Use of Augmentation Data and Hyperparameter Tuning in Batik Type Classification using the CNN Model

Abstract

Batik is one of Indonesia's most recognized artistic cultures in the world and has different motifs and types of traditional batik and each has its own uniqueness. But unfortunately, there are still so many Indonesian people who cannot distinguish the types of batik based on their motifs. That's why we need a way to help people easily be able to distinguish the types of batik based on their motifs. This research was conducted to classify types of batik based on their motifs using the Convolutional Neural Network deep learning model using Data Augmentation and Hyperparameter Tuning. CNN is included in the type of Deep Neural Network because of its high network depth and is widely applied to image data. Besides that, Data Augmentation and Hyperparameter Tuning are also applied to reduce overfitting. The results of this study show that the CNN model that uses Data Augmentation optimization and Hyperparameter Tuning gets a much higher accuracy, precision and recall value of 66.67% compared to the CNN mode that does not use Data Augmentation and Hyperparameter Tuning which has validation accuracy, precision , and recall of 28.15%. Besides that, among Data Augmentation and Hyperparameter Tuning, Data Augmentation is the one that most influences the increase in validation accuracy, precision, and recall compared to Hyperparameter Tuning with an increase in validation accuracy to 64% from a validation accuracy of 28.15%.