Especially, a high-dimensional feature composed by the combination of the facial geometric and appearance features is introduced to the facial expression recognition due to its containing the accurate and comprehensive information of emotions.
In this paper, we have confirmed, via extensive testing on the CK+ and JAFFE datasets, that gradient local ternary pattern (GLTP) [19] is an accurate and efficient feature extraction technique well suited for the task of facial expression recognition (FER).
A 3D virtual face model is used to obtain accurate estimation of the head rotation angle such that the non-rigid motion components can be precisely separated to enhance the facial expression recognition performance.
(That was demonstrated by him growling at the screen – facial expression recognition).
Table 2 Comparison of facial expression recognition using JAFFE database.
Fig. 1 Examples of facial expression recognition results.
At first, our method was proposed for facial expression recognition.
Psychologists often use single images for expression recognition.
We also evaluate the performance of DTCTH in expression recognition.
Various techniques have been developed for automatic facial expression recognition.
