PENGENALAN WAJAH MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK-RESTRICTED BOLTZMANN MACHINE BERBASIS PRINCIPAL COMPONENT ANALYSIS

Ali Hasan Ash Shiddiq, - (2020) PENGENALAN WAJAH MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK-RESTRICTED BOLTZMANN MACHINE BERBASIS PRINCIPAL COMPONENT ANALYSIS. S1 thesis, Universitas Pendidikan Indonesia.

[img] Text
S_KOM_1608246_Title.pdf

Download (2MB)
[img] Text
S_KOM_1608246_Chapter1.pdf

Download (688kB)
[img] Text
S_KOM_1608246_Chapter2.pdf
Restricted to Staf Perpustakaan

Download (1MB)
[img] Text
S_KOM_1608246_Chapter3.pdf

Download (1MB)
[img] Text
S_KOM_1608246_Chapter4.pdf
Restricted to Staf Perpustakaan

Download (1MB)
[img] Text
S_KOM_1608246_Chapter5.pdf

Download (599kB)
Official URL: http://repository.upi.edu

Abstract

Teknologi pengenalan wajah berpotensi untuk diterapkan pada berbagai bidang dalam kehidupan sehari-hari. Penelitian ini melakukan pengembangan teknologi pengenalan wajah dengan mengusulkan metode Convolutional Neural Network-Restricted Boltzmann Machine (CNN-RBM) berbasis Principal Component Analysis (PCA) menggunakan set data Labeled Faces in the Wild (LFW). CNN-RBM berbasis PCA memanfaatkan PCA sebagai pereduksi dimensi pada input, kemudian menggunakan CNN sebagai ekstraksi fitur, dan menggunakan RBM pada tahap klasifikasi wajah. Hasil eksperimen membuktikan bahwa CNN-RBM berbasis PCA mampu mengungguli baseline dengan peningkatan akurasi sebesar 1,6%. Face recognition technology can be applied in various fields of in everyday life. This research develops face recognition technology using Convolutional Neural Network-Restricted Boltzmann Machine (CNN-RBM) based on Principal Component Analysis (PCA) using labeled Faces in the Wild (LFW) set data. PCN-based CNN-RBM uses PCA as a dimension reduction in input, then uses CNN as a feature extraction, and uses RBM in face classification. The experimental results prove that PCN-based CNN-RBM was able to outperform the baseline with 1,6% accuracy improvement.

Item Type: Thesis (S1)
Additional Information: No Panggil : S KOM ALI p-2020; NIM : 1608246
Uncontrolled Keywords: Pengenalan wajah; deep learning; convolutional neural network; restricted boltzmann machine; principal component analysis; labeled faces in the wild;
Subjects: L Education > L Education (General)
Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Program Studi Ilmu Komputer
Depositing User: Ali Hasan Ash Shiddiq
Date Deposited: 31 Aug 2020 04:23
Last Modified: 31 Aug 2020 04:23
URI: http://repository.upi.edu/id/eprint/51328

Actions (login required)

View Item View Item