Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer
Lukman
Researcher
Computer Science & IT

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

Found 1 Documents
Search

 1 
Klasifikasi Jenis Rempah-Rempah Menggunakan Metode Algoritma Convolutional Neural Network (CNN) Lukman; Farid Wajidi; Ismaun Rusman
BETRIK Vol. 16 No. 03 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/kczxhd54

Abstract

Spices play a crucial role in the lives of Indonesian people, where these ingredients are utilized as flavor enhancers, natural dyes, preservatives, and primary components in traditional medicine. Nevertheless, a significant portion of the population still encounters difficulties in distinguishing various types of spices due to morphological similarities between groups, as observed in ginger, turmeric, galangal, lesser galangal, Java ginger, and red ginger. This research is designed to classify these six types of spices using the Convolutional Neural Network (CNN) method. The dataset employed consists of 600 spice images, with each class comprising 100 images, subsequently divided into training data (80%) and testing data (20%). The research process encompasses dataset collection, the pre-processing stage involving resizing images to 46x46 pixels, data division, CNN model training, and performance evaluation through the confusion matrix. The results indicate that the CNN model successfully recognizes the ginger and red ginger classes with high accuracy, whereas in the classes of lesser galangal, turmeric, and Java ginger, classification errors persist due to visual similarities between spices. Overall, the CNN approach proves effective for spice classification, although further enhancements are required in specific classes to achieve more optimal and accurate outcomes.
Co-Authors Farid Wajidi Ismaun Rusman