Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal SEMINAR NASIONAL PENELITIAN DAN PENGABDIAN KEPADA MASYARAKAT
Putri, Amanda Titania
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Law, Crime, Criminology & Criminal Justice Nursing

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Implementasi Deteksi Jenis Tanaman Herbal Dengan Model Klasifikasi Gambar Menggunakan Teachable Machine Putri, Amanda Titania; Safira, Ola; Yulianti, Amelia; Faozi, Imam; Setiawan, Retno Agus
Seminar Nasional Penelitian dan Pengabdian Kepada Masyarakat 2025 Prosiding Seminar Nasional Penelitian dan Pengabdian Kepada Masyarakat (SNPPKM 2025)
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/snppkm.v4i1.1373

Abstract

Herbal plants are a source of natural ingredients widely used in traditional medicine and alternative therapies. However, the process of identifying herbal plant types is still often done manually, potentially leading to errors, especially for the general public. The aim of this research is to implement an intelligent system capable of classifying herbal plant types based on leaf images, thereby helping to identify herbal plants independently while providing educational value. The research utilizes an image dataset of several types of herbal plant leaves that were processed and trained using Google Teachable Machine. This platform facilitates training machine learning models through an image-based approach without requiring complex programming knowledge. The dataset is divided into several classes according to the type of herbal plant, and the training process is carried out by varying parameters such as epoch, batch size, and learning rate to obtain the most optimal configuration. The results of this research create a web-based intelligent system application that can effectively classify herbal plant images, provide educational information to users, and can be further developed into a practical tool for herbal plant identification. The research also highlights several challenges, such as the need for a sufficiently large and diverse dataset, variations in lighting conditions and image backgrounds, and the model's ability to perform consistently under real-world conditions.
Co-Authors Faozi, Imam Safira, Ola Setiawan, Retno Agus Yulianti, Amelia