IMPLEMENTASI DEEP LEARNING BERBASIS CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN METODE TRANSFER LEARNING PADA KLASIFIKASI BATIK NUSANTARA

Syaila Ananta Karenina, . (2025) IMPLEMENTASI DEEP LEARNING BERBASIS CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN METODE TRANSFER LEARNING PADA KLASIFIKASI BATIK NUSANTARA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf

Download (134kB)
[img] Text
AWAL.pdf

Download (2MB)
[img] Text
BAB I.pdf
Restricted to Repository UPNVJ Only

Download (200kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only

Download (3MB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only

Download (399kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only

Download (17MB)
[img] Text
BAB V.pdf

Download (174kB)
[img] Text
DAFTAR PUSTAKA.pdf

Download (182kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only

Download (1MB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only

Download (10MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
HASIL PLAGIARSME.pdf
Restricted to Repository staff only

Download (18MB)

Abstract

Batik is an Indonesian cultural heritage that holds high artistic and symbolic value. The diversity of batik motifs across various regions makes the process of recognizing and classifying motif images a significant aspect in the field of digital image processing. This study aims to classify five types of Batik Nusantara motifs Parang, Kawung, Mega Mendung, Ceplok, and Tujuh Rupa using a Convolutional Neural Network (CNN) with a Transfer Learning approach based on the ResNet-18 architecture. Two training scenarios were applied: one without an optimizer and one using the Stochastic Gradient Descent (SGD) optimizer. The results showed that without using an optimizer, the model only achieved 27% accuracy. Meanwhile, applying SGD significantly improved the model’s performance, achieving 81% accuracy, with a precision of 82%, recall of 81%, and F1-score of 81%. These findings indicate that weight optimization plays a crucial role in enhancing the model's ability to classify batik images. Therefore, the Transfer Learning method optimized using SGD is capable of producing optimal results in batik motif classification and contributes to cultural preservation through image recognition technology.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511137] [Pembimbing 1: Musthofa Galih Pradana] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Widya Cholil] [Penguji 2: Muhammad Panji Muslim]
Uncontrolled Keywords: Batik Nusantara, CNN, Transfer Learning, ResNet-18, Stochastic Gradient Descent, image classification
Subjects: Q Science > QA Mathematics
T Technology > T Technology (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: SYAILA ANANTA KARENINA
Date Deposited: 26 Aug 2025 10:10
Last Modified: 26 Aug 2025 10:10
URI: http://repository.upnvj.ac.id/id/eprint/37535

Actions (login required)

View Item View Item