Abstract: Disclosed is a cutting path planning algorithm for semiconductor workpiece based on image processing, belonging to the technical field of image calculation, and solving the technical problem of manually cutting off the heterocrystal region on the wafer, which includes the following steps: 1, obtaining a semantic boundary of an image; 2, finding a largest inscribed rectangle MRect in the single crystal image X1; 3. dividing the contour region in the single crystal region to find the corresponding cutting line; 4. determining the final cutting line. The cutting line planned by the application may realize automatic cutting of the wafer, and may better reserve the required single crystal region.

Abstract: Disclosed is a multi-angle image semantic segmentation method for cadmium zinc telluride chips, belonging to the field of image quality augmentation. Firstly, construction of an n+1 dataset is performed by using acquire CZT images, and then pixel-level and latent-level knowledge representation is performed through a Pixel Aggregation Network PAN and a Latent Aggregation Network LAN in a Progressive Complementary Knowledge Aggregation network PCKA, which ultimately improves the quality and speed of CZT image segmentation. The method is suitable for applications that require multi-angle image acquisition and semantic segmentation, such as semiconductor material segmentation.