Wafer defect detection is a critical part of the semiconductor wafer manufacturing industry. Human-based manual defect detection is tedious and often prone to misjudgement. Hence, there is a push towards automatic wafer defect detection in the industry. This paper shall investigate the efficacy of a transfer learning pipeline that utilizes different pre-trained VGG models, i.e., VGG16 and VGG19, that act as a feature extractor coupled with a Random Forest (RF) model in classifying wafer defect images. The hyperparameter of the RF classifier is further fine-tuned through the grid-search technique via a five-fold cross-validation method. It was shown in the study that the optimised VGG16+RF pipeline provided a better classification of the wafer defects.
The Classification of Semiconductor Wafer Defects by Means of Feature-based Transfer Learning Approach
Lect. Notes in Networks, Syst.
International Conference on Robot Intelligence Technology and Applications ; 2023 ; Taicang December 06, 2023 - December 08, 2023
29.11.2024
7 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
The Classification of Brain Tumours by Means of Feature-Based Transfer Learning
Springer Verlag | 2024
|The Classification of Kidney Disease: A Feature-Based Transfer Learning Approach
Springer Verlag | 2024
|Feature-Based Transfer Learning as a Means for Colorectal Cancer Diagnosis
Springer Verlag | 2024
|Image Feature Based Machine Learning Approach for Road Terrain Classification
British Library Conference Proceedings | 2018
|Surface Defect Detection: An Approach Utilising Feature-Based Transfer Learning
Springer Verlag | 2024
|