Modified deep belief network based human emotion recognition with multiscale features from video sequences

Abstract

Emotion recognition from human faces are recently considered as growing topic for the applications in HCI (human-computer interaction) field. Therefore, a new framework is introduced in this method for emotion recognition from video. Human faces may carry huge features which increase the complexity of recognizing the emotions from the give video. Therefore, to minimize such defect, the wrapper based feature selection technique is introduced which reduce the complexity of proposed recognition framework. Initially, the frames from the input video is preprocessed. Next, the features exhibited by each emotions are extracted with geometric and local binary pattern-based feature extraction methods. Then, the features that reduce the performance of recognition technique is avoided using a feature selection algorithm. It selects the features that provides effective result on recognition process. Finally, the selected features are provided to deep belief network (DBN) for emotion recognition. The weight parameter selection of DBN is improved using an efficient Harris Hawk optimization algorithm. The performance of presented architecture is evaluated using a three different datasets they are FAMED, CK+, and MMI. The overall rate shown by proposed architecture is found better than existing methods. Furthermore, the precision, recall, and specificity are also evaluated for six different emotions (angry, disgust, fear, happy, sad, and surprise) in this proposed method. This entire emotion recognition process is implemented in Python platform.

Wireless Sensing Technology Combined with Facial Expression to Realize Multimodal Emotion Recognition

“…Mustaqeem and Soon-il Kwonwei [ 33 ] proposed a one-dimensional dilated convolutional neural network (DCNN) to solve the problem of lack of real-time processing in speech emotion recognition. Velagapudi Sreenivas et al [ 34 ] used not only wrapper-based feature selection techniques to reduce the complexity of the recognition framework but also optimized the weight parameters of the DBN network by the Harris Hawk optimization algorithm and demonstrated that the proposed method outperformed not only existing methods on three datasets but also outperformed existing methods on six emotional states. The proposed method not only proves to be superior to existing methods on three datasets but also has high recognition accuracy in the recognition of six emotional states.…”

Pet dog facial expression recognition based on convolutional neural network and improved whale optimization algorithm

“…Expression recognition is the main way for computers to understand expression information, and its research can be traced back to the 1970s, at that time, two American scholars Ekman and Friesen took the lead in studying the relationship between muscle movement and facial expression, and proposed a facial expression coding system. The emergence of deep learning has realized the extraction of image features in the way of autonomous learning, and has also provided a new research method for expression recognition 1 , 2 . Expression recognition technology is widely used, including fatigue driving detection 3 , safety monitor 4 , teaching monitoring 5 , pain identification 6 , etc.…”