Figure 14
From: Multi-pose lipreading and audio-visual speech recognition
Lipreading performance with pose normalization in the image space. This figure shows the performance of a frontal classifier when the input corresponds to a lateral view of the speaker and the visual features have been normalized to a frontal pose in the image space. The experiments show the expected trade-off between the size-of the patch and the overlapping. N stands for the number of patches and o for the patch overlapping used in the LLR transform.