Skip to main content
. 2022 Apr 12;13:847267. doi: 10.3389/fphys.2022.847267

FIGURE 3.

FIGURE 3

Framework of the proposed method. It includes a pre-trained CNN module; an SRP module for generating tooth mark candidate regions; an SPP-layer for obtaining and normalizing the deep features of tooth mark candidate regions; two weakly supervised branches, a classification module and a detection module; The hadamard operation of the branch results and summation yields the image-level classification results.