Unlock instant, AI-driven research and patent intelligence for your innovation.

Defect classification method and defect detection system

A defect classification and defect type technology, applied in the field of defect classification and defect inspection system, can solve the problems of performance degradation, low accuracy, long processing time, etc.

Active Publication Date: 2017-01-04
DONGFANG JINGYUAN ELECTRON LTD
View PDF5 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the increasing number of defects and data size may cause performance degradation, such as lower accuracy or longer processing time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Defect classification method and defect detection system
  • Defect classification method and defect detection system
  • Defect classification method and defect detection system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the embodiments of the present invention, and are not intended to limit the embodiments of the present invention.

[0030] In semiconductor manufacturing, defect inspection systems are used to detect and classify wafer or reticle defects. For example, a wafer defect inspection system can inspect a wafer for defects and obtain information about the defects, such as an image ("defect image") and defect location coordinates. In defect classification, a label can be assigned to a defect after the characteristics of the defect image associated with the defect have been analyzed. By assigning the correct tags to inspected defects, predetermined actions can be quickly implemented to address defects, wafers, or reticles on the production line. Addit...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a defect classification method and a defect detection system. The defect classification method comprises the following steps: receiving a first defect record based on inspection of a target sample, wherein the first defect record include a first defect image associated with an unknown defect; and selecting first assemblies, ranked according to importance, from the first defect image by virtue of a first learning technique, and judging whether the first defect image is associated with a first known defect type by virtue of a second learning technique based on the first assemblies ranked according to importance.

Description

technical field [0001] The present disclosure generally relates to defect classification methods and defect inspection systems in wafer or reticle inspection. Background technique [0002] Wafer or reticle defect inspection systems have a defect classification function and are widely used in semiconductor manufacturing. With the development and progress of technology, the resolution becomes smaller and smaller (for example, below 20 nm), and the number of defects may increase under various system conditions, such as process changes and Optical Proximity Correction (OPC) technology. Increasing systemic flaws can lead to performance degradation. [0003] Machine learning techniques can be used for defect classification. However, the increasing number of defects and data size may cause performance degradation, such as lower accuracy or longer processing time. Contents of the invention [0004] In order to achieve the above purpose, on the one hand, an embodiment of the pre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/88G01N21/95
CPCG01N21/88G01N21/9501G01N21/8851G01N2021/8854G01N2021/95676
Inventor 马卫民张健张兆礼
Owner DONGFANG JINGYUAN ELECTRON LTD