TY - GEN
T1 - Micro Expression
T2 - 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018
AU - Rosiani, Ulla Delfana
AU - Ririd, Ariadi Retno Tri Hayati
AU - Choirina, Priska
AU - Sooai, Adri Gabriel
AU - Sumpeno, Surya
AU - Purnomo, Mauridhi Hery
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - 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.
AB - 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.
KW - component
KW - formatting
KW - insert(key words)
KW - style
KW - styling
UR - http://www.scopus.com/inward/record.url?scp=85066477196&partnerID=8YFLogxK
U2 - 10.1109/CENIM.2018.8711313
DO - 10.1109/CENIM.2018.8711313
M3 - Conference contribution
AN - SCOPUS:85066477196
T3 - 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding
SP - 221
EP - 226
BT - 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 November 2018 through 27 November 2018
ER -