Wafer Defect Pattern Recognition Based On OPTICS And Supervised Learning

In the industry of integrated circuits,defect patterns shown on a wafer map contain crucial information for quality engineers to find the causes of defect to increase yield.For examples,the ring defect patterns may be caused in the wafer moving and the clusters with curvilinear patterns may be caused by scratches.This paper proposes a method for wafer defect pattern recognition which could recognize more than one defect patterns based on Ordering Point to Identify the Cluster Structure(OPTICS)and Support Vector Machine(SVM).Fisrt,proposed method get the cluster of wafer map based on OPTICS,then extract features of these clusters and classification by SVM.The effectiveness of the proposed method has been verified from following three aspects from a real-world data set of wafer maps(WM-811K): salient defect pattern recognition accuracy up to 94.3% and the accuracy of some types has an obvious improvement,multi-patterns recognition accuracy(89.3%),and computation time has a significantly reduction.