A Real-Time Operator-Centric Patch Extraction and Analysis Platform for Industrial Semiconductor Wafer C&C Processes

초록

In semiconductor manufacturing, accurate detection of anomalies in high-speed rotating wafers is crucial for ensuring product quality and yield. Conventional methods for region of interest (ROI) selection in defect detection often rely on manual operator input, which is time-consuming and prone to inconsistency. This study presents a web-based patch extraction system capable of real-time ROI identification and monitoring with reduced manual selection. The proposed system integrates a high-speed vision module with HSV-based color space segmentation to automatically extract wafer surface patches while supporting operator-centric interaction through an intuitive web interface. Additionally, a Vision Transformer (ViT)-based backend was implemented and evaluated to assess its anomaly detection performance on the extracted patches. Experimental results demonstrate that the proposed method improves detection accuracy and processing speed compared to manual ROI selection, enabling efficient and consistent monitoring in wafer inspection processes. The system's modular architecture also facilitates future integration with advanced deep learning models and deployment in diverse manufacturing environments.

키워드