KLASIFIKASI TANAMAN OBAT-OBATAN BERDASARKAN CITRA DAUN DENGAN MENGGUNAKAN JARINGAN SYARAF TIRUAN
DOI:
https://doi.org/10.24114/jmk.v6i3.22217Keywords:
Gray Level Co-occurance Matrix (GLCM), Shape Morphology, Backpropagation, Medicinal Leaf Image.Abstract
Herbal medicines are an alternative to health efforts for Indonesian people. The number of types of medicinal plants in Indonesia makes it difficult for some people to recognize the types of plants. Therefore, a system that can help identify the type of medicinal plant is needed. The system is processing the image of a plant that is taken to recognize its structural characteristics, so as to produce an output in the form of a recognizable type of plant. This study aims to determine the characteristics of the texture and shape morphology from medicinal plants leaves so that it can be used to detect and recognize the type of leaves. This study uses 10 types of medicinal plant leaves. The system design that is built using Gray Level Co-occurance Matrix (GLCM) feature extraction and shape morphology feature extraction with Backpropagation Artificial Neural Network classifier that is able to train the system before being applied to test the image of the leaf to be recognized. Based on the introduction testing on the all image, the image can be identified by type and yield recognition accuracy is 83.5% with the highest accuracy results produced by Jarak and Mengkudu, and the lowest recognition rate produced by sirih. ABSTRAK Obat-obatan herbal merupakan alternatif dalam upaya kesehatan bagi masyarakat Indonesia. Banyaknya aneka ragam jenis tanaman obat di Indonesia membuat sebagian masyarakat sulit untuk mengenali jenis-jenis tanaman yang ada. Oleh karena itu, diperlukan suatu sistem yang dapat membantu mengenali jenis tanaman obat. Sistem tersebut merupakan pengolahan citra tanaman yang diambil untuk dikenali karakteristik strukturalnya sehingga menghasilkan keluaran berupa tanaman dapat dikenali jenisnya. Penelitian ini bertujuan untuk mengetahui karakterikstik tekstur, morfologi bentuk daun tanaman obat sehingga dapat digunakan untuk mendeteksi dan mengenali jenis daun. Penelitian ini menggunakan 10 jenis daun tanaman obat-obatan. Perancangan sistem yang dibangun menggunakan ekstraksi fitur tekstur Gray Level Co-occurance Matrix (GLCM) dan ekstraksi fitur morfologi bentuk dengan classifier Jaringan Syaraf Tiruan Backpropagation yang mampu melatih sistem sebelum diterapkan untuk melakukan pengujian terhadap citra daun yang akan dikenali jenisnya. Berdasarkan pengujian pengenalan pada keseluruhan citra, citra dapat dikenali jenisnya dan menghasilkan tingkat akurasi pengenalan sebesar 83,5% dengan hasil akurasi tertinggi dihasilkan oleh daun jarak dan mengkudu sebesar 100%, serta tingkat pengenalan terendah dihasilkan oleh daun sirih sebesar 60%.References
Andono, P. N., Sutojo, T., dan Muljono (2017): Pengolahan Citra Digital, Penerbit Andi, Yogyakarta.
Badieah, Gernowo, R., dan Surarso, B., (2016): Metode Jaringan Syaraf Tiruan Untuk Prediksi Performa Mahasiswa Pada Pembelajaran Berbasis Problem Based Learning (PBL), Jurnal Sistem Informasi Bisnis, 6, 46-58.
Chaki, J., dan Parekh, R., (2011): Plant Recognition using Shape based Features and Neural Network Classifier, International Journal of Advanced Computer Science and Applications (LIACSA), 2(10), 41-47.
Jabal, M. F. A., Hamid, S., Shuib, S., dan Ahmad, I., (2011): Leaf Features Extraction and Recognition Approaches to Classify Plant, Journal of Computer Science, 9(10), 1295-1304.
Kadir, A., Nugroho, L. E., Susanto, A., dan Santoso, P. I., (2011): Leaf Classifiation Using Shape, Color, and Texture Features, International Journal of Computer Science, 225-230.
Kadir, A., dan Susanto A., (2013): Teori dan Aplikasi Pengolahan CItra Digital, Penerbit Andi, Yogyakarta.
Siang, J. J., (2005): Jaringan Syaraf Tiruan dan Pemrogramannya Menggunakan Matlab, Penerbit Andi, Yogyakarta.
Downloads
Published
Issue
Section
License
Copyright (c) 2020 KARISMATIKA: Kumpulan Artikel Ilmiah, Informatika, Statistik, Matematika dan Aplikasi

This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Penulis.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).