Skip to main content
. 2019 Mar 7;9:3840. doi: 10.1038/s41598-019-40414-y

Figure 3.

Figure 3

Examples of annotations processing after each stage: (Stage 1) annotated by the trained faster R-CNN, there were certain overlapping boxes (a); (Stage 2) after deleting the overlap boxes with lower scores, certain labels of teeth number were incorrect because the neural network confused them with other similar teeth; (Stage 3) the teeth number labels were matched with template for correction, but errors were induced when there were missing teeth (in films 1 and 3), however, the gap between adjacent teeth boxes (stage 2). (b) could be treated as a feature to predict the missing teeth; (Stage 4) after inserting the predicted missing teeth and matching with template from (Stage 2), the labels of teeth number were corrected.