transitory computer-readable medium according to any of clauses 59-63, wherein mapping the obtained image to the template image comprises: correlating a set of locations of any one or more defects in the obtained image with the locations of one or more corresponding features on the template image.

[0233] 65. The non-transitory computer-readable medium of any of clauses 59-64, wherein a set of instructions executable by one or more processors of a computing device causes the computing device to further perform storing information associated with a mapping of the obtained image to the template image.

[0234] 66. The non-transitory computer-readable medium of any of clauses 59-65, wherein a set of instructions executable by one or more processors of a computing device causes the computing device to further perform storing information associated with the analysis based on the mapping.

[0235] It should be understood that the embodiments of the present disclosure are not limited to the exact constructions described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The present disclosure has been described in conjunction with various embodiments, and other embodiments of the present invention will be apparent to those skilled in the art by considering the specification and practice of the invention disclosed herein. The description and examples are intended to be considered as exemplary only, with the true scope and spirit of the present invention being indicated by the appended claims.

[0236] The above description is intended to be illustrative rather than limiting. It will therefore be apparent to those skilled in the art that modifications described may be made without departing from the scope of the claims set forth below.

Claims

1. A non-transitory computer-readable medium storing a set of instructions, the set of instructions being executable by one or more processors of a computing device to cause the computing device to perform a method for image analysis, the method include: obtaining an image of the sample; identifying features captured in said image of said sample; generating a template image according to the identified design layout of the features; comparing the image of the sample to the template image; as well as The image is processed based on the comparison.

2. The non-transitory computer-readable medium of claim 1, wherein the template image is generated include: generating a position template in the design layout, the position template representing a portion of the obtained image; as well as The template image is generated based on the position template.

3. The non-transitory computer-readable medium of claim 1 , wherein generating the template image further comprises: include: training a machine learning model by mapping information associated with the design layout to information associated with a reference image; as well as Generate a simulated template image using the trained machine learning model.

4. The non-transitory computer readable medium of claim 2, wherein the position template is generated include: identifying an area of ​​the design layout corresponding to the portion of the obtained image; as well as The plurality of features in the identified region are grouped into one or more repeating patterns based at least on distances between adjacent ones of the plurality of features.

5. The non-transitory computer readable medium of claim 4, wherein generating the position template further comprises: include: Boundary coordinates of the one or more repeating patterns are determined. 6 . The non-transitory computer readable medium of claim 5 , wherein the boundary coordinates of the one or more repeating patterns are configurable.

7. The non-transitory computer-readable medium of claim 3, wherein the set of instructions executable by the one or more processors of the computing device causes the computing device to further perform indexing positions of the plurality of features in the one or more repeating patterns.

8. The non-transitory computer-readable medium of claim 7, wherein the set of instructions executable by the one or more processors of the computing device causes the computing device to further perform storing information associated with the boundary coordinates of the one or more repeating patterns and information associated with index positions of the plurality of features in the one or more repeating patterns.

9. The non-transitory computer readable medium of claim 1 , wherein the image of the sample is compared to the template image. include: aligning the image of the sample with the template image; as well as A set of locations of any one or more defects are identified in the acquired image of the sample.

10. The non-transitory computer readable medium of claim 9, wherein the any one or more defects indicate any one of necking, bridging, edge placement error, holes, or wire breaks.

11. The non-transitory computer readable medium of claim 9, wherein processing the image based on the comparison further comprises: include: The set of locations of any one or more defects are binned based on the locations of one or more corresponding features on the template image.

12. The non-transitory computer-readable medium of claim 2, wherein the template image comprises a simulated scanning electron microscope (SEM) image of an area of ​​the position template corresponding to the obtained image.

13. The non-transitory computer readable medium of claim 12, wherein the simulated SEM image is substantially free of distortion.

14. The non-transitory computer-readable medium of claim 3, wherein the reference image comprises an inspected scanning electron microscope (SEM) image.

15. A system for image analysis, include: A controller comprising circuitry configured to cause the system to: obtaining an image of the sample; identifying features captured in said image of said sample; generating a template image according to the identified design layout of the features; comparing the image of the sample to the template image; as well as The image is processed based on the comparison.