Open AccessA Hybrid Pain Detection Technique using SVM Parameter Optimization and Contourlet-Gabor Transform Feature Fusion
Author(s) -
Aparna Saini,
A. S. Mandal,
R.K. Sharma
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.l3902.1081219
Subject(s) - contourlet , support vector machine , pattern recognition (psychology) , artificial intelligence , computer science , feature (linguistics) , feature extraction , expression (computer science) , wavelet transform , linguistics , philosophy , wavelet , programming language
This paper highlights automatic pain expression recognition from facial images of pain. This technique is frequently used in healthcare applications. The research detects the pain expression by an effective recognition method. It is based on the concepts of fusion of contourlet transform with Gabor transform for feature extraction, and classification of expressions by using SVM. The ABC algorithm and GA is implemented for optimizing SVM parameters. In order to authenticate the precision and stoutness of the system, a number of experiments have been done on two databases namely UNBC shoulder pain database and IFD-CEERI database. It's provided throughout the simulation techniques. The suggested strategy is actually effective in recognition of pain expression in terms of accuracy