MENENTUKAN EKSPRESI WAJAH DENGAN METODE K-MEANS KLUSTERING

  • Jasman Pardede
  • Irma Amelia Dewi
  • Ade Bambang Kurnia
Keywords: K-Means Clustering, JAFFE, Facial Expression

Abstract

To determine human facial expression be required data set as data test. In this research, data set use Japanese Female Facial Expression (JAFFE). To detect the face area of a picture uses GMS and then transformed to be data that need to calculate with K-Means. The data that calculated are probability ofthe eyes opening, angle of lips, and array pixel by size 32 x 80. By the calculation of Euclidian Distance between all ofdata set and input result the similarity for each centroid. The precision of research is 87.68%. The precision to women subject is 90,28% and to men subject is 88,61%. The precision using of JAFFE data is 88.2%. The precision the subject who has mustache and beard is only 40%.

References

[1] McCraty, Rolling, MA., Barrios-Choplin, Bob, PhD., Atkinson, Mike., dan Tomasino, Dana, BA. (1998). “The Effects of Different Types of Music on Mood, Tension, and Mental Clarity”. Alternative Therapies. 4 (1), 75-84.
[2] Calder, A. J., Burton A. M., Miller, P., Young, A. W. & Akamatsu, S. 2001. “A Principal Component Analysis of Facial Expressions”. Vision Research, vol 41, pp 1179-1208.
[3] Michael J. Lyons, Shigeru Akamatsu, Miyuki Kamachi & Jiro Gyoba. (1998). “Coding Facial Expressions with Gabor Wavelets”. IEEE Computer Society, pp. 200-205.
[4] Gunadi, I Gede Aris., dan Harjoko, Agus. (2014). “Pengenalan Pola Gerak Mulut Dengan Menggunakan Pendekatan SOM (Self Organaizing Feature Map)”. Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI). 3 (1), 15-20.
[5] Utami, Dina Budi. (2012). “Pengenalan Gerak Jari Tangan Menggunakan Hidden Markov Model pada Augmented Interface System”.
Published
2016-10-29
Section
Articles