Facial Expression Recognition Using ALGBP-TOP
Nakisa Abounasr, Hossein Pourghassem · International journal of imaging and robotics · 2013
Human-computer interaction (HCI) is the most application of automatic facial expression recognition. In this paper, a dynamic texture-based approach is considered to recognize the facial expressions. The local binary patterns in three orthogonal planes (LBP-TOP) are represented to combine motion and appearance of texture. Our proposed algorithm based on the average Gabor filters and LBP-TOP (that is called ALGBP-TOP) features is recognized facial expressions. We evaluate our proposed algorithm on the Cohn-Kanade facial expression database that obtains an acceptable recognition accuracy of 94.42% by using the ALGBP-TOP features.