Sistem Cerdas Berbasis Image Processing dan deep learning untuk Deteksi Lapisan Lilin pada Permukaan Buah

##plugins.themes.academic_pro.article.main##

Ande Suganda
Nuri David Maria Veronika

Abstract

Grapes are among the most perishable agricultural commodities. To improve shelf life and visual appeal, artificial wax coatings are often applied to their surface. However, these coatings may pose health risks if not properly detected. This study aims to develop an intelligent system based on image processing and deep learning to automatically and non-destructively detect the presence of wax coatings on apples. The dataset consists of a total of 312 apple images, collected using smartphone and digital cameras and expanded through data augmentation to increase variation and training volume. Classification was carried out using a Convolutional Neural Network architecture with input images resized to 150x150 pixels and trained for 20 epochs using the ImageDataGenerator library. The resulting model achieved a training accuracy of up to 99.36% and a validation accuracy of 100%. Testing confirmed that the system can effectively distinguish between waxed and unwaxed apple surfaces by recognizing differences in texture and light reflection. This system shows strong potential for implementation in automated post-harvest quality control within agricultural industries.

##plugins.themes.academic_pro.article.details##

How to Cite
Suganda, A. and Maria Veronika, N. D. (2025) “Sistem Cerdas Berbasis Image Processing dan deep learning untuk Deteksi Lapisan Lilin pada Permukaan Buah”, Ranah Research : Journal of Multidisciplinary Research and Development, 7(5), pp. 3636-3642. doi: 10.38035/rrj.v7i5.1642.

References

Enzelin, L. O. (2024). Digital Innovation and Rapid Application Development: A New Approach to Staff and Lecturer Recruitment at University. Journal of Information Systems and Informatics, Vol 6 No 1, 153–169.
Gao, X., Li, S., Su, X., Li, Y., Huang, L., Tang, W., et al. (2024). Application of Advanced Deep Learning Models for Efficient Apple Defect Detection and Quality Grading in Agricultural Production. Agriculture, Volume 14, Issue 7, Article 1098.
Lavanya, A. L. (2023). Assessing the Performance of Python Data Visualization Libraries: A Review. Journal of Computer Engineering In Research Trends, 10(1), 29–39.
Lv, M. X.-X.-H.-H. (2025). A Comprehensive Review of Deep Learning in Computer Vision for Monitoring Apple Tree Growth and Fruit Production. Sensors, Volume: 25, Edisi: 8, Nomor Artikel: 2433.
Meier, M. &. (2024). Agile R&D units’ organisation and its relationship with innovation performance. R&D Management.
Ningrum, M. K. (2023, Oktober 29). Dampak Buruk Lapisan Lilin pada Buah Anggur ketika Dikonsumsi, Begini Cara Tepat Menghilangkannya. Dipetik Mei 2025, 6, dari Tempo.Co: https://www.tempo.co/gaya-hidup/dampak-buruk-lapisan-lilin-pada-buah-anggur-ketika-dikonsumsi-begini-cara-tepat-menghilangkannya-127254
Rana, R. (2024). Agile Future Creation Methodology: Innovation Method for Startups to Build Future-Proof Solutions. Journal of Entrepreneurial Researchers, 2(1), 70–87.
Singh, P. S. (2022). Survey: Tensorflow in Machine Learning. ResearchGate.