Identifikasi Citra Daun Tanaman Herbal menggunakan Convolutional Neural Network

  • Marselinus Putu Harry Setyawan Universitas Udayana
  • I Dewa Made Bayu Atmaja Darmawan Universitas Udayana

Abstract

Indonesia is one of the countries with the highest number of herbal plant species in the world. However, it is not linear with people's knowledge about herbal plants and their health benefits. Leaves are one of the characteristics of plants that can be used to identify plant species because each plant has leaves and is easier to distinguish than tree bark. This research uses the Local Binary Pattern (LBP) method to obtain the texture features of leaf herbal plants, and the Convolutional Neural Network (CNN) to perform the classification. The highest accuracy was obtained with an epoch value of 25 and a batch size of 32. This combination resulted in a model with an accuracy of 95%, and when tested with validation data it produced an accuracy of 84%. Overall, the model that was built was able to identify the types of herbal plants very well.

Published
2022-11-25
How to Cite
SETYAWAN, Marselinus Putu Harry; DARMAWAN, I Dewa Made Bayu Atmaja. Identifikasi Citra Daun Tanaman Herbal menggunakan Convolutional Neural Network. Jurnal Nasional Teknologi Informasi dan Aplikasinya (JNATIA), [S.l.], v. 1, n. 1, p. 337-346, nov. 2022. Available at: <https://ojs.unud.ac.id/index.php/jnatia/article/view/92699>. Date accessed: 26 jan. 2023.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.