Patent · US Active

Detecting defects in semiconductor specimens using weak labeling

US11379972B2 · kind B2 · utility

1Cited by
10References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 3, 2020
Grant dateJul 5, 2022
Priority date
Expiry dateAug 5, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/30148
  • WIPO fieldMeasurement
  • WIPO sectorInstruments

Abstract

A system of classifying a pattern of interest (POI) on a semiconductor specimen, where the system includes a processor and memory circuitry configured to obtain a high-resolution image of the POI, and generate data usable for classifying the POI in accordance with a defectiveness-related classification. Generating the data utilizes a machine learning model that has been trained in accordance with training samples. The training samples include a high-resolution training image captured by scanning a respective training pattern on a specimen, the respective training pattern being similar to the POI, and a label associated with the image. The label is derivative of low-resolution inspection of the respective training pattern.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.