Authors : D. R. Solanke; Mahendra Makesar; Rajesh Bhoyar; Suhas Pachpande

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/394z3y2j

Scribd : https://tinyurl.com/bp6rdm8h

DOI : https://doi.org/10.38124/ijisrt/26jun487

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Automated fruit grading using deep learning offers an efficient alternative to manual inspection in precision agriculture. This study presents the implementation and comparative evaluation of convolutional neural network (CNN) architectures for Citrus lemon fruit image classification. Transfer learning models, including popular pre trained CNN models, together with a custom sequential CNN, were trained and assessed using accuracy, categorical cross entropy loss, ROC analysis, and precision/recall metrics. Experimental results indicate that EfficientNet achieved the highest testing accuracy of 98.46% with the lowest loss (0.038), followed by DenseNet (97.88%) and the sequential CNN (97.07%). The model demonstrated strong discrimination capability with a true positive rate of 0.968, false positive rate of 0.0073, and an AUC of 0.9806. Class wise evaluation produced balanced precision, recall, and F1 scores of 0.98. The findings confirm that efficient deep CNN architectures provide reliable and scalable solutions for automated lemon quality classification.

Keywords : Citrus Lemon Classification, Convolutional Neural Networks, Deep Learning, Fruit Quality Assessment, Transfer Learning.

References :

1. K. D. M. Sundaram, T. Shankar, and N. S. Reddy, “A novel fuzzy pooling based modified ThinNet architecture for lemon fruit classification,” Journal of Intelligent and Fuzzy Systems, vol. 43, no. 5, pp. 6877–6891, 2022.
2. Avuçlu, E., & Şenol, B. (2023). “Classification of Lemon Quality Using the Residual Convolutional Neural Network Deep Learning Model”, International Conference on Innovative Academic Studies, 3(1), 762–766, 2023
3. N. Undu, S. Sonam, G. Rani, and V. S. Dhaka, “A deep learning based system for automatic sorting and quality grading of citrus fruits,” pp. 1–5, 2024.
4. Y. Fu et al., “Circular fruit and vegetable classification based on optimized GoogLeNet,” IEEE Access, vol. 9, pp. 113599–113611, 2021.
5. Y. F. N. Ashfani, Y. Litanianda, and R. A. Putri, “Classification of Citrus Fruit Types Using Convolutional Neural Network Method: A Deep Learning Study” Uranus Journal Ilmiah  Teknik Electro, vol. 2, no. 2, pp. 70–79, 2024.
6. T. A. Omotoso et al., “Development of optimized convolutional neural network for infected citrus fruit detection and classification,” Lautech Journal of Engineering and Technology, vol. 19, no. 3, pp. 112–121, 2025.
7. R. Sharma and V. K. Kukreja, “Amalgamated convolutional long term network (CLTN) model for lemon citrus canker disease multi classification,” pp. 326–329, 2022.
8. K. Roy et al., “Classification of citrus fruits and prediction of their largest producer based on deep learning architectures,” in Proc. Springer, Singapore, pp. 147–155, 2021.
9. R. S. Latha et al., “Automatic fruit detection system using multilayer deep convolution neural network,” in Proc. Int. Conf. Computer Communication and Informatics, 2021.
10. A. K. Saini, R. Bhatnagar, and D. K. Srivastava, “Citrus fruits diseases detection and classification using transfer learningIn Proceedings of the International Conference on Data Science, Machine Learning and Artificial Intelligence (DSMLAI '21'). Association for Computing Machinery, 277–283, 2021
11. S. T. Meti and G. Veena, “Fruit CNN: A fruit classification and quality assessment system using two stack ensemble method,” pp. 1–6, 2024.
12. Y. F. Wijaya and D. Hindarto, “Advancing fruit image classification with state of the art deep learning techniques,” Sinkron: Jurnal dan Penelitian Teknik Informatika, 2024.
13. G. Singh, K. Guleria, and S. Sharma, “Advanced fruit sorting: Pre trained ResNet50 model for rotten and fresh fruit classification,” pp. 1–5, 2024.
14. L. Alzubaidi et al., “A deep convolutional neural network model for multi class fruits classification,” in Proc. Springer, Cham, pp. 90–99, 2019.
15. H. Naidu et al., “A fast and efficient convolutional neural network for fruit recognition and classification,” in Proc. Springer, Singapore, pp. 148–157, 2020.
16. X. Chen et al., “The fruit classification algorithm based on the multi optimization convolutional neural network,” Multimedia Tools and Applications, vol. 80, no. 7, pp. 11313–11330, 2021.
17. T. Arshad et al., “Fruit classification through deep learning: A convolutional neural network approach,” in Proc. Springer, Singapore, pp. 2671–2677, 2019.
18. U. Amin et al., “Automatic fruits freshness classification using CNN and transfer learning,” Applied Sciences, vol. 13, no. 14, p. 8087, 2023.
19. R. G. Raut et al., “Classification of fruits using convolutional neural networks,” pp. 1–4, 2022.
20. Nachiket C. Patel, Prem H. Laddha, Ravi S. Kumar, Yogi S. Patel, “Fruit recognition and feature extraction of fruits using deep learning,” Int. J. Advanced Research in Science, Communication and Technology, pp. 274–278, 2022.
21. D. M. Bongulwar, “Fruit recognition using deep learning approach,” Research Developments in Science and Technology, Vol. 6 (pp.46 52), 2022.
22. D. M. Bongulwar, “Identification of fruits using deep learning approach,” IOP Conf. Series, vol. 1049, p. 012004, 2021.
23. S. Lu et al., “Fruit classification based on six layer convolutional neural network,” in Proc. Int. Conf. Digital Signal Processing, pp. 1–5, 2018.
24. S. Dümen et al., “Performance of vision transformer and Swin transformer models for lemon quality classification in fruit juice factories,” Zeitschrift für Lebensmittel Untersuchung und  Forschung, 2024.
25. “DenseNet 201 and Xception pre trained deep learning models for fruit recognition,” Electronics, 2023.
26. A. Mohite et al., “Deep learning based fruit recognition and quality assessment: A convolutional neural network approach,” pp. 589–593, 2024.
27. K. Sangeetha et al., “Classification of fruits and its quality prediction using deep learning,” pp. 342–346, 2024.
28. Z. Huang, “A CNN based implementation of fruit recognition,” Highlights in Science Engineering and Technology, 2024.
29. R. Raut, A. Jadhav, C. Sorte and A. Chaudhari “Classification of fruits using convolutional neural networks,” in Proc. ICAECT, 2022.
30. A. Kumar et al., “Fruit CNN: An efficient deep learning based fruit classification and quality assessment for precision agriculture”, 13th International Congress on Ultra-Modern Telecommunications and Control Systems and Workshops (ICUMT), 2021
31. S. K. Behera et al., “ResNet101 SVM: Hybrid convolutional neural network for citrus fruits classification,” Journal of Intelligent and Fuzzy Systems, vol. 46, pp. 7035–7045, 2024.
32. M. Afroj et al., “LightNN: An optimized deep learning framework for enhanced fruit classification,” pp. 1–6, 2024.
33. Y. N. Yu et al., “Citrus pest identification model based on improved ShuffleNet,” Applied Sciences, 2024.
34. Gill, Harmandeep & Khehra, Baljit, “Fruit image classification using deep learning,”, Computers, Materials & Continua, 71(3), 5135 5150, 2022.