Pengembangan Model Pengenalan Wajah Manusia dengan Teknik Reduksi Dimensi Bi2DPCA dan Support Vector Machine sebagai Classifier

  • Fredicia Fredicia Universitas Kristen Krida Wacana
  • Agus Buono Sekolah Pascasarjana IPB
  • Endang Purnama Giri Sekolah Pascasarjana IPB

Abstract

This paper presents the modeling of face recognition using feature extraction based on Principal Component Analysis (PCA) and Support Vector Machine (SVM) as a classifier. Three PCA techniques were compared, they are 1DPCA, 2DPCA and Bi-2DPCA. Meanwhile, three type of SVM kernel functions-linear, polynomial, and radial basis function (RBF) were used. The experiment used the ORL Face Database AT&T Laboratory, which contain 400 images with 10 images per each person. The leave one out method is used for validating each pair of extraction and classifier method. The highest accuracy is obtained by a combination of linear kernel and Bi-2DPCA85%, with 94.25%, and also the fastest computation time, is 15.34 seconds.

Index Terms— Face Recognition, Principle Component Analysis, Kernel, Support Vector Machine, Leave-one Out Cross Validation

Downloads

Download data is not yet available.
Published
2016-04-01
How to Cite
Fredicia, F., Buono, A., & Giri, E. (2016). Pengembangan Model Pengenalan Wajah Manusia dengan Teknik Reduksi Dimensi Bi2DPCA dan Support Vector Machine sebagai Classifier. Ultimatics : Jurnal Teknik Informatika, 8(1), 11-15. https://doi.org/https://doi.org/10.31937/ti.v8i1.497