3D HMM-based Facial Expression Recognition using Histogram of Oriented Optical Flow

Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2015, Vol 3, Issue 6

Abstract

In this paper, we propose a 3D HMM (Three-dimensional Hidden Markov Models) approach to recognizing human facial expressions and associated emotions. Human emotion is usually classified by psychologists into six categories: Happiness, Sadness, Anger, Fear, Disgust and Surprise. Further, psychologists categorize facial movements based on the muscles that produce those movements using a Facial Action Coding System (FACS). We look beyond pure muscle movements and investigate facial features – brow, mouth, nose, eye height and facial shape – as a means of determining associated emotions. Histogram of Optical Flow is used as the descriptor for extracting and describing the key features, while training and testing are performed on 3D Hidden Markov Models. Experiments on datasets show our approach is promising and robust.

Authors and Affiliations

Sheng H. Kung, Mohamed Zohdy, Djamel Bouchaffra

Keywords

Related Articles

Application of Genetic Algorithms Coupled with Neural Networks to Optimization of Reinforced Concrete Footings

This paper first applies genetic algorithms to optimally design reinforced concrete isolated footings subjected to concentric loading. Based on the ACI Building Code, constraints are built by considering wide-beam and pu...

Toward Multi-Approach Model for Semi-Automating a Data Warehouse Design from an Ontology

The proliferation of projects that are part of the semantic Web is truly impressive. In fact, ontologies become increasingly present in information systems, they constitute great data sources that arouse the interest of...

Vibration Level Improvement of Id Fan in a Cement Plant Based On CFD Study of Incoming Dust Particles Streamline

This paper presents numerical study of aerosol flow inside of the induce draft (ID) fan inlet duct of a cement plant and the field observation of the proposed guide plate implementation as vibration reducer. Since ID fan...

Investigating Undergraduate Students’ Attitudes Towards English Mobile Learning A Case Study of Moroccan University Students

The increase of mobile devices, the availability of several features, and the decrease in terms of cost of smartphones made them useful not only for communication, but also for learning. Similarly, the importance of Engl...

Technical Data Extraction and Representation in Expert CAPP System

Computeraided process planning (CAPP) is an essential interface for linking design and manufacturing processes, the purpose of CAPP is to transform a part design specification obtained from CAD system into a sequence of...

Download PDF file
  • EP ID EP278793
  • DOI 10.14738/tmlai.36.1661
  • Views 66
  • Downloads 0

How To Cite

Sheng H. Kung, Mohamed Zohdy, Djamel Bouchaffra (2015). 3D HMM-based Facial Expression Recognition using Histogram of Oriented Optical Flow. Transactions on Machine Learning and Artificial Intelligence, 3(6), 42-69. https://europub.co.uk/articles/-A-278793