Integrated Approach to Recognition of Macro & Micro Expressions from Facial Images.
Date of Submission
December 2017
Date of Award
Winter 12-12-2018
Institute Name (Publisher)
Indian Statistical Institute
Document Type
Master's Dissertation
Degree Name
Master of Technology
Subject Name
Computer Science
Department
Electronics and Communication Sciences Unit (ECSU-Kolkata)
Supervisor
Mukherjee, Dipti Prasad (ECSU-Kolkata; ISI)
Abstract (Summary of the Work)
We present a computer based approach which recognizes emotional facial expressions along with subtle micro expressions. Our system captures live video streams and recognizes both macro and micro expression at the same time. This procedure integrates the task where a set of frames is classified whether it contains micro expressions or macro expressions at first. Afterwards corresponding micro or macro expressions are further classified to its type. We have introduced Motion Magnification using Eulerian Video Magnification method to magnify subtle local motions that helps identifying types of micro expression. We have done extensive experiments on two publicly available data sets CK+ containing videos of posed macro expressions and CASME II containing videos of posed micro expressions. Using variants of LBP features such as Uniform LBP and Rotation Invariant LBP feature dimension is reduced by 80% compared to normal LBP based features that leads to reduction of response time and increases computational efficiency and results in effective classifier performance.
Control Number
ISI-DISS-2017-273
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
DOI
http://dspace.isical.ac.in:8080/jspui/handle/10263/6847
Recommended Citation
Mukherjee, Debayan, "Integrated Approach to Recognition of Macro & Micro Expressions from Facial Images." (2018). Master’s Dissertations. 48.
https://digitalcommons.isical.ac.in/masters-dissertations/48
Comments
ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843061