Penerapan Deep Learning Dalam Pengenalan Endek Bali Menggunakan Convolutional Neural Network

Theresia Hendrawati (Institut Bisnis dan Teknologi Indonesia, Bali)
Dewa Ayu Putri Wulandari (Institut Bisnis dan Teknologi Indonesia, Bali)
I Gde Swiyasa Surya Dharma (Institut Bisnis dan Teknologi Indonesia, Bali)
Ni Luh Wiwik Sri Rahayu Ginantra, M.Kom (Institut Bisnis dan Teknologi Indonesia, Bali)
Christina Purnama Yanti (Institut Bisnis dan Teknologi Indonesia, Bali)

JURNAL MEDIA INFORMATIKA BUDIDARMA
Vol 7, No 4 (2023): Oktober 2023

Endek Bali has been recognized as one of the Intellectual Property of Traditional Cultural Expressions, with registration number EBT 12.2020.0000085 on December 22, 2020. In the present era, many people find it difficult to distinguish between endek fabric and batik fabric because their patterns are quite similar. This research aims to help identify Bali's Endek fabric based on digital images. One of the approaches used is the Convolutional Neural Network method with ResNet50, which is a deep learning method used to recognize and classify objects in digital images. Evaluation result from testing the best model with new testing model using confession matrix get result of 90,69% accuracy, 90,69% recall, 90,60% precision and 90,68% f1-score. Thus, the model developed in this research demonstrates optimal performance in classifying images of Bali's Endek.