Image Classification On Garutan Batik Using Convolutional Neural Network with Data Augmentation

Abstract

In Indonesia, Batik is one of the cultural assets in the field of textiles with various styles. There are many types of batik in Indonesia, one of which is Batik Garutan. Batik Garutan has different motifs that show the characteristics of Batik Garutan itself. Therefore, to distinguish the features of Batik Garutan from another batik, a system is needed to classify the types of batik patterns. Classification of batik patterns can be done using image classification. In image classification, there are methods to increase the size and quality of the limited training dataset by performing data augmentation. This study aims to obtain an image classification model by applying data augmentation. The image classification process is carried out using the Deep Learning method with the Convolutional Neural Network algorithm, which is expected to be helpful as a reference for research and can be applied to software development related to image classification. This study generated models from several experiments with different epoch parameters and dataset proportions. A system obtained the investigation with the best performance with a data proportion of 9:1, resulting in an accuracy value of 91 percent.

Image Classification of Room Tidiness Using VGGNet with Data Augmentation

“…The fourth study addressed detection in image classification for diabetic retinopathy using a Neural Network with VGGNet-16 architecture, resulting in an accuracy of 93.73% [13]. The fifth study conducted image classification for Garutan batik using CNN and data augmentation, resulting in the highest accuracy of 91.30% with the ResNet-50 architecture [14]. The last study discussed medical image classification for disease diagnosis using a Convolutional Neural Network with VGGNet architecture and achieved an accuracy of 92.3% [15].…”