A Fast Postprocessing Algorithm for the Overlapping Problem in Wafer Map Detection

Figure 1

Hybrid wafer map defects detected by Mask R-CNN with the traditional greedy NMS as the postprocessing method. Each map includes two objects, one for “Loc” and one for “Scratch” (these two categories belong to six basic wafer maps, as defined in [28]). When the image passes through the detector network, a category score is obtained, and postprocessing is performed based on the score. (a) “Loc” score 0.96 and (b) “Loc” score 0.99.

(a)

(b)