4 Citations (Scopus)

Abstract

In the micro-expression detection system on part of facial components, it is necessary to detect that component in accurately, precisely and fast. This study shows a comparison between accuracy and speed in the detection of the component area of the face (right eye, left eye and mouth) automatically. Micro expression occurs in a short time, fast and in very smooth movements. The face component detection method conducted in this study is a feature-based method (Viola Jones method) which is compared with the model-based method (ASM and DRMF methods). Comparison of the accuracy of the three methods in the detection of the face component area shows that the ASM and DRMF methods provide an accuracy value of 100%, while the Haar Cascade Classifier method shows an average accuracy of 44%. Meanwhile, on speed measurement to find the face component area, the DRMF method is the fastest with an average processing time of 0.08 seconds followed by ASM method of 0.14 seconds, and the Haar method of 0.25 seconds.

Original languageEnglish
Title of host publication2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages221-226
Number of pages6
ISBN (Electronic)9781538675090
DOIs
Publication statusPublished - 2 Jul 2018
Event2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Surabaya, Indonesia
Duration: 26 Nov 201827 Nov 2018

Publication series

Name2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding

Conference

Conference2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018
Country/TerritoryIndonesia
CitySurabaya
Period26/11/1827/11/18

Keywords

  • component
  • formatting
  • insert(key words)
  • style
  • styling

Fingerprint

Dive into the research topics of 'Micro Expression: Comparison of Speed and Marking Accuracy in Facial Component Detection'. Together they form a unique fingerprint.

Cite this