Abstract—Defects on the wafer surface usually reflect the abnormal problems in the semiconductor manufacturing process. By detecting and identifying the wafer surface defect mode, it can diagnose fault source in time and adjust online. In this paper, an online detection and adaptive recognition model for wafer surface defect mode is presented. Firstly, the model is used to extract the feature of the wafer surface defect mode. The Hidden Markov Model (HMM) is constructed for each wafer mode based on the feature set, and an on-line detection and recognition method based on HMM dynamic integration is proposed. The proposed model is successfully applied to the wafer defect detection and recognition in WM-811K database. The experimental results fully demonstrate the validity and practicability of the model.
Index Terms—wafer, defect, automatic detection, mode recognition
Cite: Yefan Zhou, "Research on Image-Based Automatic Wafer Surface Defect Detection Algorithm," Journal of Image and Graphics, Vol. 7, No. 1, pp. 26-31, March 2019. doi: 10.18178/joig.7.1.26-31
Copyright © 2012-2020 Journal of Image and Graphics, All Rights Reserved