Research Article Open Access

Symbolic Aggregate approXimation-Local Binary Pattern Feature Descriptor Combination for Automatic Facial Expression Recognition

Sumithra M.D.1 and M. Abdul Rahiman2
  • 1 Karpagam Academy of Higher Education, India
  • 2 C-APT, India
Journal of Computer Science
Volume 15 No. 1, 2019, 45-56

DOI: https://doi.org/10.3844/jcssp.2019.45.56

Submitted On: 1 November 2018 Published On: 8 January 2019

How to Cite: M.D., S. & Abdul Rahiman, M. (2019). Symbolic Aggregate approXimation-Local Binary Pattern Feature Descriptor Combination for Automatic Facial Expression Recognition. Journal of Computer Science, 15(1), 45-56. https://doi.org/10.3844/jcssp.2019.45.56

Abstract

Automatic identification of facial expression is a significant research area which is anticipated for real time processing in Human-Computer Interaction domain. Along with an efficient classifier for assigning the class label to each of the input face image, it is very necessary to have a strong feature vector for training the classifier. This paper proposes an effectual combination of Local Binary Pattern and Symbolic Aggregate approXimation method for the feature vector generation for the classifier. Twenty one facial patches are extracted from the face image and the LBP value and SAX string for these twenty one patches are utilised for feature vector generation. The feature vectors of images are submitted to the Ensemble Bag classifier for training purpose. Images which were not used for training is used for testing. An average accuracy of 98.7% was obtained when tested on JAFFE data set for seven expressions and an accuracy of 96.96% was obtained for nine expressions on fused database. A detailed analysis of the testing conducted on images with partial occlusion and illumination variance are presented here.

  • 736 Views
  • 608 Downloads
  • 0 Citations

Download

Keywords

  • Local Binary Pattern (LBP)
  • Symbolic Aggregate approXimation (SAX)
  • Feature Vector
  • Ensemble Bag Classifier
  • Learning