Abstract
In this paper, we focus on a defect analysis task that requires engineers to identify the causes of yield reduction from defect classification results. We organize the analysis work into three phases: defect classification, defect trend monitoring and detailed classification. To support the first and third engineer’s analytical work, we use a convolutional neural network based on the transfer learning method for automatic defect classification. We evaluated our proposed methods on real semiconductor fabrication data sets by performing a defect classification task using a scanning electron microscope image and thoroughly examining its performance. We concluded that the proposed method can classify defect images with high accuracy while lowering labor costs equivalent to one-third the labor required for manual inspection work.
Highlights
D EFECT inspection and detect trend monitoring, which provide useful information for engineers endeavoring to identify root causes of process failures, are crucially important for yield quality control
To overcome inconsistent manual classification and other costly problems, we present a convolutional neural network(CNN)-based transfer learning method of automatic defect classification [11]
We focus on a defect analysis task that requires engineers to identify the causes of yield reduction from defect classification results
Summary
D EFECT inspection and detect trend monitoring, which provide useful information for engineers endeavoring to identify root causes of process failures, are crucially important for yield quality control. Recent advances in deep learning technology have achieved human-level classification performance [8], and provided advanced analytical tools for analyzing big data from manufacturing [9]. Deep learning-based techniques typically require ground-truth labels for a large training data set. The data-labeling process is expensive, making it difficult to obtain strong supervision information [10]. To overcome inconsistent manual classification and other costly problems, we present a convolutional neural network(CNN)-based transfer learning method of automatic defect classification [11]. We evaluated our proposed methods on real semiconductor fabrication data sets using an SEM-image classification task.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
