Machine Learning Approach for Rhizomes Classification Based on Color
- https://doi.org/10.2991/aer.k.210810.057How to use a DOI?
- Rhizome, Machine Learning, Color
Rhizome plants are often used as ingredients or traditional ingredients such as temuireng, temulawak and temumangga. Such rhizomes have the same color, shape, and smell characteristics. In this study, the types of rhizomes were classified based on their color into three classes, namely temuireng, temulawak, and temumangga. The color of the rhizome was captured using the camera. The image feature extraction process was carried out to obtain the color characteristics of the image by calculating the RGB value of the image. The obtained values were classified using several machine learning methods, namely Decision Tree, Naive Bayes, and KNN. This study used 120 data for all classes with the ratio of training data and test data was 70% and 30% respectively. In the initial stages of classification, data cleaning was carried out, before training and test data were used to create a classification model. From the classification results, the accuracy value of each method was obtained and then the method with the best accuracy can be selected. Result showed that the optimal method for classifying three types of temulawak (temuireng, temulawak and temumangga) based on RGB color features was using the KNN method with an accuracy of 87.5% that similar to previous researcher who used SVM method.
- © 2021, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Bayu Agustian AU - Maimunah PY - 2021 DA - 2021/08/11 TI - Machine Learning Approach for Rhizomes Classification Based on Color BT - Proceedings of the 2nd Borobudur International Symposium on Science and Technology (BIS-STE 2020) PB - Atlantis Press SP - 330 EP - 335 SN - 2352-5401 UR - https://doi.org/10.2991/aer.k.210810.057 DO - https://doi.org/10.2991/aer.k.210810.057 ID - Agustian2021 ER -