Publication Type : Conference Proceedings
Publisher : Advances in Signal Processing and Intelligent Recognition Systems
Source : Advances in Signal Processing and Intelligent Recognition Systems, Springer, p.63–73 (2016)
Url : http://www.scopus.com/inward/record.url?eid=2-s2.0-84954494528&partnerID=40&md5=7e79b0b57b230d662a9a948823f4aa2f
ISBN : 9783319286563
Keywords : 3D images, BU3DFE database, classification, emotion, Euclidean distance, neural network
Campus : Bengaluru
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science, Visual Media and Communication
Year : 2016
Abstract : Over the last decade emotion recognition has gained prominence for its applications in the field of Human Robot Interaction (HRI), intelligent vehicle, patient health monitoring, etc. The challenges in emotion recognition from nonfrontal images, motivates researchers to explore further. In this paper, we have proposed a method based on geometric features, considering 4 yaw angles (0°, +15°, +30°, +45°) from BU-3DFE database. The novelty in our proposed work lies in identifying the most appropriate set of feature points and formation of feature vector using two different approaches. Neural network is used for classification. Among the 6 basic emotions four emotions i.e., anger, happy, sad and surprise are considered. The results are encouraging. The proposed method may be implemented for combination of pitch and yaw angles in future. © Springer International Publishing Switzerland 2016.
Cite this Research Publication : D. KrishnaSri, Dr. Suja P., and Tripathi, S., “Emotion Recognition from 3D Images with Non-Frontal View Using Geometric Approach”, Advances in Signal Processing and Intelligent Recognition Systems. Springer, pp. 63–73, 2016.