Deteksi Deformasi Wajah 3d Menggunakan Ekstraksi Fitur Berbasis PCA

Darujati, Cahyo (2020) Deteksi Deformasi Wajah 3d Menggunakan Ekstraksi Fitur Berbasis PCA. Doctoral thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 07111160010011-Disertation.pdf] Text
07111160010011-Disertation.pdf - Accepted Version
Restricted to Repository staff only until 1 April 2023.

Download (5MB) | Request a copy

Abstract

Dalam beberapa penelitian yang ada, Pengenalan wajah 3D berpotensi mencapai akurasi yang
lebih baik daripada pengenalan wajah 2D dengan mengukur geometri fitur kaku di wajah. Hal
ini menghindari perangkap algoritma pengenalan wajah 2D seperti perubahan pencahayaan, ekspresi wajah yang berbeda, tata rias dan orientasi kepala. Salah satu permasalahan yang ada karena kerapuhan sistem deteksi wajah 3D. Dengan latar belakang tersebut, maka penelitian ini membangun sebuah model yang mampu melakukan deteksi deformasi wajah 3D menggunakan kombinasi beberapa algoritma terkait dengan ekstraksi fitur. Dimulai dengan mengenal fitur wajah baik 2D dan 3D, Tetap ataupun bergerak. Kemudian melakukan deformasi pada wajah 2D dan 3D. Terakhir, melakukan pengenalan deformasi wajah menggunakan PCA NN.

=====================================================================================================

In some existing research, 3D face recognition has the potential to achieve better accuracy than its 2D counterpart by measuring geometry of rigid features on the face. This avoids such pitfalls of 2D face recognition algorithms as change in lighting, different facial expressions, make-up
and head orientation. One of the problems that exist is the fragility of the 3D face detection system.
With this background, this research has built a model capable of detecting 3D facial deformation using a combination of several algorithms related to feature extraction. Starting with recognizing facial features in both 2D and 3D, fixed or moving. Then deform the 2D and
3D faces. Finally, perform facial deformation recognition using PCA NN.

Item Type: Thesis (Doctoral)
Uncontrolled Keywords: deformasi, deteksi, wajah 3d, ekstraksi fitur, deformation, detection, face 3D, features extraction
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1650 Face recognition. Optical pattern recognition.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7882.B56 Biometric identification
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7882.P3 Pattern recognition systems
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20001-(S3) PhD Thesis
Depositing User: Cahyo Darujati
Date Deposited: 06 Mar 2021 01:17
Last Modified: 06 Mar 2021 01:17
URI: http://repository.its.ac.id/id/eprint/83537

Actions (login required)

View Item View Item