Abstract
In order to improve the accuracy of group emotion recognition, a group emotion recognition model based on global scene feature and local face feature is constructed in this paper. When extracting global scene features, with the consideration of that the different size of the background objects may have different influences on the emotion recognition, the paper proposes a feature extraction algorithm for the global scene based on the fusion of multi-scale feature maps. With the consideration of the emotion propagation between different figures in the image, the paper proposes a LSTM based algorithm for fusion the face features among different figures. Experiments show that the global scene feature extraction algorithm proposed in this paper has higher accuracy than the global scene feature extraction algorithm based on standard network architecture. Besides, the facial emotion feature fusion algorithm based on LSTM has higher classification accuracy than the fusion algorithm based on average calculation and the algorithm based on voting. Besides, the group emotion recognition model proposed in this paper has an accuracy 24.38% higher than the benchmark method, 13.32% higher than the deep learning method and 14.57% higher than the deep learning method.
Highlights
With millions of images being uploaded onto social media platforms, there is an increasing interest in inferring the emotion and mood display of a group of people in images [1]
Yu et al.: Group Emotion Recognition Based on Global and Local Features features of multiple figures in the image, which results in the problem that the fusion features can not effectively describe the psychological feelings of the observers, this paper proposes a facial emotional feature fusion algorithm based on deep bidirectional LSTM network
It can be seen from the figure that the global scene feature extraction algorithm based on multiscale feature maps proposed in this paper comprehensively uses different scales of features and considers the characteristics of the background objects with different sizes, which can improve the group emotion recognization compared with ‘‘FeaVec3 acc’’
Summary
With millions of images being uploaded onto social media platforms, there is an increasing interest in inferring the emotion and mood display of a group of people in images [1]. Automated group emotion recognition has great economic value in areas such as smart city planning [2], public safety [3], hospital care [4], early detection of emergencies [5], and security monitoring [6]. The automated group emotion recognition has attracted great attention from academia, there are still some shortcomings in the current works: (1) Most of the existing research works [9]–[11] takes the features on the last layer of deep neural network as the global scene features. The last layer of the deep neural network has a large receptive field, which is suitable for extracting features oflarge-scale background objects. When extracting global scene features, The associate editor coordinating the review of this manuscript and approving it for publication was Orazio Gambino
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
