Abstract
Automated Inspection has become a vital part of quality control during semiconductor wafer production. However, current automated processes take a large amount of time to set-up and also require significant computational resources in order to achieve good accuracy, with often only binary classification (Pass/Fail) facilitated. This paper presents an alternative to current industry inspection practices by using local image features and machine learning to detect and classify defects upon semiconductor wafers in order to differentiate between different types of defects.
Original language | English |
---|---|
Title of host publication | Irish Machine Vision and Image Processing Conference |
Pages | 183 - 189 |
Number of pages | 7 |
Publication status | Published (in print/issue) - 28 Aug 2019 |
Keywords
- Image Processing
- Bag of Visual Words
- Machine Learning
- Defect Classification