Quantum-inspired binary gravitational search algorithm to recognize the facial expressions

2020 ◽  
Vol 31 (10) ◽  
pp. 2050138
Author(s):  
Yogesh Kumar ◽  
Shashi Kant Verma ◽  
Sandeep Sharma
Keyword(s):  
Feature Selection ◽  
Facial Expression ◽  
Facial Expression Recognition ◽  
Search Algorithm ◽  
Gravitational Search Algorithm ◽  
Expression Recognition ◽  
Side View ◽  
Selection Approach ◽  
Gravitational Search ◽  
Feature Selection Approach

This paper addresses an autonomous facial expression recognition system using the feature selection approach of the Quantum-Inspired Binary Gravitational Search Algorithm (QIBGSA). The detection of facial features completely depends upon the selection of precise features. The concept of QIBGSA is a modified binary version of the gravitational search algorithm by mimicking the properties of quantum mechanics. The QIBGSA approach reduces the computation cost for the initial extracted feature set using the hybrid approach of Local binary patterns with Gabor filter method. The proposed automated system is a sequential system with experimentation on the image-based dataset of Karolinska Directed Emotional Faces (KDEF) containing human faces with seven different emotions and different yaw angles. The experiments are performed to find out the optimal emotions using the feature selection approach of QIBGSA and classification using a deep convolutional neural network for robust and efficient facial expression recognition. Also, the effect of variations in the yaw angle (front to half side view) on facial expression recognition is studied. The results of the proposed system for the KDEF dataset are determined in three different cases of frontal view, half side view, and combined frontal and half side view images. The system efficacy is analyzed in terms of recognition rate.

An ensemble approach of improved quantum inspired gravitational search algorithm and hybrid deep neural networks for computational optimization

2021 ◽  
pp. 2150100
Author(s):  
Yogesh Kumar ◽  
Shashi Kant Verma ◽  
Sandeep Sharma
Keyword(s):  
Neural Networks ◽  
Facial Expression ◽  
Deep Neural Networks ◽  
Search Algorithm ◽  
Gravitational Search Algorithm ◽  
Recognition Rate ◽  
Expression Recognition ◽  
Computational Optimization ◽  
Ensemble Approach ◽  
Gravitational Search

In this paper, an autonomous ensemble approach of improved quantum inspired gravitational search algorithm (IQI-GSA) and hybrid deep neural networks (HDNN) is proposed for the optimization of computational problems. The IQI-GSA is a combinational variant of gravitational search algorithm (GSA) and quantum computing (QC). The improved variant enhances the diversity of mass collection for retaining the stochastic attributes and handling the local trapping of mass agents. Further, the hybrid deep neural network encompasses the convolutional and recurrent neural networks (HDCR-NN) which analyze the relational & temporal dependencies among the different computational components for optimization. The proposed ensemble approach is evaluated for the application of facial expression recognition by experimentation on Karolinska Directed Emotional Faces (KDEF) and Japanese Female Facial Expression (JAFFE) datasets. The experimentation evaluations evidently exhibit the outperformed recognition rate of the proposed ensemble approach in comparison with state-of-the-art techniques.

scholarly journals Facial Expression Analysis by Machine Learning

2010 ◽  
pp. 239-258
Author(s):  
Siu-Yeung Cho ◽  
Teik-Toe Teoh ◽  
Yok-Yen Nguwi
Keyword(s):  
Feature Selection ◽  
Facial Expression ◽  
Real Time ◽  
Facial Expression Recognition ◽  
Classification Performance ◽  
Difficult Problem ◽  
Facial Features ◽  
Expression Recognition ◽  
Real Time Processing ◽  
Good Classification Performance

Facial expression recognition is a challenging task. A facial expression is formed by contracting or relaxing different facial muscles on human face that results in temporally deformed facial features like wide-open mouth, raising eyebrows or etc. The challenges of such system have to address with some issues. For instances, lighting condition is a very difficult problem to constraint and regulate. On the other hand, real-time processing is also a challenging problem since there are so many facial features to be extracted and processed and sometimes, conventional classifiers are not even effective in handling those features and produce good classification performance. This chapter discusses the issues on how the advanced feature selection techniques together with good classifiers can play a vital important role of real-time facial expression recognition. Several feature selection methods and classifiers are discussed and their evaluations for real-time facial expression recognition are presented in this chapter. The content of this chapter is a way to open-up a discussion about building a real-time system to read and respond to the emotions of people from facial expressions.

Introducing clustering based population in Binary Gravitational Search Algorithm for Feature Selection

2020 ◽  
Vol 93 ◽  
pp. 106341 ◽  
Author(s):  
Ritam Guha ◽  
Manosij Ghosh ◽  
Akash Chakrabarti ◽  
Ram Sarkar ◽  
Seyedali Mirjalili
Keyword(s):  
Feature Selection ◽  
Search Algorithm ◽  
Gravitational Search Algorithm ◽  
Gravitational Search
Sign in / Sign up

Export Citation Format

Share Document