Implementation and Classification of Images of Batik Types Using the Convolutional Neural Network Method with ResNet Architecture.

Wiratama, Rizal Whisnu (2024) Implementation and Classification of Images of Batik Types Using the Convolutional Neural Network Method with ResNet Architecture. Implementation and Classification of Images of Batik Types Using the Convolutional Neural Network Method with ResNet Architecture. (1736).

Text D4 TI_1941720227_KOMPILASI_2023.pdf Download (5MB)

Abstract

This study aims to implement the deep learning method using the Convolutional Neural Network (CNN) with the ResNet model to identify types of batik. Batik art is one of the results of the culture of the Indonesian people who have high cultural values. However, identification of various batik motifs is often difficult, especially for ordinary people. Therefore, the use of artificial intelligence in the form of AI can facilitate the batik pattern recognition process. The use of AI in the field of digital image processing is very important in today's various applications. Deep learning, as part of AI, allows computers to learn to classify objects directly from images. This deep learning method utilizes CPU, RAM, and GPU to process large data computations quickly and efficiently. Convolutional Neural Network (CNN) is one of the most effective deep learning methods in digital image recognition. The ResNet architecture, which is a CNN architecture family developed by Google Research, is proven to have a high level of accuracy and better efficiency than other architectures. The Resnet model has a relatively smaller size and faster inference time, and is easily adapted for a variety of transfer learning tasks. In the context of this research, the implementation of the deep learning method uses CNN and the Resnet architecture to classify batik images. This research is expected to help identify the types of batik, which in turn can increase understanding and appreciation of Indonesian culture.

Item Type:	Article
Subjects:	A Computer Science > Computer Programming
Divisions:	Jurusan Teknologi Informasi > Teknik Informatika
Depositing User:	Rizal Whisnu Wiratama
Date Deposited:	14 Mar 2024 03:25
Last Modified:	14 Mar 2024 03:25
URI:	http://repota.jti.polinema.ac.id/id/eprint/901

Actions (login required)

View Item