Fourier transform-based hierarchical clustering of layout patterns.

Fourier transform-based hierarchical clustering addresses the inefficiencies in IC inspection by allowing customizable pattern grouping, enhancing defect detection and process optimization.

JP7828365B2Active Publication Date: 2026-03-11ASML NETHERLANDS BV
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-04-28
Publication Date
2026-03-11

AI Technical Summary

Technical Problem

Existing IC inspection systems face challenges in efficiently and accurately clustering vast amounts of data from SEM images due to predefined and fixed grouping parameters, leading to time-consuming pattern analysis and inefficient defect detection.

Method used

The system employs a method of grouping IC patterns using Fourier transform-based hierarchical clustering, allowing for customizable partitioning of patterns into subsets based on similarity, enhancing inspection efficiency and accuracy by recursively evaluating features.

Benefits of technology

This approach improves the efficiency and accuracy of IC inspection by enabling flexible pattern grouping and hot spot analysis, optimizing the IC manufacturing process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007828365000001
    Figure 0007828365000001
  • Figure 0007828365000002
    Figure 0007828365000002
  • Figure 0007828365000003
    Figure 0007828365000003
Patent Text Reader

Abstract

Apparatus, systems and methods are disclosed for grouping a plurality of patterns extracted from image data. In some embodiments, the method of grouping patterns includes receiving image data including a plurality of patterns representing features formed on a portion of a wafer. The method also includes separating the plurality of patterns after a Fourier transform into a plurality of sets of patterns. The method further includes performing hierarchical clustering on each set of patterns to obtain a plurality of subsets of patterns by recursively evaluating features related to similarity between patterns within each set of patterns.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method for sorting defect on basis of picked-up image and method for displaying the result

    JP2001134763A

  • Domain-based virtual Fourier filter

    JP2013542404A

  • Multi-stage image alignment method for large offset die-to-die inspection

    JP2021500740A

  • Defect displaying method

    US20190370950A1

  • Pattern grouping method based on machine learning

    US20200020092A1