Introduction
The Unsupervised Segmentation algorithm can be used to judge whether the image of an object is OK, NG, or Unknown on the basis of set thresholds. Moreover, heat maps are available to show the possible areas with defects.
-
If the Defect confidence of an image is less than the threshold set for OK results, the image will be labeled as OK.
-
If the Defect confidence of an image is greater than the threshold set for NG results, the image will be labeled as NG.
-
If the Defect confidence of an image is greater than the threshold set for OK results and less than the threshold set for NG results, the image will be labeled as Unknown.
Tutorial: Training and Application of Unsupervised Segmentation Model
