Akbar, Afrizal Laksita (2020) PENGENALAN WAJAH MENGGUNAKAN METODE DEEP NEURAL NETWORKS DENGAN PERPADUAN METODE DISCRETE WAVELET TRANSFORM, STATIONARY WAVELET TRANSFORM, DAN DISCRETE COSINE TRANSFORM. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
05111550010005-Master_Thesis.pdf Download (2MB) | Preview |
Abstract
Metode pengenalan identitas dilakukan dengan menggunakan wajah, sidik jari, telapak tangan, retina mata, atau suara yang umum dikenal dengan metode biometric. Wajah adalah organ tubuh manusia yang paling sering dijadikan indikasi pengenalan seseorang. Dalam pengembangan sistem pengenalan wajah terdapat beberapa isu yang harus diperhatikan, karena dalam proses pengenalan wajah terdapat beberapa faktor yang mempengaruhi, yaitu faktor pencahayaan, ekspresi wajah dan perubahan atribut wajah antara lain dagu, kumis, dan aksesoris yang digunakan misalnya kacamata atau syal.
Pada penelitian ini, diusulkan penggabungan metode Discrete Wavelet Transform dan Stationary Wavelet Transform untuk meningkatkan kualitas citra khususnya pada gambar berukuran kecil. Sedangkan metode Histogram Equalization dapat memperbaiki citra pada kondisi citra dengan kelebihan atau kekurangan intensitas cahaya. Metode Discrete Cosine Transform digunakan untuk mengubah citra wajah ke dalam bentuk citra frekuensi untuk ekstraksi fitur pada metode klasifikasi Deep Neural Networks.
Pengujian dilakukan dengan 10 fold Cross Validation. Hasil penelitian menunjukkan bahwa penggabungan 4 metode yang diusulkan diperoleh tingkat akurasi yang paling baik sebesar 92.73% dibandingkan dengan metode Histogram Equalization 80.73%, Discrete Wavelet Transform 85.85%, Stationary Wavelet Transform 64.27%, Discrete Cosine Transform 89.50%, penggabunggan Discrete Wavelet Transform dan Stationary Wavelet Transform 86.89%, penggabunggan Histogram Equalization, Discrete Wavelet Transform, dan Stationary Wavelet Transform 69.77%, dan Stationary Wavelet Transform, Discrete Wavelet Transform, dan Histogram Equalization 77.39%.
================================================================
Personal identification can be done by using face, fingerprint, palm prints, eye’s retina, or voice recognition which commonly called as biometric methods. The face recognition is the most popular and widely used among those biometric methods. However, there are some issues in the implementation of this method. They are lighting factor, facial expression and attributes (chin, mustache, or wearing some accessories).
In this study, we propose a combination method of Discrete Wavelet Transform and Stationary Wavelet Transform that able to improve the image quality, especially in the small-sized image. Moreover, we also use Histogram Equalization in order to correct noises such as over or under exposure, Discrete Cosine Transform in order to transform the image into frequency domain, and Deep Neural Networks in order to perform the feature extraction and classify the image. A 10-fold cross-validation method was used in this study.
As the result, the proposed method showed the highest accuracy up to 92.73% compared to Histogram Equalization up to 80.73%, Discrete Wavelet Transform up to 85.85%, Stationary Wavelet Transform up to 64.27%, Discrete Cosine Transform up to 89.50%, the combination of Histogram Equalization, Discrete Wavelet Transform, and Stationary Wavelet Transform up to 69.77%, and the combination of Stationary Wavelet Transform, Discrete Wavelet Transform, and Histogram Equalization up to 77.39%.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Pengenalan Wajah, Face Recognition, Histogram Equalization, Discrete Wavelet Transform, Stationary Wavelet Transform, Discrete Cosine Transform, Deep Neural Networks |
| Subjects: | T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis |
| Depositing User: | Afrizal Laksita Akbar |
| Date Deposited: | 14 Aug 2020 03:34 |
| Last Modified: | 08 Jun 2023 13:19 |
| URI: | http://repository.its.ac.id/id/eprint/78130 |
Actions (login required)
 |
View Item |