Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal ULTIMA Computing
Hanes, Natanael
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Engineering

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

Found 1 Documents
Search

 1 
Convolutional Neural Network Roasted Coffee Bean Classification Based on Color Hanes, Natanael; Wulandari, Meirista; Setyaningsih, Endah
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4351

Abstract

Coffee quality is significantly influenced by the roasting level, which is commonly determined by the color of the beans. Traditional classification methods rely on manual sorting and human judgment, making the process labor-intensive, subjective, and prone to error. To address these limitations, this project proposes a deep learning-based coffee bean classification system using Convolutional Neural Networks (CNNs). CNNs, known for their strong performance in image recognition, can analyze visual features like color, texture, and shape to automatically classify coffee beans based on roast level. The system is evaluated using metrics such as accuracy, precision, recall, and F1 score. Among the tested input sizes, the CNN model performs best at 64×64 pixels, achieving a peak accuracy of 99% with minimal misclassifications. This result highlights the model’s effectiveness in delivering high classification performance while maintaining computational efficiency, even with low-resolution images.
Co-Authors Endah Setyaningsih Meirista Wulandari, Meirista