A multi-scale and rotation-invariant phase pattern (MRIPP) and a stack of restricted Boltzmann machine (RBM) with prepro
- PDF / 1,682,687 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 32 Downloads / 174 Views
ORIGINAL RESEARCH
A multi‑scale and rotation‑invariant phase pattern (MRIPP) and a stack of restricted Boltzmann machine (RBM) with preprocessing for facial expression classification A. Sherly Alphonse1 · K. Shankar2 · M. J. Jeyasheela Rakkini3 · S. Ananthakrishnan3 · Suganya Athisayamani3 · A. Robert Singh4 · R. Gobi5 Received: 17 June 2020 / Accepted: 4 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In facial expression recognition applications, the classification accuracy decreases because of the blur, illumination and localization problems in images. Therefore, a robust emotion recognition technique is needed. In this work, a Multi-scale and Rotation-Invariant Phase Pattern (MRIPP) is proposed. The MRIPP extracts the features from facial images, and the extracted patterns are blur-insensitive, rotation-invariant and robust. The performance of classification algorithms like Fisher faces, Support Vector Machine (SVM), Extreme Learning Machine (ELM), Convolutional Neural Network (CNN) and Deep Neural Network (DNN) are analyzed. In order to reduce the time for classification, an OPTICS-based pre-processing of the features is proposed that creates a non-redundant and compressed training set to classify the test set. Ten-fold cross validation is used in experimental analysis and the performance metric classification accuracy is used. The proposed approach has been evaluated with six datasets Japanese Female Facial Expression (JAFFE), Cohn Kanade (CK +), Multi- media Understanding Group (MUG), Static Facial Expressions in the Wild (SFEW), Oulu-Chinese Academy of Science, Institute of Automation (Oulu-CASIA) and Man–Machine Interaction (MMI) datasets to meet a classification accuracy of 98.2%, 97.5%, 95.6%, 35.5%, 87.7% and 82.4% for seven class emotion detection using a stack of Restricted Boltzmann Machines(RBM), which is high when compared to other latest methods. Keyword Emotion · Pattern · Classification · Feature · Texton
1 Introduction Machines offer an intelligent response by well understanding and recognition of human emotions. The emotion states are well delivered by facial expressions. The detection of * A. Robert Singh [email protected] 1
Department of Information Technology, Ponjesly College of Engineering, Nagercoil, India
2
Department of Computer Applications, Alagappa University, Karaikudi, India
3
School of Computing, Sastra Deemed To Be University, Thanjavur, India
4
School of Computing, Kalasalingam Academy of Research and Education, Anand Nagar, India
5
Department of Computer Science, Christ University, Bengalore, India
emotions is needed in several applications like smart environments, Content-Based Image Retrieval (CBIR), detection of fraud, driver tiredness detection and education systems as it advances the quality of Human Computer Interaction (HCI) by enhancing computer intelligence. In facial expression recognition applications, the repetition of intensity variations (Haghighat et al. 2015) in the acquired facial images is enco
Data Loading...
