Enhanced Facial Emotion Recognition by Optimal Descriptor Selection with Neural Network

Abstract

Facial Emotion Recognition (FER) is the approach of detecting emotions of humans from facial expressions. Emotions are detected automatically by the human brain and hence, many computer aided techniques are implemented for recognizing emotions. Recognition of natural emotions is an exciting area with a broad range of real time applications like automated tutoring models, smart environments computer–human interaction, driver warning systems, and video and image retrieval. The major goal of this paper is to implement an intelligent model for FER. The proposed model involves few steps: (a) Face extraction (b) Image filtering, (c) Extraction of facial components, (d) Descriptor selection, and (d) Classification. Initially, the face is extracted from the input image by the Viola–Jones method, which is generally employed for the detection of object. Further, the noise of the image is filtered by the Gabor Filtering. Further, the facial components are extracted as features via the Affine-Scale-Invariant Feature Transform (ASIFT), which is the modified version of SIFT method. Since the length of the descriptors generated from ASIFT is high; the number of descriptors is reduced by the optimal descriptor selection approach with the aid of hybrid meta-heuristic algorithm termed as MV-WOA. The extracted descriptors are subjected to Neural Network (NN). As a modification to the existing machine learning algorithms, the number of hidden neurons in the NN is optimized by the proposed WOA+MVO algorithm. By conducting experiments, the results demonstrate that the developed system can perform better the recent traditional approaches for emotion recognition for classifying seven emotions like normal, smile, sad, surprise, anger, fear, and disgust.

KEYWORDS:

• Affine-scale-invariant feature transform
• Convolutional neural network
• Facial emotion recognition
• Multi-verse optimization
• Neural network
• Scale-invariant feature transform
• Whale optimization algorithm

Additional information

Notes on contributors

P. M. Ashok Kumar

P M Ashok Kumar obtained his PhD from Anna University, BTech in ECE from JNTU Hyderabad and ME in Computer Science Engg from Anna University, Chennai, India. Currently he is working as associate professor in the Department of Computer Science Engineering, KL University, India. He authored more than 20 articles in both SCIE & Scopus indexed journals, conferences. His main research interests include image processing, data mining, machine learning. He is currently working on face detection & recognition, video traffic surveillance, texture feature extraction, object tracking features.

Jeevan Babu Maddala

M Jeevan Babu obtained his BTech in CSE from JNTU Hyderabad and ME Computer Science Engg from Acharya Nagarjuna University, India. Currently, he is working as assistant professor in the Department of Computer Science Engineering, VVIT, India. He authored more than 10 articles in Scopus indexed journals, conferences. His main research interests include image processing, data mining, machine learning. He is currently working on face detection & recognition, video traffic surveillance, texture feature extraction, object tracking features. E-mail: [email protected]

K. Martin Sagayam

K Martin Sagayam hails from Tiruchirapalli district in the state of Tamilnadu, India. He received his BE degree in electronics and communication engineering from Anna University in the year 2009 and his master degree in communication systems from Anna University in the year 2012. Currently, he is working as assistant professor in the Department of ECE, Karunya Institute Technology and Sciences, Coimbatore, India. He has authored/ co-authored 10 refereed International Journals. He has also presented 13 papers in reputed international and national conferences. He has authored 3 book chapters with reputed international publishers. His research articles are cited by many international journals and have received approximately 24 citations. He is a reviewer for reputed journals. He is an active member of professional bodies. His area of interest includes pattern recognition, artificial intelligence and signal processing in imaging. E-mail: [email protected]