Enhancing facial component analysis

Siska Pebiana, T. Basaruddin, M. Rahmat Widyanto, Dewi Yanti Liliana

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

Abstract

Capturing non-verbal information from a face is the most important phase in emotion recognition through facial expression. In order to do that, it needs to find suitable features extraction method that could help to figure out the meaning from the given face. Inspired by Liliana Dewi[1] that used a geometric feature for analyzing facial component with a good result accuracy around 98.59%. So this paper tries to improve that method in order to enhance the result of facial components analysis. This study use Hellen dataset to retrain the Active Appearance Model (AAM), add image preprocessing like image enhancement, use other geometric features and Fuzzy Rule-Based System for extract the feature on extended Cohn Kanade (CK+) dataset. The result of this research gives better in recognizing facial components than previous work with accuracy around 99.36%.

Original languageEnglish
Title of host publicationProceedings of the 2019 2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019
PublisherAssociation for Computing Machinery
Pages175-179
Number of pages5
ISBN (Electronic)9781450366427
DOIs
Publication statusPublished - 10 Jan 2019
Event2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - and its Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019 - Bali, Indonesia
Duration: 10 Jan 201913 Jan 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - and its Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019
CountryIndonesia
CityBali
Period10/01/1913/01/19

Keywords

  • Aam
  • Active appearance model
  • Facial component analysis
  • Fuzzy rule based system

Fingerprint Dive into the research topics of 'Enhancing facial component analysis'. Together they form a unique fingerprint.

Cite this