Symmetrical Singular Value Decomposition Representation pada Citra Wajah Iluminasi berbasis Gabor Filter untuk Pengenalan Wajah

FERNANDO, IG DONNY (2018) Symmetrical Singular Value Decomposition Representation pada Citra Wajah Iluminasi berbasis Gabor Filter untuk Pengenalan Wajah. Other thesis, Universitas Sebelas Maret.

PDF - Published Version Download (23Kb)

Abstract

The purpose of this research is to present Symmetrical Singular Value Decomposition Representation (SSVDR) method with Gabor Filter under illumination effect for face recognition. SSVDR method was proposed to normalize illuminated face images caused by the difference of light. SSVDR method represented characteristics of face images on low-intensity combined with the symmetrical reversed part of the face based on Singular Value Decomposition (SVD). Gabor Filter was used to extract the face images which were already processed using SSVDR. In order to do the face recognition, PCA and LDA methods were used with Nearest Neighbor as the classifier. PCA and LDA techniques are used to represent high-dimensional data into lower dimensions, whereas the Nearest Neighbor method is used to identify based on closest distance of data. The result showed that face recognition using SSVDR based on Gabor Filter obtained accuracy 91.86% with PCA and 91.57% with LDA.

Actions (login required)