Machine Learning for Ripeness Classification of Nendra Bale Banana: A Classical Approach Using SVM, kNN, and Random Forest

References

[1] FAO, FAOSTAT — Crops and Livestock Products: Bananas. Rome: Food and Agriculture Organization of the United Nations, 2024.

[2] National Horticulture Board, Indian Horticulture Database — Banana Production Statistics. Ministry of Agriculture, Govt. of India, 2023.

[3] E. Almeyda and W. Ipanaqué, “Recent developments in post-harvest handling and shelf-life assessment of bananas: a review,” Sci. Hortic., vol. 305, pp. 111–123, 2022.

[4] J. Hou, Y. Hu, L. Hou, K. Guo, and T. Satake, “Classification of ripening stages of bananas based on support vector machine,” Int. J. Agric. Biol. Eng., vol. 8, no. 6, pp. 99–103, 2015.

[5] N. Saranya, K. Srinivasan, and S. K. Pravin Kumar, “Banana ripeness stage identification using deep learning,” J. Ambient Intell. Humaniz. Comput., vol. 13, pp. 4033–4039, 2022.

[6] Y. Gulzar, “Fruit image classification model based on MobileNetV2 with deep transfer learning,” Sustainability, vol. 15, no. 3, art. 1906, 2023.

[7] P. Baglat, A. Hayat, F. Mendonça, A. Gupta, S. S. Mostafa, and F. Morgado-Dias, “Non-destructive banana ripeness detection using shallow and deep learning: a systematic review,” Sensors, vol. 23, no. 2, art. 738, 2023.

[8] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in IEEE CVPR, 2005, pp. 886–893.

[9] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.

[10] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.

[11] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: inverted residuals and linear bottlenecks,” in IEEE CVPR, 2018, pp. 4510–4520.

[12] F. Pedregosa et al., “Scikit-learn: machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.

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

[14] O. Martínez-Mora, O. Capuñay-Uceda, L. Caucha-Morales, R. Sánchez-Ancajima, I. Ramírez-Morales, S. Córdova-Márquez, and F. Cuenca-Mayorga, “Artificial vision-based dual CNN classification of banana ripeness and quality attributes using RGB images,” Processes, vol. 13, no. 4, art. 1142, 2025.

[15] M. Shinga, Y. Silué, and O. Fawole, “Machine learning-based prediction of firmness in coated bananas under retail conditions,” Postharvest Biol. Technol., vol. 220, art. 113276, 2025.

[16] T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Inf. Theory, vol. 13, no. 1, pp. 21–27, 1967.

@article{1723730,
      author = {Manasa T. N., M. P. Pushpalatha},
      title = {Machine Learning for Ripeness Classification of Nendra Bale Banana: A Classical Approach Using SVM, kNN, and Random Forest},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {4},
      pages = {648-655},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1723730.pdf},
      abstract = {acceptance, and overall shelf life. Nendra Bale (Nendran), a dual-purpose, starch-rich Indian banana cultivar widely used for both table consumption and cooking, exhibits a ripening pattern that is markedly more texture-driven than colour-driven, distinguishing it from commercially dominant, colour-dominant cultivars. This study introduces an image-based framework for classifying the ripening stage of Nendra Bale bananas using classical machine learning. A first-hand dataset of 80 raw images across four ripening stages (Green, Mid-ripe, All-Yellow, Overripe) was collected under everyday mobile-camera conditions and augmented to 5,391 images to support more robust model training. Three classical classifiers (Support Vector Machine, k-Nearest Neighbours, Random Forest) were evaluated on Histogram of Oriented Gradients (HOG) features under both raw and augmented conditions. On the raw dataset, kNN gave the highest accuracy (76.47%), ahead of SVM and Random Forest (70.59% each); once the dataset was augmented, SVM became the strongest and most consistent model (81.60%), ahead of kNN (78.62%) and Random Forest (74.53%). A probabilistic stage-to-shelf-life mapping is proposed to convert predictions into an expected remaining life in days. The study offers a low-cost, non-destructive, deployable approach for quality assessment and post-harvest decision support for a texture-dominant, dual-purpose Indian banana cultivar.},
      keywords = {banana ripeness classification, Nendra Bale, Random Forest, SVM, k-Nearest Neighbours},
      month = {October},
      doi = {https://doi.org/10.64388/IREV10I4-1723730}
  }