Fine-Tuned MobileNetV2 for Multi-Fruit Ripeness Classification Using Deep Transfer Learning

DOI

10.2991/978-94-6239-664-7_54How to use a DOI?

Keywords

Fruit Ripeness Classification; Deep learning; Transfer Learning; MobileNetV2; Agricultural automation; Food quality control; Computer vision

Abstract

Accurate fruit ripeness detection plays a vital role in ensuring food quality, minimizing waste, and supporting automation in agriculture. This research investigates deep learning techniques for classifying the ripeness of three fruits—apples, bananas, and oranges—into fresh, unripe, and rotten categories. Four pre-trained convolutional neural network models—MobileNetV2, InceptionV3, ResNet50, and DenseNet121—were applied to both individual fruit datasets and a combined dataset. All models performed exceptionally well on single-fruit classification, with MobileNetV2 achieving perfect accuracy. When evaluated on the combined dataset, MobileNetV2 maintained strong performance with 97% accuracy, which further improved to 99% after fine-tuning. The finetuning process involved freezing the base model, training 75 layers, and adding a global average pooling layer, dropout, early stopping, and a learning rate scheduler. These results demonstrate the effectiveness of a lightweight, fine-tuned CNN model for robust and high-accuracy fruit ripeness classification, making it suitable for real-world deployment.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Md. Shazedur Rahman
AU  - Rofidul Hasan Ovik
AU  - Sadman Sadik Khan
AU  - A. K. M. Bahalul Haque
AU  - Sudipta Das Gupta
AU  - Md Nyem Hasan Bhuiyan
PY  - 2026
DA  - 2026/06/08
TI  - Fine-Tuned MobileNetV2 for Multi-Fruit Ripeness Classification Using Deep Transfer Learning
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 786
EP  - 798
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_54
DO  - 10.2991/978-94-6239-664-7_54
ID  - Rahman2026
ER  -