A hybrid deep and handcrafted feature learning approach for imbalanced wafer map defect classification
Researchers have developed a new framework for classifying defects in semiconductor wafer maps using a combination of deep learning and handcrafted features. The model addresses data imbalance issues and achieves high accuracy on the WM-811K dataset.
Why it matters
Improving defect classification in semiconductor manufacturing is critical for increasing yield and reducing waste in the global chip supply chain.
Scientific Reports ( 2026 ) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in