Pattern Recognition of Batik Madura Using Backpropagation Algorithm

DOI

10.2991/acsr.k.220202.044How to use a DOI?

Keywords

Batik; Backpropagation; Gray level co-occurrence matrix; Neural network

Abstract

Since October 2, 2009, UNESCO has acknowledged batik as one of Indonesia’s intellectual properties. Throughout the archipelago, distinct and diverse batik motifs have emerged and been produced with the passage of time; Madura batik is one of them. The Backpropagation Algorithm is used to recognize Madura Batik Patterns in this research. Bunga Satompok, Manuk Poter, Pecah Beling, Rumput Laut, and Sekar Jagat are the motifs used in this study. To begin, resize the image to 200 × 200 pixels and convert it to a grayscale image. The Gray Level Co-occurrence Matrix (GLCM) approach is used to extract image features, and the Backpropagation Algorithm is used to recognize them. With GLCM, the angle orientations utilized in the feature extraction process are 0, 45, 90, and 135 degrees. There are 1, 3, and 5 hidden layers used throughout the training process, with hidden neurons in each layer of 8, 16, and 32. The highest accuracy is achieved when five hidden layers with 32 hidden neurons and one hidden layer with 32 hidden neurons in each layer are used in the testing process, which is 98 percent.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Abduh Riski
AU  - Ega Bandawa Winata
AU  - Ahmad Kamsyakawuni
PY  - 2022
DA  - 2022/02/08
TI  - Pattern Recognition of Batik Madura Using Backpropagation Algorithm
BT  - Proceedings of the  International Conference on Mathematics, Geometry, Statistics, and Computation (IC-MaGeStiC 2021)
PB  - Atlantis Press
SP  - 238
EP  - 243
SN  - 2352-538X
UR  - https://doi.org/10.2991/acsr.k.220202.044
DO  - 10.2991/acsr.k.220202.044
ID  - Riski2022
ER  -