Presents and compares U-Net and DenseU-Net models for fully automatic tongue-contour segmentation in ultrasound images, reporting comparable accuracy with differences in speed and cross-dataset generalization.
We used the Adam optimizer [25] with a learning rate of 0.0001, and the model was trained for 30 epochs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
A CNN-based tool for automatic tongue contour tracking in ultrasound images
Presents and compares U-Net and DenseU-Net models for fully automatic tongue-contour segmentation in ultrasound images, reporting comparable accuracy with differences in speed and cross-dataset generalization.