Empirical Evaluation of SVM for Facial Expression Recognition
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 11
Abstract
Support Vector Machines (SVMs) have shown bet-ter generalization and classification capabilities in different appli-cations of computer vision; SVM classifies underlying data by a hyperplane that can separate the two classes by maintaining the maximum margin between the support vectors of the respective classes. An empirical analysis of SVMs on the facial expression recognition task is reported with high intra and low inter class variations by conducting an extensive set of experiments on a large-scale Fer 2013 dataset. Three different kernel functions of SVM are used; linear kernel, quadratic kernel and cubic kernel, whereas, Histogram of Oriented Gradient (HoG) is used as a feature descriptor. Cubic Kernel achieves highest accuracy on Fer 2013 dataset using HoG.
Authors and Affiliations
Saeeda Saeed, Junaid Baber, Maheen Bakhtyar, Ihsan Ullah, Naveed Sheikh, Imam Dad, Anwar Ali Sanjrani
Keywords
Related Articles
- EP ID EP417776
- DOI 10.14569/IJACSA.2018.091195
- Views 114
- Downloads 0
Identification of Toddlers’ Nutritional Status using Data Mining Approach
One of the problems in community health center or health clinic is documenting the toddlers’ data. The numbers of malnutrition cases in developing country are quite high. If the problem of malnutrition is not resolved, i...
Semantic E-Learn Services and Intelligent Systems using Web Ontology
Present vision for the web is the semantic web in which information is given explicit meaning, making it easier for machines to automatically process and integrate information available on the web. It provides the inform...
Tutoring Functions in a Blended Learning System: Case of Specialized French Teaching
There is an emergence of blended learning today which combines diversified teaching methods, alternating distance learning and classroom learning. As a matter of fact, most Moroccan universities are presently aware of th...
Development of a Two Factor Authentication for Vehicle Parking Space Control based on Automatic Number Plate Recognition and Radio Frequency Identification
This paper proposed a two factor authentication for vehicle access controls using Automatic Number Plate Recognition (ANPR) and Radio Frequency Identification system (RFID) for the University of Zambia (UNZA) vehicle acc...
The Effect of Religious Beliefs, Participation and Values on Corruption: Survey Evidence from Iraq
This research tests the role that religious beliefs, rituals and values plays on the corruption in Iraq. Furthermore, the research assesses ethical and moral ideals pertinent to religion, in the Iraqi educational sector....