Wafer image chip cutting lane automatic positioning method
By combining template matching and region growing algorithms with grayscale thresholding algorithms, the positioning problem of dicing channels for irregularly shaped wafers was solved, achieving high-precision wafer dicing and improving the dicing yield.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING UNIV OF TECH
- Filing Date
- 2022-07-26
- Publication Date
- 2026-06-12
AI Technical Summary
Existing technologies struggle to precisely position irregularly shaped and rough-edged wafer dicing tracks during the cutting process, resulting in large cutting errors and impacting the yield rate.
Coarse localization is achieved by using template matching and region growing algorithms, and fine localization is achieved by combining gray value thresholding algorithms based on the differences in gray value distribution between the inner and outer regions of the chip. Wafer dicing channels are located by using the edge lines of the inner regions of the chip.
It improves the positioning accuracy of images of irregularly shaped and rough-edged wafers, expands the scope of application, and ensures the accuracy and efficiency of the dicing process.
Smart Images

Figure 1 
Figure 2