Using Deep Learning ADC For Defect Classification For Automatic Defect Inspection

In traditional semiconductor packaging, manual defect review after automated optical inspection (AOI) is an arduous task for operators and engineers, involving review of both good and bad die. It is hard to avoid human errors when reviewing millions of defect images every day, and as a result, underkill or overkill of die can occur. Automatic defect classification (ADC) can reduce the number of... » read more

More Accurate And Detailed Analysis of Semiconductor Defects In SEM Images Using SEMI-PointRend

A technical paper titled "SEMI-PointRend: Improved Semiconductor Wafer Defect Classification and Segmentation as Rendering" was published (preprint) by researchers at imec, University of Ulsan, and KU Leuven. Abstract: "In this study, we applied the PointRend (Point-based Rendering) method to semiconductor defect segmentation. PointRend is an iterative segmentation algorithm inspired by ima... » read more

How Do Machines Learn?

We depend, or hope to depend, on machines, especially computers, to do many things, from organizing our photos to parking our cars. Machines are becoming less and less "mechanical" and more and more "intelligent." Machine learning has become a familiar phrase to many people in advanced manufacturing. The next natural question people may ask is: How do machines learn? Recognizing diverse obje... » read more

Demystifying ADC

ADC stands for automatic defect classification. It’s a software that classifies defects based on image and metadata such as location, ROI, and other information associated with a defect. ADC is not a mysterious black box that’s impossible to understand. Instead, ADC classifies defects the same way a human operator does, by first being trained by an expert. Then, just like human classificati... » read more