In the integrated circuit (IC) manufacturing process, defects directly impact the final product yield. Integrated circuit defects are characterized by a wide variety of defect types and complex circuit structures. We proposes a defect detection model based on multi-layer attention mechanisms, which enables the detection and classification of common defects in etching processes. First, we use a pre-trained backbone to extract features from different layers. Then, we perform feature encoding and fusion across these different layers. Finally, we utilize an end-to-end decoder to determine the location and type of defects. Compared to similar methods, our method shows a significant improvement in accuracy across different types of defects and requires fewer training samples. Some types of defects have already met the application requirements, and our approach incurs lower training costs when dealing with new types of defects, necessitating only fine-tuning of the model rather than retraining the entire network.
In semiconductor manufacturing, the detection of defects efficiently and accurately plays an important role in improving production quality and process optimization. However, most of the current defect inspection methods need to collect reference images on wafer. Based on the machine learning (ML) model, this paper first using the layout to generate the corresponding Scanning Electron Microscopy (SEM) image as the reference image for defect, and then by comparing the similarity of the defect image with the generated reference image to achieve accurate identification and localization of the defect. Experimental results demonstrate that the accuracy of this method for defect inspection is 98%, at the same time, the processing speed is at 100 image levels per minute. This study can not only improve the accuracy and efficiency of defect inspection, but also provide new ideas for the processing and multi-classification of defect images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.