Classification of Banana Ripeness Using a VGG16-Based Convolutional Neural Network (CNN)

Authors

DOI:

https://doi.org/10.35194/mji.v17i2.5930

Keywords:

Computer Vision, Arsitektur VGG16, Convolutional Neural Network, Buah Pisang

Abstract

The ripeness level of bananas is a crucial factor that affects the quality, taste, and selling value of the commodity, but the manual sorting process that is commonly carried out is still subjective, inconsistent, and time-consuming. This study aims to implement and evaluate the performance of a VGG16-based Convolutional Neural Network (CNN) architecture in automatically classifying the ripeness level of bananas. The research dataset consists of 5,616 digital images obtained from the Roboflow Universe platform and grouped into six specific classes: freshripe, freshunripe, overripe, ripe, rotten, and unripe. The system development methodology includes data division using stratified splitting techniques, image pre-processing with data augmentation strategies to prevent overfitting, and the application of transfer learning. The model was trained using the Stochastic Gradient Descent (SGD) optimization algorithm with a learning rate of 0.001 for 25 epochs on GPU-based hardware. Performance evaluation was conducted in depth using a confusion matrix, F1-Score metrics, and Precision-Recall curve analysis. The experimental results showed that the VGG16 model achieved an overall accuracy of 97.13%. Class-by-class analysis shows perfect performance in the freshunripe category, although there is a slight decrease in precision in the ripe class due to the similarity of visual characteristics with the overripe class. The stability of the training and validation accuracy curves also indicates that the model has good generalization capabilities. This study concludes that the VGG16 architecture is a reliable and accurate solution to support the efficiency of smart farming systems.

References

[1] A. Hermawan, T. R. Effendi, and N. Fadillah, “Deteksi kematangan buah pisang berdasarakan kulit menggunakan metode multi-level thresholding dan ycbcr,” vol. 02, no. 02, pp. 105–108, 2021.
[2] F. Huda and M. P. K. Putra, “Klasifikasi jenis buah pisang menggunakan algoritma convolutional neural network,” vol. 1, no. 3, pp. 100–105, 2023.
[3] G. D. Cahyo, R. Helilintar, and I. N. Farida, “Pengolahan citra kematangan pisang menggunakan convolutional neural network vgg19,” INOTEK, vol. 9, pp. 1507–1515, 2025.
[4] M. R. Pratama and J. Aryanto, “Deteksi dan klasifikasi kematangan pisang menggunakan yolov8 dan model hibrida mobilenetv2 – knn,” vol. 9, no. 3, pp. 787–796, 2025, doi: 10.29408/edumatic.v9i3.32597.
[5] A. Rizky et al., “Perbandiangan vgg16 dan mobilenetv2 untuk klasifikasi tingkat kematangan buah apel,” pp. 30–39.
[6] S. Real-time and R. Artikel, “Implementasi algoritma yolov8 ( you only look once ) untuk deteksi jenis buah pisang,” vol. 15, pp. 9–17, 2026.
[7] I. Najiah, I. Hariyanti, A. R. Sanjaya, A. R. Sanjaya, K. P. Celak, and D. K. Pisang, “Deteksi jenis dan kematangan pisang menggunakan metode extreme learning,” vol. 2, no. 2, pp. 232–242, 2020.
[8] N. Sary, H. Handoko, S. Pasaribu, R. J. Situmeang, and R. Darmawan, “Implementasi algoritma yolov11 dan roboflow untuk deteksi tingkat kematangan anggur berbasis web,” pp. 264–274, 2025, doi: 10.47002/metik.v9i2.1121.
[9] D. Liandaputra and A. Zahra, “Klasifikasi tingkat kematangan buah nanas menggunakan metode deep learning,” vol. 8, no. 2, pp. 1091–1103, 2024.
[10] U. N. Putra et al., “Klasifikasi tingkat kematangan buah jeruk menggunakan arsitektur vgg16,” 2025.
[11] R. Suhendra, R. S. Ayu, R. S. Qaisa, I. Juliwardi, and N. Astrianda, “Penerapan cnn arsitektur vgg16 untuk deteksi kesegaran ikan berdasarkan citra digital,” pp. 19–25, 2025.
[12] A. I. Syirojuddin, A. A. Riadi, A. Susanto, U. M. Kudus, K. Kudus, and J. Tengah, “Klasifikasi tingkat kematangan parijoto berdasarkan karakteristik warna menggunakan algoritma k-nearest neighbor,” pp. 30–40, 2025.
[13] F. Tangguh and Y. Islami, “Analisis performa algoritma stochastic gradient descent ( sgd ) dalam mengklasifikasi tahu berformalin,” vol. 3, no. 1, pp. 1–8, 2022.
[14] M. Rijal, A. Muhammad Yani, and A. Rahman, “Deteksi citra daun untuk klasifikasi penyakit padi menggunakan pendekatan deep learningdengan model cnn,” vol. 10, no. 1, pp. 56–62, 2024.
[15] M. Kamil, T. Endra, and E. Tju, “Naïve bayes dan confusion matrix untuk efisiensi analisa intrusion detection system alert,” vol. 02, pp. 81–88, 2022.
[16] L. Lusiana, A. Wibowo, and K. Dewi, “Implementasi algoritma deep learning you only look once ( yolov5 ) untuk deteksi buah segar dan busuk,” vol. 11, no. 1, pp. 123–130, 2023.
[17] H. Jayadi and A. Nurul Fajar, “Klasifikasi pisang berbasis algoritma vgg16melalui metode cnn deep learning,” vol. 15, no. 1, pp. 1–17, 2023.
[18] A. I. Hanifah and A. Hermawan, “Klasifikasi kematangan pisang menggunakan metode convolutional neural network classification of banana fruit maturity levels using the convolutional neural network method,” vol. 12, no. 148, pp. 169–176, 2023, doi: 10.34010/komputika.v12i2.9999.
[19] D. Husen, “Evaluasi teknik augmentasi data untuk klasifikasi tumor otak menggunakan cnn pada citra mri,” pp. 219–228, 2024.
[20] R. Dzikri Fauzi and M. Fachrie, “Sistem prediksi tingkat kematangan buah tomat mengguanakan arsitektur vgg16,” vol. 5, no. 3, pp. 401–414, 2024, doi: 10.46576/djtechno.

Downloads

Published

2025-12-31