THE STUDY OF RENDER FARM IMAGE CLASSIFICATION USING DEEP NEURAL NETWORK

SARI, AULIA PERMATA (2019) THE STUDY OF RENDER FARM IMAGE CLASSIFICATION USING DEEP NEURAL NETWORK. S1 thesis, Universitas Mercu Buana Jakarta.

[img] Text (JURNAL MAHASISWA)
41515110156 - AULIA PERMATA SARI.pdf
Restricted to Registered users only

Download (2MB)

Abstract

Rendering on the making of movie animation is a process of combining the imagination of animators and artistic creativity by turning the graphic display into millions of moving images. To perform the rendering process, the render farm is used, which is a combination of a group of high-performance computers (super-computers) commonly referred to as Computer Generated Imager. Throughout this time, the render artist analyzes the image results of render farm manually by separating images that match the criteria and not according to the criteria one by one so that it takes a long time. Reflecting on that, the study presented in this paper proposed the method that is able to separate images of the results of render farm more quickly and accurately. The technique proposed in this study was the classification of approve and revise image from the results of the render farm machine by the use of Deep Neural Network (DNN) algorithm. To test the DNN that best fits the dataset, experiments were carried out on several layer depths and adjustment of epoch. In terms of treatment of the dataset, the experiment scenario selected was percentage and cross validation. The best performance in the experiment results was generated by layer depth configuration, which was 6, using epoch 75 with the value of accuracy, precision and recall being 92%, 100% and 93% respectively. Key words: Deep Neural Network, Deep Learning, Image Classification, Render Farm Rendering pada pembuatan film animasi merupakan proses penggabungan imajinasi animator dan kreativitas artistik dengan merubah tampilan grafis menjadi jutaan gambar bergerak. Mesin yang digunakan pada proses rendering adalah render farm, yaitu kombinasi sekelompok komputer berperforma tinggi (super-computer) yang biasa disebut dengan Computer Generated Imager. Selama ini render artist melakukan analisa gambar hasil render farm secara manual dengan memisahkan gambar yang sesuai dengan kriteria dan tidak sesuai dengan kriteria satu persatu sehingga membutuhkan waktu yang cukup lama. Penelitian tugas akhir ini menyajikan hasil penelitian usulan metode yang mampu memisahkan gambar hasil render farm dengan lebih cepat dan akurat. Teknik yang diusulkan dalam penelitian ini adalah klasifikasi gambar approve dan revise dari hasil mesin render farm dengan algoritma Deep Neural Network (DNN). Untuk menguji DNN yang paling sesuai dengan dataset, dilakukan eksprimen terhadap beberapa kedalaman layer dan penyesuaian nilai epoch. Dari sisi perlakuan atas dataset, skenario eksperimen yang dipilih adalah persentase dan cross validation. Hasil eksperimen dengan kinerja terbaik dihasilkan oleh konfigurasi kedalaman layer sebanyak 6 menggunakan epoch 75 dengan nilai akurasi, presisi dan recall adalah berturut-turut 92%, 100% dan 93%. Kata kunci: Deep Neural Network, Deep Learning, Klasifikasi Gambar, Render Farm

Item Type: Thesis (S1)
Call Number CD: JM/TI. 19 203
NIM/NIDN Creators: 41515110156
Uncontrolled Keywords: Deep Neural Network, Deep Learning, Klasifikasi Gambar, Render Farm
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika > 004.6 Interfacing and Communications/Tampilan Antar Muka (Interface) dan Jaringan Komunikasi Komputer
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika > 004.6 Interfacing and Communications/Tampilan Antar Muka (Interface) dan Jaringan Komunikasi Komputer > 004.65 Computer Communications Networks/Jaringan Komunikasi Komputer
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 005 Computer Programmming, Programs, Data/Pemprograman Komputer, Program, Data > 005.7 Data in Computer Systems/Data dalam Sistem-sistem Komputer > 005.75 Specific Types of Data Files and Databases/Jenis Spesifik File Data dan Pangakalan Data
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 005 Computer Programmming, Programs, Data/Pemprograman Komputer, Program, Data > 005.7 Data in Computer Systems/Data dalam Sistem-sistem Komputer > 005.75 Specific Types of Data Files and Databases/Jenis Spesifik File Data dan Pangakalan Data > 005.754 Network Databases/Pangakalan Data Jaringan
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: Dede Muksin Lubis
Date Deposited: 30 Aug 2022 04:32
Last Modified: 30 Aug 2022 04:32
URI: http://repository.mercubuana.ac.id/id/eprint/68650

Actions (login required)

View Item View Item