WO2023065493A1 - Procédé et appareil de détection de défauts, et dispositif et support de stockage - Google Patents

Procédé et appareil de détection de défauts, et dispositif et support de stockage Download PDF

Info

Publication number
WO2023065493A1
WO2023065493A1 PCT/CN2021/137500 CN2021137500W WO2023065493A1 WO 2023065493 A1 WO2023065493 A1 WO 2023065493A1 CN 2021137500 W CN2021137500 W CN 2021137500W WO 2023065493 A1 WO2023065493 A1 WO 2023065493A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
image
image area
pattern
defect
Prior art date
Application number
PCT/CN2021/137500
Other languages
English (en)
Chinese (zh)
Inventor
宫凯歌
Original Assignee
长鑫存储技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 长鑫存储技术有限公司 filed Critical 长鑫存储技术有限公司
Publication of WO2023065493A1 publication Critical patent/WO2023065493A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
    • H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor

Definitions

  • the present disclosure relates to but not limited to the field of semiconductors, and in particular relates to a defect detection method, device, equipment and storage medium.
  • the scanned image of the wafer product taken by the measuring machine after the process (such as after photolithography treatment, etc.) is usually used as the measurement image, and based on the captured quantity Manually observe the test image to determine whether there are defects in the wafer product.
  • defect detection through manual observation has high labor costs, low efficiency, and is prone to missed or false detections.
  • the embodiments of the present disclosure provide a defect detection method, device, equipment and storage medium.
  • An embodiment of the present disclosure provides a defect detection method, the method comprising:
  • the defect detection result of each image area is determined by measuring the pattern in each image area.
  • the wafer product includes a dynamic random access memory
  • the at least one structural area includes at least one structural area in at least one structural layer preset in the dynamic random access memory.
  • the determining at least one image region to be measured in the edge feature map based on the design map of the structural region corresponding to the scanned image includes: calculating the edge feature map of the scanned image and the Registering the design diagram of the structural region corresponding to the scanned image to obtain at least one image region in the edge feature map that does not match the design diagram; and determining each of the mismatched image regions as to be measured image area.
  • the determining the defect detection result of each image area by measuring the pattern in each image area includes: determining the measurement index of each image area; For each image area, based on the measurement index of the image area, the pattern in the image area is measured to obtain the measurement result of the measurement index in the image area; based on each of the The measurement result of the measurement index of the image area determines the defect detection result of each said image area.
  • the determining the measurement index of each of the image areas includes: determining the pattern type of each of the image areas; for each of the image areas, based on the pattern type of the image area, A measurement index of the image area is determined.
  • the pattern type includes at least one of the following: hole type, line block type; the determination of the measurement index of the image area based on the pattern type of the image area includes: When the pattern type in the image area is the hole type, the area of the hole pattern in the image area is determined as the measurement index of the image area; the pattern type in the image area is the hole type In the case of the line block type, the spatial key dimension of the line block pattern in the image area is determined as the measurement index of the image area.
  • the hole pattern includes a hole pattern in the cell array area in at least one of the following areas: active area, bit line contact area, capacitor area; the line block pattern includes a metal wiring layer The strip pattern in at least one of the following areas: the sense amplifier area, the sub-word line driver area, and the sub-word line connection area.
  • the determining the defect detection result of each image area based on the measurement result of the measurement index of each image area includes: acquiring the measurement index of each image area Reference value area: For each image area, compare the measurement result of the measurement index of the image area with the reference value area, and determine the defect detection result of the image area.
  • the defect detection result includes a defect state; comparing the measurement result of the measurement index of the image area with a reference value area, and determining the defect detection result of the image area includes: When determining that the measurement result of the measurement index in the image area is within the reference value area, determine that the defect state of the image area is no defect; determine that the measurement result of the measurement index in the image area is not in the reference value area. In the case of the value area, it is determined that the defect state of the image area is defective.
  • the measurement index is the area of the hole pattern in the image area
  • the reference value area is a reference area range
  • the reference value area of the measurement index of each of the image areas is acquired , including: obtaining the area of each hole pattern in each of the scanned images; determining the area distribution information of each hole pattern in each of the scanned images based on the area of each hole pattern in each of the scanned images ; For each image area, based on the area distribution information of the hole pattern in the scanned image corresponding to the image area, determine the reference area range of the hole pattern in the image area.
  • the determining the reference area range of the hole pattern in the image region based on the area distribution information of the hole pattern in the scanned image corresponding to the image region includes: When the area distribution information of the hole pattern in the image obeys the normal distribution, determine the mean value of the area of the hole pattern in the scanned image; based on the mean value of the area, determine the reference area of the hole pattern in the image region scope.
  • the defect detection result further includes a defect type
  • comparing the measurement result of the measurement index of the image area with a reference value area to determine the defect detection result of the image area further includes : In the case where the measured area of the hole pattern in the image area is less than the first area threshold, it is determined that the defect type in the image area is missing holes; the measured area of the hole pattern in the image area is not less than When the first area threshold is smaller than the minimum value in the reference area range, it is determined that the defect type in the image area is hole shrinkage; the measurement area of the hole pattern in the image area is greater than the reference area If the maximum value in the range is less than twice the maximum value in the reference area range, it is determined that the defect type in the image area is hole expansion; the measurement area of the hole pattern in the image area is not less than the specified In the case of twice the maximum value in the above reference area range, it is determined that the defect type of the image area is hole bridge.
  • the measurement index is the spatial critical dimension of the line block pattern in the image region
  • the reference value area is the reference range of the spatial critical dimension
  • the reference value area of the measurement index includes: for each of the image areas, determining the spatial key dimension of the reference pattern corresponding to the line block pattern in the image area in the design drawing corresponding to the image area, and based on The spatial critical dimension determines a reference range of the spatial critical dimension of the line block pattern in the image area.
  • the defect detection result further includes a defect type
  • comparing the measurement result of the measurement index of the image area with a reference value area to determine the defect detection result of the image area further includes : In the case that the spatial critical dimension of the line-block pattern in the image region is smaller than a first size threshold, it is determined that the defect type in the image region is a line-block bridge; the spatial critical dimension of the line-block pattern in the image region is greater than In a case where the spatial critical dimension is twice the maximum value of the reference range, it is determined that the defect type in the image area is a line block break.
  • the method further includes: counting the defect types of each image region whose defect state is defective, to obtain the number of image regions corresponding to each defect type.
  • An embodiment of the present disclosure provides a defect detection device, the device comprising:
  • An acquisition module configured to acquire at least one scanned image obtained by scanning at least one structural region of the wafer product, and a design drawing of each structural region;
  • An extraction module configured to perform edge feature extraction on each of the scanned images to obtain an edge feature map of each of the scanned images
  • the first determining module is configured to determine at least one image region to be measured in the edge feature map based on the design map of the structural region corresponding to the scanned image for each of the scanned images;
  • the second determination module determines the defect detection result of each image area by measuring the pattern in each image area.
  • the first determination module is further configured to: register the edge feature map of the scanned image with the design map of the structural region corresponding to the scanned image to obtain at least An image area that does not match the design drawing; each of the image areas that do not match is determined as an image area to be measured.
  • the second determining module is further configured to: determine the measurement index of each of the image regions; for each of the image regions, based on the measurement indexes of the image region, the measuring the pattern in the area to obtain the measurement result of the measurement index in the image area; based on the measurement result of the measurement index of each of the image areas, determining the defect detection of each of the image areas result.
  • An embodiment of the present disclosure provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements some or all of the steps in the above method when executing the program.
  • An embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, part or all of the steps in the above method are implemented.
  • At least one scanned image obtained by scanning at least one structural region of the wafer product and a design drawing of each structural region are acquired; edge feature extraction is performed on each scanned image to obtain the Edge feature map; for each scanned image, based on the design map of the corresponding structural area of the scanned image, determine at least one image area to be measured in the edge feature map; by measuring the pattern in each image area, determine each Defect detection results for an image region.
  • the image area to be measured in the edge feature map can preliminarily determine the image area that may have defects.
  • the defect detection result of the image area is determined by measuring the pattern in the image area to be measured. In this way, it can be Improve the efficiency and accuracy of defect detection in wafer products, and reduce missed or false detections.
  • FIG. 1 is a schematic diagram of an implementation flow of a defect detection method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of an implementation flow of a defect detection method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of an implementation flow of a defect detection method provided by an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram of an implementation flow of a defect detection method provided by an embodiment of the present disclosure
  • FIG. 5A is a schematic diagram of the implementation flow of a defect detection method provided by an embodiment of the present disclosure
  • FIG. 5B is a schematic diagram of implementing defect detection on a hole-shaped scanned image provided by an embodiment of the present disclosure
  • FIG. 5C is a schematic diagram of the distribution of the number and area of a hole pattern provided by an embodiment of the present disclosure.
  • FIG. 5D is a schematic diagram of an implementation of defect detection on a line-block type scanned image provided by an embodiment of the present disclosure
  • FIG. 6 is a schematic diagram of the composition and structure of a defect detection device provided by an embodiment of the present disclosure.
  • FIG. 7 is a schematic diagram of a hardware entity of a computer device provided by an embodiment of the present disclosure.
  • first/second/third is only used to distinguish similar objects, and does not represent a specific order for objects. Understandably, “first/second/third” is used in Where permitted, the specific order or sequence may be interchanged such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein.
  • An embodiment of the present disclosure provides a defect detection method, which can be executed by a processor of a computer device.
  • the computer device refers to any server, notebook computer, tablet computer, desktop computer, smart TV, set-top box, mobile device (such as mobile phone, portable video player, personal digital assistant, dedicated messaging device, portable game device), etc. Appropriate equipment with data processing capabilities.
  • Fig. 1 is a schematic diagram of the implementation flow of a defect detection method provided by an embodiment of the present disclosure. As shown in Fig. 1, the method includes the following steps S101 to S104:
  • Step S101 acquiring at least one scanned image obtained by scanning at least one structural region of a wafer product, and a design drawing of each structural region.
  • the wafer product may include at least one structural layer, such as a capacitor layer, a metal wiring layer, etc.
  • each structural layer may include at least one structural area, such as a cell array area, a sense amplifier area, a sub-word line driver area, a sub-word line driver area, and a sub-layer. word line connection area, etc.
  • any suitable image acquisition device can be used to scan at least one structure area of the wafer product, which is not limited here.
  • a scanning electron microscope (Scanning Electron Microscope, SEM) machine can be used to scan at least one structural region in the wafer product to obtain at least one scanning image.
  • the scanned image of at least one structural region of the wafer product may be directly obtained from the image acquisition device, or may be scanned by the image acquisition device and stored in the database and then retrieved from the database, which is not limited here.
  • the product designer Before the actual production of each wafer product, the product designer will design the wafer product and store the design information of the designed wafer product in the Graphic Design System (GDS) of the wafer product , the design information may include a design drawing of each structural region in the wafer product, and the design drawing may include design width, length, direction, and pattern shape, etc. During implementation, the design drawing of the structure region in the wafer product can be obtained from the graphic design system.
  • GDS Graphic Design System
  • Step S102 performing edge feature extraction on each of the scanned images to obtain an edge feature map of each of the scanned images.
  • any suitable edge detection algorithm can be used, such as Canny edge detection algorithm, Sobel edge detection algorithm, etc., to extract the edge features of the pattern in the scanned image to obtain the edge feature map of the scanned image, which is not discussed in the embodiments of the present disclosure. limited.
  • the edges of patterns in different scanned images will be different, and the edge features in the edge feature map may include straight line features or curve features.
  • Step S103 for each of the scanned images, determine at least one image area to be measured in the edge feature map based on the design map of the structural area corresponding to the scanned image.
  • the design map of the structural region corresponding to the scanned image can be registered with the edge feature map of the scanned image to obtain the difference between the edge feature map and the design map. Matching at least one image area, and determining each unmatched image area as an image area to be measured.
  • At least one candidate area in the design drawing of each structural region in the wafer product can be determined in advance, and for each scanned image, based on the design drawing of the corresponding structural region of the scanned image, the design drawing can be determined at least one candidate region, and determine the image region corresponding to the at least one candidate region in the edge feature map of the scanned image as the image region to be measured.
  • Step S104 by measuring the pattern in each of the image areas, determine the defect detection result of each of the image areas.
  • the defect detection result of the image area may include, but not limited to, one or more of the defect state, defect type, etc. of the image area.
  • the defect state can be defective or non-defective
  • the defect type can include, but not limited to, one or more of missing holes, narrowed holes, enlarged holes, bridged holes, bridged wire blocks, broken wire blocks, and the like.
  • measurement may be performed in an appropriate manner according to the actual shape of the pattern in the image area, so as to determine the defect detection result of the image area, which is not limited in this embodiment of the present disclosure.
  • the area of the pattern in the image area may be measured, and the defect detection result of the image area may be determined based on the measured area result. For example, if the area result is within the preset reference area range, it can be determined that there is no defect in the image area; if the area result is outside the preset reference area range, it can be determined that there is a defect in the image area.
  • the critical dimension of the pattern in the image area may be measured, and the defect detection result of the image area may be determined based on the measured critical dimension result. For example, if the critical dimension result is within the preset critical dimension reference range, it can be determined that there is no defect in the image area; defect.
  • the critical dimension of the pattern may be determined according to actual conditions, which is not limited in the embodiments of the present disclosure.
  • the wafer product includes a dynamic random access memory (Dynamic Random Access Memory, DRAM), and the at least one structural region includes at least one structural layer preset in the dynamic random access memory At least one structure area.
  • DRAM Dynamic Random Access Memory
  • at least one structural layer may be preset by the user according to actual application scenarios, which is not limited here.
  • determining at least one image region to be measured in the edge feature map based on the design map of the structural region corresponding to the scanned image in the above step S103 may include:
  • Step S111 registering the edge feature map of the scanned image and the design map of the corresponding structural region of the scanned image to obtain at least one image area in the edge feature map that does not match the design map;
  • Step S112 determining each unmatched image area as an image area to be measured.
  • the registration may be a process of superimposing and matching the edge feature map of the scanned image and the design map of the corresponding structural region. At least one image region in the edge feature map that does not match the design map can be determined through registration, so that at least one image region to be measured can be quickly determined, thereby improving the efficiency and accuracy of defect detection in wafer products.
  • At least one scanned image obtained by scanning at least one structural region of the wafer product and a design drawing of each structural region are acquired; edge feature extraction is performed on each scanned image to obtain the Edge feature map; for each scanned image, based on the design map of the corresponding structural area of the scanned image, determine at least one image area to be measured in the edge feature map; by measuring the pattern in each image area, determine each Defect detection results for an image region.
  • the image area to be measured in the edge feature map can preliminarily determine the image area that may have defects.
  • the defect detection result of the image area is determined by measuring the pattern in the image area to be measured. In this way, it can be Improve the efficiency and accuracy of defect detection in wafer products, and reduce missed or false detections.
  • An embodiment of the present disclosure provides a defect detection method, which can be executed by a processor of a computer device. As shown in Figure 2, the method includes the following steps S201 to S206:
  • Step S201 acquiring at least one scanned image obtained by scanning at least one structural region of a wafer product, and a design drawing of each structural region.
  • Step S202 performing edge feature extraction on each of the scanned images to obtain an edge feature map of each of the scanned images.
  • Step S203 for each of the scanned images, determine at least one image area to be measured in the edge feature map based on the design map of the structural area corresponding to the scanned image.
  • the above-mentioned steps S201 to S203 respectively correspond to the above-mentioned steps S101 to S103, and the specific implementation manners of the above-mentioned steps S101 to S103 can be referred to for implementation.
  • Step S204 determining the measurement index of each of the image regions.
  • At least one measurement index can be determined for each image area, and the measurement index of the image area can be used to measure the pattern in the image area to determine whether there is a defect in the pattern in the image area.
  • an appropriate measurement index may be determined according to the shape or type of the actual pattern in the image area, which is not limited here.
  • the measurement index of each image area can be determined based on the pattern type of each image area. For example, when the pattern type in the image area is a hole-like type, the area of the hole-like pattern in the image area can be determined as the measurement index of the image area; if the pattern type in the image area is a line-block type In some cases, the spatial key dimension of the line block pattern in the image area can be determined as the measurement index of the image area.
  • Step S205 for each image area, based on the measurement index of the image area, measure the pattern in the image area, and obtain the measurement result of the measurement index in the image area.
  • the corresponding measurement index in the pattern in the image area may be measured to obtain the measurement result of the measurement index.
  • Step S206 based on the measurement results of the measurement indicators of each of the image areas, determine the defect detection results of each of the image areas.
  • the defect detection result of the image region may be determined in an appropriate manner based on the measurement result of the measurement index of the image region according to the actual situation, which is not limited in this embodiment of the present disclosure.
  • the defect state and/or defect type of each image region can be determined by comparing the measurement result of the measurement index of each image region with a preset reference result.
  • the measurement index is the area of the hole pattern
  • the preset reference result is the preset area range.
  • the measurement index is the width of the groove in the line block pattern
  • the preset reference result is a preset width range
  • the width of the groove in the line block pattern in the image area is within the preset width range
  • the pattern in the image area is measured to obtain the image
  • the measurement result of the measurement index in the area and determine the defect detection result of each image area based on the measurement result of the measurement index of each image area.
  • An embodiment of the present disclosure provides a defect detection method, which can be executed by a processor of a computer device. As shown in Figure 3, the method includes the following steps S301 to S307:
  • Step S301 acquiring at least one scanned image obtained by scanning at least one structural region of the wafer product, and a design drawing of each structural region.
  • Step S302 performing edge feature extraction on each of the scanned images to obtain an edge feature map of each of the scanned images.
  • Step S303 for each of the scanned images, based on the design map of the corresponding structural area of the scanned image, at least one image area to be measured in the edge feature map is determined.
  • the above steps S301 to S303 respectively correspond to the above steps S101 to S103, and the specific implementation manners of the above steps S101 to S103 can be referred to for implementation.
  • Step S304 determining the pattern type of each image area.
  • the pattern type of the image area is the type of the pattern included in the image area, including but not limited to one or more of the hole-like type, the line-block type, and the like.
  • any suitable image recognition algorithm may be used to identify the pattern in each image area and determine the pattern type of each image area.
  • the pattern type corresponding to at least one structure region of the wafer product can be determined in advance according to actual conditions, and the pattern type of each image region can be determined by determining the structure region corresponding to each image region.
  • Step S305 for each of the image areas, based on the pattern type of the image area, determine the measurement index of the image area.
  • applicable measurement indexes may be different, and the measurement indexes of each image region may be determined based on the pattern type of each image region. For example, when the pattern type in the image area is a hole-like type, the area of the hole-like pattern in the image area can be determined as the measurement index of the image area; if the pattern type in the image area is a line-block type In some cases, the spatial key dimension of the line block pattern in the image area can be determined as the measurement index of the image area.
  • Step S306 for each image area, based on the measurement index of the image area, measure the pattern in the image area, and obtain the measurement result of the measurement index in the image area.
  • Step S307 based on the measurement results of the measurement indicators of each of the image areas, determine the defect detection results of each of the image areas.
  • the above steps S306 to S307 correspond to the above steps S205 to S206 respectively, and the specific implementation manners of the above steps S205 to S206 can be referred to for implementation.
  • the measurement index of the image area is determined. In this way, it can support the defect detection of image areas of different pattern types, and can determine the appropriate measurement index for each image area, so that the measurement results of the measurement index can better reflect the defect situation of each image area , which can further improve the accuracy of defect detection in wafer products.
  • the pattern type includes at least one of the following: a hole type, a line block type; the determination of the measurement index of the image area based on the pattern type of the image area described in the above step S305 , including the following steps S311 to S312:
  • Step S311 if the pattern type in the image area is the hole type, determine the area of the hole pattern in the image area as the measurement index of the image area;
  • Step S312 if the pattern type in the image area is the line block type, determine the spatial key dimension of the line block pattern in the image area as the measurement index of the image area.
  • the hole-like type means that the pattern in the image area is hole-like, that is, the image area includes a hole-like pattern.
  • the line-block type refers to that the pattern in the image area is line-block, that is, the image area includes line-block patterns, such as patterns such as grooves and lines.
  • the spatial key dimension of the line block pattern may be determined according to the actual pattern shape in the line block pattern, for example, may include but not limited to the width of patterns such as grooves or lines.
  • the hole pattern includes a hole pattern in a cell array (Cell Array) area in at least one of the following areas: active area (Active Area, AA), bit line contact area (Bitline Contact, BLC ), a capacitance (Capacitance, CAP) area;
  • the line block pattern includes a strip pattern in at least one of the following areas of the metal wiring layer: sub-word-line connection area (Sub Word-line Conjunction, SWC), sense amplifier (Sense Amplify, SA) area, Sub Word-line Driver (Sub Word-line Driver, SWD) area.
  • the sub-word line connection area, the sense amplifier area, and the sub-word line driver area may be respectively the sub-word line connection area, the sense amplifier area, and the sub-word line driver area in the memory cell transistor.
  • the pattern type in the image area is a hole type
  • the area of the hole pattern in the image area is determined as the measurement index of the image area
  • the pattern type in the image area is line block
  • the spatial key dimension of the line block pattern in the image area is determined as the measurement index of the image area.
  • the area can better reflect the defect situation of the hole pattern, and the spatial critical dimension can better reflect the defect situation of the line block pattern, so based on the measurement result of the hole pattern area, it is possible to more accurately determine each
  • the defect detection results of the image area of the hole type based on the measurement results of the spatially critical dimensions of the line block pattern, can more accurately determine the defect detection result of the image area of each line block pattern, which can further improve the quality of wafer products. Accuracy of defect detection.
  • An embodiment of the present disclosure provides a defect detection method, which can be executed by a processor of a computer device. As shown in Figure 4, the method includes the following steps S401 to S407:
  • Step S401 acquiring at least one scanned image obtained by scanning at least one structural region of a wafer product, and a design drawing of each structural region.
  • Step S402 performing edge feature extraction on each of the scanned images to obtain an edge feature map of each of the scanned images.
  • Step S403 for each of the scanned images, determine at least one image area to be measured in the edge feature map based on the design map of the structural area corresponding to the scanned image.
  • Step S404 determining the measurement index of each of the image regions.
  • Step S405 for each image area, based on the measurement index of the image area, measure the pattern in the image area, and obtain the measurement result of the measurement index in the image area.
  • the above-mentioned steps S401 to S405 correspond to the above-mentioned steps S201 to S205 respectively, and the specific implementation manners of the above-mentioned steps S201 to S205 can be referred to for implementation.
  • Step S406 acquiring a reference value area of the measurement index of each image area.
  • the reference value area is a value area used to refer to the measurement result of the measurement index, and may be a continuous area, or may include multiple interval areas.
  • the reference value area can be pre-set by the user according to the specifications of the wafer product, or it can be the default, or it can be automatically determined according to the design drawing of the structural area corresponding to the image area, or it can be the current
  • the image area is obtained through statistical analysis of the measurement results of the measurement indicators of the historical image area corresponding to the same structural area, and is not limited here.
  • Step S407 for each of the image regions, comparing the measurement result of the measurement index of the image region with the reference value region, and determining the defect detection result of the image region.
  • the reference value area of the measurement index of the image area may be a normal value area of the measurement index, and may be in the case where the measurement result of the measurement index of the image area is within the reference value area, It is determined that the defect detection result of the image area is no defect, and when the measurement result of the measurement index of the image area is not in the reference value area, it is determined that the defect detection result of the image area is defective.
  • the reference value area of the measurement index of the image area may be an abnormal value area of the measurement index, and it may be determined when the measurement result of the measurement index of the image area is within the reference value area.
  • the defect detection result of the image area is defective, and if the measurement result of the measurement index of the image area is not in the reference value area, it is determined that the defect detection result of the image area is no defect.
  • the defect detection result includes a defect state; the measurement result of the measurement index of the image area described in the above step S407 is compared with the reference value area to determine the defect detection of the image area As a result, the following steps S411 to S412 are included:
  • Step S411 if it is determined that the measurement result of the measurement index in the image area is within the reference value area, determine that the defect state of the image area is no defect.
  • Step S412 if it is determined that the measurement result of the measurement index in the image area is not in the reference value area, determine that the defect state of the image area is defective.
  • the defect detection result of the image area can be quickly and accurately determined, thereby further improving the accuracy of defect detection in wafer products. accuracy and efficiency.
  • the measurement index is the area of the hole pattern in the image area
  • the reference value area is a reference area range
  • Step S421 acquiring the area of each hole pattern in each of the scanned images.
  • Step S422 based on the area of each hole pattern in each scan image, determine the area distribution information of each hole pattern in each scan image.
  • the area distribution information of the hole pattern in the scanned image may include, but not limited to, the mean, maximum, minimum, median, quantile, variance, standard deviation, etc. of the area of each hole pattern in the scanned image. One or more of them, which are not limited in the embodiments of the present disclosure.
  • Step S423 for each image area, based on the area distribution information of the hole pattern in the scanned image corresponding to the image area, determine the reference area range of the hole pattern in the image area.
  • the reference area range of the hole pattern may be a value range of the area when the hole pattern is normal. Since the area of the hole pattern in the image area of the hole type may be adjusted according to the process, the normal value is not necessarily equal to the area of the hole pattern in the design drawing of the corresponding structure area. During implementation, the reference area range of the hole pattern in the image area may be determined in an appropriate manner according to the area distribution information of the hole pattern in the scanned image, which is not limited here.
  • the mean value of the area of each hole-shaped pattern in the scanned image corresponding to the image area can be determined as the reference area range of the hole-shaped pattern in the image area;
  • the range between the 25% quantile and the 75% quantile of the area is determined as the reference area range of the hole pattern in the image area.
  • the determination of the reference area range of the hole pattern in the image region based on the area distribution information of the hole pattern in the scanned image corresponding to the image region in the above step S423 includes the following steps S431 to Step S432:
  • Step S431 if the area distribution information of the hole pattern in the scanned image corresponding to the image area follows a normal distribution, determine the mean value of the area of the hole pattern in the scanned image.
  • Step S432 based on the mean value of the area, determine a reference area range of the hole pattern in the image area.
  • the area distribution information of the hole pattern in each scanned image is determined, and for each image region, based on the hole shape in the scanned image corresponding to the image region
  • the area distribution information of the pattern determines the reference area range of the hole pattern in the image area.
  • the defect detection result also includes the defect type; the measurement result of the measurement index of the image area described in the above step S407 is compared with the reference value area to determine the defect of the image area
  • the detection result may also include the following steps S441 to S444:
  • Step S441 if the measured area of the hole pattern in the image area is smaller than a first area threshold, determine that the defect type in the image area is a missing hole.
  • the first area threshold may be pre-set by the user according to the specifications of the wafer product, or it may be a default value, or it may be automatically determined according to the design drawing of the structural area corresponding to the image area, or it may be determined according to the corresponding area of the image area.
  • the area distribution information of the hole pattern in the scanned image is determined, which is not limited here.
  • the defect type in the image region is a missing hole.
  • Step S442 if the measured area of the hole pattern in the image area is not smaller than the first area threshold and smaller than the minimum value in the reference area range, determine that the defect type of the image area is hole shrinkage.
  • the first area threshold is smaller than the minimum value in the reference area range.
  • the area of the hole in the pattern is smaller than the reference area range, so that it can be determined that the defect type in the image area is The hole shrinks.
  • Step S443 when the measured area of the hole pattern in the image area is greater than the maximum value in the reference area range and less than twice the maximum value in the reference area range, determine the defect in the image area
  • the type is hole enlargement.
  • Step S444 when the measured area of the hole pattern in the image area is not less than twice the maximum value in the reference area range, determine that the defect type in the image area is hole bridge.
  • the area of the hole in the pattern is too large, which may be caused by the bridging of two holes, so that the image can be determined
  • the defect type of the region is hole bridging.
  • the defect detection result also includes the defect type. If the measured area of the hole pattern in the image area is smaller than the first area threshold, it is determined that the defect type in the image area is missing holes; in the image area, the hole pattern When the measurement area of the pattern is not less than the first area threshold and is less than the minimum value in the reference area range, it is determined that the defect type in the image area is a hole shrinkage; the measurement area of the hole pattern in the image area is greater than that in the reference area range.
  • the defect type in the image area is hole expansion; the measurement area of the hole pattern in the image area is not less than twice the maximum value in the reference area range case, determine the defect type of the image area as hole bridging. In this way, various types of defects in the hole pattern can be identified, and further analysis of the defects and optimization of the process can be facilitated, thereby improving the progress of research and development of wafer products.
  • the measurement index is the spatial critical dimension of the line block pattern in the image area
  • the reference value area is the reference range of the spatial critical dimension
  • Step S451 for each image area, determine the spatial critical dimension of the reference pattern corresponding to the line block pattern in the image area in the design drawing corresponding to the image area, and determine based on the spatial critical dimension The reference range of the spatial key dimension of the line block pattern in the image area.
  • the space critical dimension of the line block pattern may be determined according to the actual pattern shape in the line block pattern, for example, may include but not limited to the width of patterns such as grooves or lines.
  • the reference pattern is the design pattern corresponding to the line block pattern in the design drawing corresponding to the image area.
  • the reference pattern corresponding to the line-block pattern in the image area can be determined by means of image registration or coordinate comparison, and then the spatial key dimension of the reference pattern can be determined.
  • the reference range of the spatially critical dimension of the line block pattern can be the value range of the space critical dimension when the line block pattern is normal.
  • the reference range of the spatial critical dimension of the line block pattern can be the width range of the corresponding groove in the reference pattern corresponding to the line block pattern .
  • those skilled in the art may determine the reference range of the spatial critical dimension of the line block pattern in the image region in an appropriate manner based on the actual situation, which is not limited in the embodiments of the present disclosure.
  • the spatial key dimension of the reference pattern corresponding to the line block pattern in the image area can be determined as the spatial key dimension reference range of the line block pattern in the image area;
  • the value obtained after reducing the first offset of the spatial critical dimension is used as the minimum value of the reference range of the spatial critical dimension, and the value obtained after the second offset is added to the spatial critical dimension is used as the maximum value of the reference range of the spatial critical dimension, so that The range between the minimum value and the maximum value is determined as the reference range of the spatial critical dimension.
  • the reference range of the key dimension of the corresponding line block pattern in the image area can be accurately and directly obtained, thereby further improving the defect detection accuracy of the line block pattern rate and efficiency.
  • the defect detection result also includes the defect type; the measurement result of the measurement index of the image area described in the above step S407 is compared with the reference value area to determine the defect of the image area
  • the detection result may also include the following steps S461 to S462:
  • Step S461 in the case that the spatial critical size of the line block pattern in the image area is smaller than a first size threshold, determine that the defect type in the image area is line block bridging.
  • the first size threshold may be pre-set by the user according to the specifications of the wafer product, or it may be the default, or it may be automatically determined according to the design drawing of the structural region corresponding to the image region, or it may be determined according to the image region corresponding to The distribution information of the spatial key dimensions of the line block pattern in the scanned image is determined, which is not limited here.
  • Step S462 in the case that the spatial critical dimension of the line block pattern in the image area is greater than twice the maximum value of the reference range of the spatial critical dimension, determine that the defect type in the image area is a line block break.
  • the spatial critical dimension of the line block pattern in the image area is greater than twice the maximum value of the reference range of the spatial critical dimension, the spatial critical dimension in the pattern is too large, which may be caused by the breakage of the line block, so that the image can be determined
  • the defect type of the area is line block break.
  • the defect detection result also includes the defect type. If the spatial key size of the line block pattern in the image area is smaller than the first size threshold, it is determined that the defect type in the image area is line block bridging. In the image area, the line block pattern In the case that the spatial critical dimension of the shape pattern is greater than twice the maximum value of the reference range of the spatial critical dimension, it is determined that the defect type in the image area is a line block break. In this way, various types of defects in the line-block pattern can be identified, and further analysis of the defects and process optimization can be facilitated, thereby improving the research and development progress of wafer products.
  • the above method further includes: step S471 , counting the defect types of each image area whose defect state is defective, to obtain the number of image areas corresponding to each defect type.
  • the number of image regions with the defect type can be counted, so as to obtain the number of image regions corresponding to each defect type.
  • the number of image regions corresponding to each defect type is obtained by counting the defect types of the image regions whose defect state is defective, and the number of image regions corresponding to each defect type can be quickly and accurately counted.
  • the quantity is convenient for further analysis of defects and process optimization, which in turn helps to improve the research and development progress of wafer products.
  • FIG. 5A is a schematic diagram of the implementation flow of a defect detection method provided by an embodiment of the present disclosure. As shown in Fig. 5A, the method includes the following steps S501 to S505:
  • Step S501 acquiring at least one scanned image output by the SEM machine
  • Step S502 performing edge feature extraction on at least one scanned image to obtain an edge feature map of each scanned image
  • Step S503 obtaining the design drawing of the structural region corresponding to each scanned image from the GDS;
  • Step S504 registering the edge feature map of each scanned image with the corresponding design map to obtain at least one image region that does not match the corresponding design map in each edge feature map;
  • Step S505 by measuring the area or key dimension of the pattern in each image area, determine the defect state of each image area and the defect type of the defective image area, and use the computer to automatically output the image corresponding to each defect type The number of regions.
  • the image processing algorithm is used to extract the edge features of the scanned image 511 , the edge feature map 512 of the scanned image 511 can be obtained. After the edge feature map 512 is registered with the design map 513 corresponding to the scanned image 511 in the GDS, at least one image region 514 that does not match the design map 513 can be determined.
  • the defect type 20 can include hole loss, hole shrinkage, hole Enlarging or hole bridging; the area of the hole pattern 11 in the image area 521 is 0, then it is determined that the defect type of the image area 521 is a hole missing (missing); the area of the hole pattern 12 in the image area 522 is less than the minimum of the reference area range value, then it is determined that the defect type of the image area 522 is shrinkage (shrinkage); the area of the hole pattern 13 in the image area 523 is greater than the maximum value of the reference area range, then it is determined that the defect type of the image area 523 is hole expansion (expanding) ); the area of the hole pattern 14 in the image area 524 is more than twice the maximum value in the reference area range, then it is determined that the defect type of the image area 524 is
  • the reference area range is not necessarily equal to the area of the corresponding area in the design drawing in GDS.
  • the reference area range may be determined according to the number and area distribution of the hole patterns.
  • the distribution of the number and area of hole patterns is as shown in Figure 5C, the horizontal axis X is the area of hole patterns, and the vertical axis Y is the number of hole patterns.
  • the preset range containing the mean value can be determined as the reference area range, and the reference area range can include The mean value of the area and the range of values around the mean value.
  • the defect type can be determined according to the area of the hole pattern corresponding to the X coordinate, and the Y coordinate corresponding to the area is the number of image regions of the corresponding defect type, as shown in Figure 5C, the area range
  • the defect type corresponding to A1 is missing holes, and the cumulative value of Y coordinates within this range is 128, so the number of image areas with missing holes is 128;
  • the defect type corresponding to the area range A2 is hole shrinkage, and the cumulative value of Y coordinates within this range is 434, the number of image areas with hole reduction is 434;
  • the defect type corresponding to the area range A3 is hole expansion, and the cumulative value of Y coordinates within this range is 890, then the number of image areas with hole expansion is 890;
  • the area range A4 The corresponding defect type is hole bridge, and the cumulative value of the Y coordinate in this range is 140, so the number of image regions of hole bridge is 140.
  • a scan image 531 of a line block type such as a pattern area corresponding to a structure such as a sub-word line connection area, an inductive amplifier area, and a sub-word line driver in a memory cell transistor
  • the scan image 531 is processed using an image processing algorithm.
  • Edge feature extraction can obtain the edge feature map 532 of the scanned image 531. After the edge feature map 532 is registered with the design map 533 corresponding to the scanned image 531 in the GDS, at least one image region 534 that does not match the design map 533 can be determined.
  • the defect type 40 may include Line block bridging or line block breaking; the spatial critical dimension B1 of the line block pattern 31 in the image area 541 is 0, then the defect type of the image area 541 is determined to be line block bridging; the spatial critical dimension of the line block pattern 32 in the image area 542 If B2 is more than twice the maximum value C of the reference range of the spatial critical dimension, it is determined that the defect type of the image region 542 is a line block break.
  • the reference range of the spatial critical dimension of the line block pattern can be determined based on the critical dimension of the corresponding area in the design drawing in the GDS, which can be the same as the critical dimension, or include the critical dimension and the value range around the critical dimension.
  • the defect types of the structural layer in the wafer product and the number of image regions corresponding to each defect type can be output quickly and accurately by computer equipment, which can reduce errors and omissions statistics and human subjective judgments when manually identifying defects.
  • the errors brought about can improve the accuracy and efficiency of the defect detection of the structural layer in the wafer product, and can provide a basis for the evaluation of the process such as the mask.
  • FIG. 6 is a schematic diagram of the composition and structure of a defect detection device provided by an embodiment of the present disclosure.
  • the defect detection device 600 includes: an acquisition module 610, an extraction module 620, a first determination module 630 and a second determination module 640 ,in:
  • An acquisition module 610 configured to acquire at least one scanned image obtained by scanning at least one structural region of the wafer product, and a design drawing of each structural region;
  • the extraction module 620 is configured to perform edge feature extraction on each of the scanned images to obtain an edge feature map of each of the scanned images;
  • the first determining module 630 is configured to determine at least one image region to be measured in the edge feature map based on the design map of the structural region corresponding to the scanned image for each of the scanned images;
  • the second determination module 640 determines the defect detection result of each image area by measuring the pattern in each image area.
  • the wafer product includes a dynamic random access memory
  • the at least one structural area includes at least one structural area in at least one structural layer preset in the dynamic random access memory.
  • the first determination module is further configured to: register the edge feature map of the scanned image with the design map of the structural region corresponding to the scanned image to obtain at least An image area that does not match the design drawing; each of the image areas that do not match is determined as an image area to be measured.
  • the second determining module is further configured to: determine the measurement index of each of the image regions; for each of the image regions, based on the measurement indexes of the image region, the measuring the pattern in the area to obtain the measurement result of the measurement index in the image area; based on the measurement result of the measurement index of each of the image areas, determining the defect detection of each of the image areas result.
  • the second determination module is further configured to: determine the pattern type of each of the image regions; for each of the image regions, based on the pattern type of the image region, determine the pattern type of the image region Metrics.
  • the pattern type includes at least one of the following: hole type, line block type; the second determination module is further configured: the pattern type in the image area is the hole type In the case of , the area of the hole pattern in the image area is determined as the measurement index of the image area; in the case of the pattern type in the image area being the line block type, the image The spatial key dimension of the line block pattern in the area is determined as the measurement index of the image area.
  • the hole pattern includes a hole pattern in the cell array area in at least one of the following areas: active area, bit line contact area, capacitor area; the line block pattern includes a metal wiring layer The strip pattern in at least one of the following areas: the sense amplifier area, the sub-word line driver area, and the sub-word line connection area.
  • the second determination module is further configured to: obtain a reference value area of the measurement index of each of the image regions; for each of the image regions, the measurement index of the image region The measurement result is compared with the reference value area to determine the defect detection result of the image area.
  • the defect detection result includes a defect state
  • the second determination module is further configured to: determine that the measurement result of the measurement index in the image area is within the reference value area, The defect state of the image area is non-defective; if it is determined that the measurement result of the measurement index in the image area is not in the reference value area, it is determined that the defect state of the image area is defective.
  • the measurement index is the area of the hole pattern in the image area
  • the reference value area is a reference area range
  • the second determination module is further configured to: acquire each of the scanned images The area of each hole-shaped pattern in each of the scanned images; based on the area of each hole-shaped pattern in each of the scanned images, determine the area distribution information of the hole-shaped patterns in each of the scanned images; for each of the image regions, based on The area distribution information of the hole pattern in the scanned image corresponding to the image area determines the reference area range of the hole pattern in the image area.
  • the second determining module is further configured to: determine the hole pattern in the scanned image when the area distribution information of the hole pattern in the scanned image corresponding to the image area obeys a normal distribution The mean value of the area; based on the mean value of the area, determine the reference area range of the hole pattern in the image area.
  • the defect detection result further includes a defect type; the second determining module is further configured to: determine that the measured area of the hole pattern in the image area is smaller than a first area threshold The defect type of the image area is missing holes; when the measured area of the hole pattern in the image area is not less than the first area threshold and is less than the minimum value in the reference area range, determine the image area The type of defect is hole reduction; in the case where the measured area of the hole pattern in the image area is greater than the maximum value in the reference area range and less than twice the maximum value in the reference area range, it is determined that the The defect type of the image area is hole enlargement; when the measured area of the hole pattern in the image area is not less than twice the maximum value in the reference area range, it is determined that the defect type of the image area is hole bridging .
  • the measurement index is the spatial critical dimension of the line block pattern in the image area
  • the reference value area is the reference range of the spatial critical dimension
  • the second determining module is further configured to: For each image area, determine the key spatial dimension of the reference pattern corresponding to the line block pattern in the image area in the design drawing corresponding to the image area, and determine the image area based on the spatial key dimension Spatially critical dimension reference ranges for midline block patterns.
  • the defect detection result further includes a defect type; the second determining module is further configured to: if the spatially critical size of the line block pattern in the image area is smaller than a first size threshold, determine the The defect type of the image area is line block bridging; in the case where the spatial critical dimension of the line block pattern in the image area is greater than twice the maximum value of the spatial critical dimension reference range, determine the defect type of the image area For line block breaks.
  • the device further includes: a statistical module configured to count defect types of each image region whose defect state is defective, to obtain the number of image regions corresponding to each defect type.
  • the above-mentioned defect detection method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
  • the essence of the technical solution of the embodiments of the present disclosure or the part that contributes to the related technology can be embodied in the form of a software product, the software product is stored in a storage medium, and includes several instructions to make a A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure.
  • the aforementioned storage medium includes: various media that can store program codes such as U disk, mobile hard disk, read-only memory (Read Only Memory, ROM), magnetic disk or optical disk.
  • embodiments of the present disclosure are not limited to any specific combination of hardware and software.
  • an embodiment of the present disclosure provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the steps in the above method when executing the program.
  • an embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented.
  • an embodiment of the present disclosure provides a computer program product
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, the above method can be implemented. some or all of the steps.
  • the computer program product can be specifically realized by means of hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) etc. wait.
  • FIG. 7 is a schematic diagram of a hardware entity of a computer device in an embodiment of the present disclosure.
  • the hardware entity of the computer device 700 includes: a processor 701, a communication interface 702, and a memory 703, wherein:
  • Processor 701 generally controls the overall operation of computer device 700 .
  • the communication interface 702 enables the computer device to communicate with other terminals or servers through the network.
  • the memory 703 is configured to store instructions and applications executable by the processor 701, and can also cache data to be processed or processed by each module in the processor 701 and the computer device 700 (for example, image data, audio data, voice communication data and video data) Communication data), which can be realized by flash memory (FLASH) or random access memory (Random Access Memory, RAM).
  • the disclosed devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division.
  • the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms of.
  • the units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may be used as a single unit, or two or more units may be integrated into one unit; the above-mentioned integration
  • the unit can be realized in the form of hardware or in the form of hardware plus software functional unit.
  • the above-mentioned integrated units of the present disclosure are realized in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.
  • the computer software products are stored in a storage medium, and include several instructions to make a
  • a computer device which may be a personal computer, a server, or a network device, etc.
  • the aforementioned storage medium includes various media capable of storing program codes such as removable storage devices, ROMs, magnetic disks or optical disks.
  • At least one scanned image obtained by scanning at least one structural region of the wafer product and a design drawing of each structural region are acquired; edge feature extraction is performed on each scanned image to obtain the Edge feature map; for each scanned image, based on the design map of the corresponding structural area of the scanned image, determine at least one image area to be measured in the edge feature map; by measuring the pattern in each image area, determine each Defect detection results for an image region.
  • the image area to be measured in the edge feature map can preliminarily determine the image area that may have defects.
  • the defect detection result of the image area is determined by measuring the pattern in the image area to be measured. In this way, it can be Improve the efficiency and accuracy of defect detection in wafer products, and reduce missed or false detections.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Manufacturing & Machinery (AREA)
  • Computer Hardware Design (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Power Engineering (AREA)
  • Testing Or Measuring Of Semiconductors Or The Like (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

Procédé et appareil de détection de défauts, et dispositif et support de stockage. Le procédé consiste : à acquérir au moins une image de balayage, cette dernière étant obtenue à l'aide du balayage d'au moins une zone structurale d'un produit de tranche, et un dessin de conception de chaque zone structurale (S101); à effectuer une extraction de caractéristiques de bord sur chaque image de balayage, afin d'obtenir une carte de caractéristiques de bord de chaque image de balayage (S102); en ce qui concerne chaque image de balayage, en fonction d'un dessin de conception d'une zone structurale correspondant à chaque image de balayage, à déterminer, dans la carte de caractéristiques de bord, au moins une zone d'image à mesurer (S103); et au moyen de modèles de mesure dans chaque zone d'image, à déterminer un résultat de détection de défauts de chaque zone d'image (S104).
PCT/CN2021/137500 2021-10-18 2021-12-13 Procédé et appareil de détection de défauts, et dispositif et support de stockage WO2023065493A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111211163.0 2021-10-18
CN202111211163.0A CN115994882A (zh) 2021-10-18 2021-10-18 缺陷检测方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023065493A1 true WO2023065493A1 (fr) 2023-04-27

Family

ID=85990626

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137500 WO2023065493A1 (fr) 2021-10-18 2021-12-13 Procédé et appareil de détection de défauts, et dispositif et support de stockage

Country Status (2)

Country Link
CN (1) CN115994882A (fr)
WO (1) WO2023065493A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103295930A (zh) * 2013-06-04 2013-09-11 上海华力微电子有限公司 一种快速高效的晶背缺陷识别方法
CN104425302A (zh) * 2013-09-04 2015-03-18 中芯国际集成电路制造(上海)有限公司 半导体器件的缺陷检测方法和装置
US20150078627A1 (en) * 2013-09-17 2015-03-19 Ricoh Company, Ltd. Image inspection result determination apparatus, image inspection system, method of determinating image inspection result, and storage medium
CN109615606A (zh) * 2018-11-09 2019-04-12 华南理工大学 一种柔性ic基板点线面缺陷的快速分类方法
CN109946304A (zh) * 2019-03-11 2019-06-28 中国科学院上海技术物理研究所 基于特征匹配的零件表面缺陷在线检测系统及检测方法
CN112862770A (zh) * 2021-01-29 2021-05-28 珠海迪沃航空工程有限公司 一种基于人工智能的缺陷分析诊断系统、方法、装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103295930A (zh) * 2013-06-04 2013-09-11 上海华力微电子有限公司 一种快速高效的晶背缺陷识别方法
CN104425302A (zh) * 2013-09-04 2015-03-18 中芯国际集成电路制造(上海)有限公司 半导体器件的缺陷检测方法和装置
US20150078627A1 (en) * 2013-09-17 2015-03-19 Ricoh Company, Ltd. Image inspection result determination apparatus, image inspection system, method of determinating image inspection result, and storage medium
CN109615606A (zh) * 2018-11-09 2019-04-12 华南理工大学 一种柔性ic基板点线面缺陷的快速分类方法
CN109946304A (zh) * 2019-03-11 2019-06-28 中国科学院上海技术物理研究所 基于特征匹配的零件表面缺陷在线检测系统及检测方法
CN112862770A (zh) * 2021-01-29 2021-05-28 珠海迪沃航空工程有限公司 一种基于人工智能的缺陷分析诊断系统、方法、装置

Also Published As

Publication number Publication date
CN115994882A (zh) 2023-04-21

Similar Documents

Publication Publication Date Title
WO2023279558A1 (fr) Procédé et appareil de détection de défaut, dispositif ,et support de stockage
WO2021082923A1 (fr) Procédé et dispositif de détection de défaut de zone d'écran de dispositif électronique
TWI226591B (en) Automatic defect classification with invariant core classes
TWI588475B (zh) 使用模板影像匹配在一晶圓上偵測缺陷
CN115147414B (zh) 一种双极型功率晶体管表面击穿缺陷检测方法
CN101295659A (zh) 半导体器件的缺陷检测方法
CN101127119B (zh) 图案检查装置以及半导体检查系统
US8224590B2 (en) Apparatus and method of inspecting mask
CN111652230B (zh) 车牌识别方法、电子设备及存储介质
WO2021082922A1 (fr) Procédé et dispositif de détection d'une déconnexion d'affichage d'écran
CN106815830B (zh) 图像的缺陷检测方法
CN117011304B (zh) 缺陷检测方法、装置、计算机设备及计算机可读存储介质
WO2023065493A1 (fr) Procédé et appareil de détection de défauts, et dispositif et support de stockage
TWI738026B (zh) 從多個臉部中選擇目標臉部及臉部識別比對方法、裝置
CN115375629A (zh) 一种lcd屏幕中线缺陷检测及缺陷信息提取方法
US20150098643A1 (en) Device for measuring critical dimension of pattern and method thereof
CN111768345B (zh) 身份证背面图像的校正方法、装置、设备及存储介质
CN111768346B (zh) 身份证背面图像的校正方法、装置、设备及存储介质
CN115375679B (zh) 一种缺陷芯片寻边寻点定位方法及装置
CN112908874A (zh) 半导体结构的量测方法及量测装置
WO2022193521A1 (fr) Procédé et appareil de caractérisation de défaut
CN116228861A (zh) 探针台标记物定位方法、装置、电子设备及存储介质
CN115523861A (zh) 阻尼器检测方法、装置及设备
CN115223882A (zh) 晶圆测试映射图错位的确定方法、装置、设备及存储介质
CN113643245A (zh) 一种屏幕缺陷的测量方法、装置及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21961231

Country of ref document: EP

Kind code of ref document: A1