Table 2 RMSE values for original CLNF model and for Modified CLNF (expressed in pixels and in cm)
From: Inner lips feature extraction based on CLNF with hybrid dynamic template for Cued Speech
RMSE | Speaker 1 | Speaker 2 | Speaker 3 | Total |
|---|---|---|---|---|
CLNF | 3.84 (0.20 cm) | 4.02 (0.21 cm) | 3.53 (0.18 cm) | 3.81 (0.20 cm) |
Modified CLNF | 1.06 (0.06 cm) | 0.90 (0.05 cm) | 0.94 (0.05 cm) | 0.99 (0.05 cm) |