Figures & data
Figure 2. (a) Artificial defect source image example; (b) Output device and (c) Camera sensors and mounts; (d) Acquired raw image (14,192 × 10,640).
![Figure 2. (a) Artificial defect source image example; (b) Output device and (c) Camera sensors and mounts; (d) Acquired raw image (14,192 × 10,640).](/cms/asset/71c1b2d6-63ad-41da-81bd-a5f7b065e344/tjid_a_2381464_f0002_oc.jpg)
Figure 3. Example of a defined defect classification; (a) Open (b) Line out (c) Short (d) Foreign bodies.
![Figure 3. Example of a defined defect classification; (a) Open (b) Line out (c) Short (d) Foreign bodies.](/cms/asset/39fd7df9-ae38-41cf-abc6-709af933cbae/tjid_a_2381464_f0003_oc.jpg)
Figure 4. Result of the defect detection, row 1 is the 1024 × 1024 output data and row 2 is the zoomed-in image.
![Figure 4. Result of the defect detection, row 1 is the 1024 × 1024 output data and row 2 is the zoomed-in image.](/cms/asset/e47e1b36-7d0d-4e97-9f3f-894992a7041b/tjid_a_2381464_f0004_oc.jpg)
Table 1. Detection rate by defined defect type.
Figure 5. Source data on the left, diffusion model on the right 3 images, OLED pattern information lost as the network process.
![Figure 5. Source data on the left, diffusion model on the right 3 images, OLED pattern information lost as the network process.](/cms/asset/2910508f-2680-4694-9818-194b2200970d/tjid_a_2381464_f0005_oc.jpg)
Table 2. Detecting unclassified defects in partial application models of diffusion models.