Intelligent identification and classification method and system for wafer defect map

Abstract

The application discloses a wafer defect map intelligent recognition and classification method and system, relates to the technical field of semiconductor integrated circuit manufacturing and detection, and comprises the following steps: acquiring a detection point set, an original image and standard reference attribute data; constructing a space weight matrix based on the reference data; calculating a generalized connection cost based on a path weighted cumulative value, constructing an initial graph model and performing probability sparsification; determining a verification point based on the weight matrix and extracting local gradient features of the original image; correcting connection probability by using a Bayesian inference model and updating a graph topology structure; and finally outputting a classification result according to connected subgraph features; and the application combines layout physical attributes and image microfeatures, realizes accurate reconstruction and classification of defect forms in a complex background.

Images