<![CDATA[The research on tile classification using Convolutional Neural Network (CNN) aims to improve and address issues in the sorting process within the tile manufacturing industry. The accuracy level in manual sorting processes is very low due to errors caused by visual limitations and physical fatigue. By leveraging the capabilities of Convolutional Neural Network (CNN), a model was developed to classify tiles. This research involved several processes, including literature review, dataset collection, dataset splitting, preprocessing, Convolutional Neural Network (CNN) design, training, testing, and result evaluation. The study used 69 tile images divided into three classes: KW 1, KW 2, and KW 3. The results of testing the Convolutional Neural Network (CNN) on tile classification using 100 epochs with a data split of 90% training and 10% validation yielded an accuracy rate of 100%.]]>
Copyrights © 2025
