Improving the Accuracy of Batik Classification using Deep Convolutional Auto Encoder

This research investigates the development of model deep convolutional autoencoders to enhance the classification of digital batik images. The dataset used was sourced from Kaggle. The autoencoder was employed to enrich the image data prior to convolutional processing. By forcing the autoencoder to learn a lower-dimensional latent representation that captures the most salient features of the batik patterns. The performance of this enhanced model was compared against a standard convolutional neural network (CNN) without the autoencoder. Experimental results demonstrate that the incorporation of the autoencoder significantly improved the classification accuracy, achieving 99% accuracy on the testing data and loss value of 3.4%. This study highlights the potential of deep convolutional autoencoders as a powerful tool for augmenting image data and improving the performance of deep learning models in the context of batik image classification.