<![CDATA[This research aims to develop a system for the detection and recognition of traditional Indonesian batik patterns using Convolutional Neural Network (CNN) method based on the Android platform, utilizing TensorFlow Lite as the framework. The research is motivated by the importance of preserving and promoting the cultural heritage of batik patterns, which represent the distinctive and treasured cultural identity of Indonesia. The methodology involves training a CNN model using a dataset consisting of 500 images of various batik patterns from 10 different types of batik. The dataset is divided into training and testing data in an 80:20 ratio. The results of the research indicate that the developed model for the detection and classification of batik patterns achieves high accuracy, with a training data accuracy of 92.25% and a testing data accuracy of 94%. In conclusion, the research demonstrates that the developed model is capable of accurately recognizing and detecting various traditional batik patterns. The research has practical benefits for the public, as it enhances knowledge and understanding of different batik patterns. Furthermore, the research contributes to the advancement of knowledge and the researcher's proficiency in implementing the CNN method for real-time detection of batik patterns.]]>
Copyrights © 2023
