Abstract
Facial expression recognition has been an active area of research over the past few decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem rely on hand-crafted features such as SIFT, HOG, and LBP, followed by a classifier trained on a database of images or videos. Most of these works perform reasonably well on datasets of images captured in a controlled condition but fail to perform as well on more challenging datasets with more image variation and partial faces. In recent years, several works proposed an end-to-end framework for facial expression recognition using deep learning models. Despite the better performance of these works, there are still much room for improvement. In this work, we propose a deep learning approach based on attentional convolutional network that is able to focus on important parts of the face and achieves significant improvement over previous models on multiple datasets, including FER-2013, CK+, FERG, and JAFFE. We also use a visualization technique that is able to find important facial regions to detect different emotions based on the classifier’s output. Through experimental results, we show that different emotions are sensitive to different parts of the face.
Highlights
Emotions are an inevitable part of interpersonal communication
We propose a deep learning-based framework for facial expression recognition, which takes the above observation into account and uses an attention mechanism to focus on the salient part of the face
We provide the experimental analysis of the proposed model on several popular facial expression recognition datasets, including Facial Expression Recognition 2013 (FER2013) [14], the extended
Summary
Emotions are an inevitable part of interpersonal communication. They can be expressed in many different forms, which may or may not be observed with the naked eye.with the right tools, any indications preceding or following them can be subject to detection and recognition. Emotion recognition can be performed using different features, such as facial expressions [2,9,10], speech [5,11], EEG [12], and even text [13]. Among these features, facial expressions are one of the most popular, if not the most popular, due to a number of reasons; they are visible, they contain many useful features for emotion recognition, and it is easier to collect a large dataset of faces (than other means for human recognition) [2,14,15]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have