AUTHOR=Chen Yu , Zhao Meng , Xu Zhenyu , Li Kaiyue , Ji Jing 

TITLE=Wafer defect recognition method based on multi-scale feature fusion

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1202985

DOI=10.3389/fnins.2023.1202985

ISSN=1662-453X

ABSTRACT=Wafer defect recognition is an important process of chip manufacturing. Different process flow will lead to different defect types. Therefore, by identifying defect patterns correctly, manufacturing problems can be recognized and fixed in time. To achieve high precision identification of wafer defects and improve the quality and production yield of wafers, this paper proposes a Multi-Feature Fusion Perceptual Network (MFFP-Net) that is inspired by human visual perception mechanism. The MFFP-Net can process information at various scales and then aggregate it so that the next stage can abstract features from the different scales simultaneously. The proposed feature fusion module can obtain higher fine-grained and richer features to capture key texture details and avoid important information loss. The final experiments show that MFFP-Net achieves good generalize ability and state-of-the-art results on real-world dataset WM-811K, with the accuracy of 96.71%, this provides an effective way for the chip manufacturing industry to improve the yield the rate.