Abstract
Emotion plays an important role in communication. For human–computer interaction, facial expression recognition has become an indispensable part. Recently, deep neural networks (DNNs) are widely used in this field and they overcome the limitations of conventional approaches. However, application of DNNs is very limited due to excessive hardware specifications requirement. Considering low hardware specifications used in real-life conditions, to gain better results without DNNs, in this paper, we propose an algorithm with the combination of the oriented FAST and rotated BRIEF (ORB) features and Local Binary Patterns (LBP) features extracted from facial expression. First of all, every image is passed through face detection algorithm to extract more effective features. Second, in order to increase computational speed, the ORB and LBP features are extracted from the face region; specifically, region division is innovatively employed in the traditional ORB to avoid the concentration of the features. The features are invariant to scale and grayscale as well as rotation changes. Finally, the combined features are classified by Support Vector Machine (SVM). The proposed method is evaluated on several challenging databases such as Cohn-Kanade database (CK+), Japanese Female Facial Expressions database (JAFFE), and MMI database; experimental results of seven emotion state (neutral, joy, sadness, surprise, anger, fear, and disgust) show that the proposed framework is effective and accurate.
Highlights
Emotion recognition plays an important role in communication and is still a challenging research field
We describe related works of facial expression recognition systems that have been studied to date. ese algorithms can largely be divided into three directions: the geometric feature extraction method, the appearance feature extraction method, and the deep learning-based method. e geometric feature extraction method extracts geometric elements of the facial structure and motion of the facial muscles, the appearance feature extraction method extracts the features of the entire facial criterion, and the deep learning-based method uses convolutional neural network (CNN) to achieve the automatic learning of the extracted facial features
Considering low hardware specifications used in real-life condition, to gain better results without deep neural networks (DNNs), in this paper, we proposed an algorithm with the combination of the improved oriented FAST and rotated BRIEF (ORB) features and Local Binary Patterns (LBP) features extracted from facial expression
Summary
Emotion recognition plays an important role in communication and is still a challenging research field. With the development of technology, it has become convenient for us to solve problems with automatic systems, such as recognizing a person’s emotion from a facial image. For facial expression recognition system, faces are detected and recorded as 2D images by using various devices, such as electromyographs (EMGs), electrocardiographs (ECGs), electroencephalographs (EEG), and cameras. E third approach is DNN-based methods, which perform very well in facial expression recognition. Considering low hardware specifications used in some real-life conditions, to gain better results without DNNs, we aim to recognize seven basic emotional states (neutral, happy, surprise, sadness, fear, anger, and disgust) based on facial expressions using the second (feature based) approach. Different textures are generated by the actions of the related muscles on the face For this reason, we chose LBP in our study for facial expression recognition.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call