Wang, S. et al. A natural visible and infrared facial expression database for expression recognition and emotion inference.
Face and Facial Expression Recognition and Audience Measurement, pp. 113-126.
However, the above are applied on domains such as facial expression recognition and action recognition [33].
We adopted the LBP-based spatiotemporal representation because of its recent convincing performance in modelling moving faces and facial expression recognition and also for dynamic texture recognition [20].
However, the main dichotomy these models emphasize is that between expression recognition and individuation.
In facial expression recognition, there are neutral-, hanger-,anger-, and surprise-expression recognition, and some expression recognition results are shown in Figure 2; In object recognition, the proposed method is designed for classifying faces, cars, and sheep.
Our research focuses on the question of classifiers that are capable of processing images rapidly and accurately without having to rely on a large-scale dataset, thus presenting a robust classification framework for both facial expression recognition (FER) and object recognition.
A 10-fold cross validation scheme is employed in 7-class facial expression recognition experiments, and the average recognition results are reported.
Moreover, versatility is one of its outstanding traits because, in our experiments, it could succeed in both object recognition and facial expression recognition applications.
To the best of our knowledge, our approach is the first to apply the proposed method to both object recognition and facial expression recognition.
