Nonlinear fuzzy robust PCA on shape modelling of active appearance model for facial expression recognition

Nunik Pratiwi, T. Basaruddin, M. Rahmat Widyanto, Dewi Yanti Liliana

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Automatic facial expression recognition is one of the potential research area in the field of computer vison.It aims to improve the ability of machine to capture social signals in human.Automatic facial expression recognition is still a challenge. We proposed method using contrast limited adaptive histogram equalization (CLAHE) for pre-processing stage then performed feature extraction using active appearance model (AAM) based on nonlinear fuzzy robust principal component analysis (NFRPCA). The feature extraction results will be classified with support vector machine (SVM). Feature points generated AAM based on NFRPCA more adaptive compared to AAM based PCA.Our proposed method’s the average accuracy rate reached 96,87% and 93,94% for six and seven basic emotions respectively.

Original languageEnglish
Title of host publicationProceedings of 2017 International Conference on Video and Image Processing, ICVIP 2017
PublisherAssociation for Computing Machinery
Pages68-72
Number of pages5
ISBN (Electronic)9781450353830
DOIs
Publication statusPublished - 27 Dec 2017
Event2017 International Conference on Video and Image Processing, ICVIP 2017 - Singapore, Singapore
Duration: 27 Dec 201729 Dec 2017

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2017 International Conference on Video and Image Processing, ICVIP 2017
Country/TerritorySingapore
CitySingapore
Period27/12/1729/12/17

Keywords

  • AAM
  • Contrast limited adaptive histogramequalization
  • Facial expression
  • Nonlinear fuzzyrobust PCA
  • SVM

Fingerprint

Dive into the research topics of 'Nonlinear fuzzy robust PCA on shape modelling of active appearance model for facial expression recognition'. Together they form a unique fingerprint.

Cite this