Multi-label classification of banana using convolutional neural networks

(1) Rafa Nafisah Mail (Universitas Ahmad Dahlan, Indonesia)
(2) Pham Thi Quoc Thuyet Mail (Institute of Research and Development, Taisei Rotec Corporation, 1456, Kamiya Kounosu City, Saitama 365-0027, Japan)
(3) * Adhi Prahara Mail (Universitas Ahmad Dahlan, Indonesia)
*corresponding author


Indonesia which has large varieties of bananas becomes one of the centers of banana diversity. Most types of bananas in Indonesia share similar appearances and textures. These characteristics can be challenging for automatic vision tasks. The majority of the previous research only performed a single classification task, either types or ripeness of bananas. This may not be sufficient because the market price of bananas is determined by the type and ripeness level of bananas. Therefore, a multi-label classification is required to help people accurately identify banana types and their ripeness levels.

This research proposed a multi-label classification of bananas using a Convolutional Neural Network (CNN). The proposed method uses pre-trained models of CNN such as VGG16 and MobileNetV2. Transfer learning and fine-tuning are used in the training process of both models to find the best result. The proposed model classifies bananas into 8 types such as ambon, kepok, horn, lady finger, barangan, cavendish, jackfruit, and plantains, and 2 ripeness levels which are ripe and unripe.

The performance of the two models was compared and the results show that VGG16 and MobileNetV2-based models achieved 79% and 82% accuracy respectively. The comparison of these two models suggests that MobileNetV2 outperformed VGG16 in a multi-label classification of bananas.


Multi-label Classification, Banana classification, Transfer learning, CNN



Article metrics

10.29099/ijair.v8i1.1023 Abstract views : 130





M. Nansamba, J. Sibiya, R. Tumuhimbise, D. Karamura, J. Kubiriba, and E. Karamura, “Breeding banana (Musa spp.) for drought tolerance: A review,†Plant Breed., vol. 139, no. 4, pp. 685–696, 2020.

I. W. L. Lewa and others, “Banana Ripeness Analysis Using Reflectance and Photoluminescence,†in 2019 IEEE R10 Humanitarian Technology Conference (R10-HTC)(47129), 2019, pp. 248–253.

M. A. Z. Abd Samad and A. Nazari, “Banana Fruit Classification using Convolutional Neural Network,†Evol. Electr. Electron. Eng., vol. 3, no. 2, pp. 1059–1122, 2022.

A. F. Al-Daour, M. O. Al-Shawwa, and S. S. Abu-Naser, “Banana classification using deep learning,†Int. J. Acad. Inf. Syst. Res., vol. 3, no. 12, 2020.

R. C. Ucat and J. C. Dela Cruz, “Postharvest grading classification of cavendish banana using deep learning and tensorflow,†in 2019 International symposium on multimedia and communication technology (ISMAC), 2019, pp. 1–6.

A. R. Mesa and J. Y. Chiang, “Multi-input deep learning model with RGB and hyperspectral imaging for banana grading,†Agriculture, vol. 11, no. 8, p. 687, 2021.

S. Arwatchananukul, R. Saengrayap, S. Chaiwong, and N. Aunsri, “Fast and Efficient Cavendish Banana Grade Classification using Random Forest Classifier with Synthetic Minority Oversampling Technique.,†IAENG Int. J. Comput. Sci., vol. 49, no. 1, 2022.

S. Ganguli et al., “Deep Learning Based Dual Channel Banana Grading System Using Convolution Neural Network,†J. Food Qual., vol. 2022, 2022.

E. Dhaniswara, Y. Kristian, and E. I. Setiawan, “Detection of Banana and Its Ripeness Using Residual Neural Network,†J. INFORMATICS Telecommun. Eng., vol. 5, no. 1, pp. 188–197, 2021.

R. E. Saragih and A. W. R. Emanuel, “Banana ripeness classification based on deep learning using convolutional neural network,†in 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), 2021, pp. 85–89.

M. F. Mohamedon, F. Abd Rahman, S. Y. Mohamad, and O. O. Khalifa, “Banana ripeness classification using computer vision-based mobile application,†in 2021 8th International Conference on Computer and Communication Engineering (ICCCE), 2021, pp. 335–338.

T. Shuprajhaa, M. Raj, K. N. Sheeba, K. Dhayalini, and others, “Deep learning based mobile application for varietal identification and ripeness grading of traditional Indian banana varieties,†in 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), 2023, pp. 1–6.

F. M. A. Mazen and A. A. Nashat, “Ripeness classification of bananas using an artificial neural network,†Arab. J. Sci. Eng., vol. 44, pp. 6901–6910, 2019.

N. Saranya, K. Srinivasan, and S. K. P. Kumar, “Banana ripeness stage identification: a deep learning approach,†J. Ambient Intell. Humaniz. Comput., vol. 13, no. 8, pp. 4033–4039, 2022.

B. Malabag, C. Santiago Jr, E. Cahapin, J. Reyes, and G. Legaspi, “Fuzzy Logic-Based Size and Ripeness Classification of Banana using Image Processing Technique,†Int. J. Emerg. Technol. Adv. Eng., vol. 12, pp. 11–18, 2022.

A. I. Thoriq, M. H. Zuhri, P. Purwanto, P. Pujiono, and H. A. Santoso, “Classification of banana maturity levels based on skin image with HSI color space transformation features using the K-NN Method,†J. Dev. Res., vol. 6, no. 1, pp. 11–15, 2022.

N. Saranya, K. Srinivasan, and S. K. Pravin Kumar, “FBCNN-TSA: An optimal deep learning model for banana ripening stages classification,†J. Intell. & Fuzzy Syst., no. Preprint, pp. 1–17, 2023.

S. Anatya, V. C. Mawardi, and J. Hendryli, “Fruit maturity classification using convolutional neural networks method,†in IOP Conference Series: Materials Science and Engineering, 2020, vol. 1007, no. 1, p. 12149.

F. B. Setiawan, C. B. Adipradana, and L. H. Pratomo, “Fruit Ripeness Classification System Using Convolutional Neural Network (CNN) Method,†PROtek J. Ilm. Tek. Elektro, vol. 10, no. 1, pp. 46–51, 2023.

Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: analysis, applications, and prospects,†IEEE Trans. neural networks Learn. Syst., 2021.

D. Indira, J. Goddu, B. Indraja, V. M. L. Challa, and B. Manasa, “A review on fruit recognition and feature evaluation using CNN,†Mater. Today Proc., vol. 80, pp. 3438–3443, 2023.

M. Heydarian, T. E. Doyle, and R. Samavi, “MLCM: Multi-label confusion matrix,†IEEE Access, vol. 10, pp. 19083–19095, 2022.

J. Bogatinovski, L. Todorovski, S. Džeroski, and D. Kocev, “Comprehensive comparative study of multi-label classification methods,†Expert Syst. Appl., vol. 203, p. 117215, 2022.

Z.-F. He, M. Yang, H.-D. Liu, and L. Wang, “Calibrated multi-label classification with label correlations,†Neural Process. Lett., vol. 50, pp. 1361–1380, 2019.

A. N. Tarekegn, M. Giacobini, and K. Michalak, “A review of methods for imbalanced multi-label classification,†Pattern Recognit., vol. 118, p. 107965, 2021.

“Banana Dataset,†2020.

K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,†in 3rd International Conference on Learning Representations, {ICLR} 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Sep. 2015, Accessed: Oct. 07, 2019. [Online]. Available:

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,†in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.

O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,†Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, Dec. 2015, doi: 10.1007/s11263-015-0816-y.

T. Team, “Tensorflow,†2022. (accessed Nov. 30, 2022).

Tensorflow, “Transfer Learning and Fine-Tuning,†2023. (accessed Apr. 11, 2023)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.


The International Journal of Artificial Intelligence Research

Organized by: Departemen Teknik Informatika
Published by: STMIK Dharma Wacana
Jl. Kenanga No.03 Mulyojati 16C Metro Barat Kota Metro Lampung
phone. +62725-7850671
Fax. +62725-7850671


View IJAIR Statcounter

Creative Commons License
This work is licensed under  Creative Commons Attribution-ShareAlike 4.0 International License.