Automated Detection of Mango Diseases and Pesticide Residue using Hybrid Deep Learning Approaches
Keywords:
Deep learning, Mango disease detection, MobileNetV2, Pesticide residue, Precision agriculture, Support Vector Machine (SVM), Transfer learningAbstract
Mangoes, commonly known as the fruit king, play an important role in agriculture globally. Nevertheless, their quality is often impaired due to fungal contamination and the excessive use of pesticides. Manual examination traditionally requires substantial effort due to its reliance on human judgment, which can be inconsistent and prone to error. This work introduces an automatic mechanism designed to simultaneously recognize major mango diseases, such as anthracnose and black mold rot, and to detect pesticide residues on the fruit surface. The proposed hybrid system uses MobileNetV2 for deep feature extraction along with a Support Vector Machine (SVM) for classification. Empirical findings indicate superior performance compared to traditional CNN models, achieving 98% accuracy for pesticide detection and 94% for disease classification. A lightweight web tool enables farmers and buyers to perform instant quality assessments through an intuitive interface.
References
S. Espinoza, C. Aguilera, L. Rojas and P. G. Campos, “Analysis of fruit images with deep learning: A systematic literature review and future directions,” in IEEE Access, vol. 12, pp. 3837–3859, 2024, doi: https://doi.org/10.1109/ACCESS.2023.3345789
M. M. Islam et al., “A two-stage model for enhanced mango leaf disease detection using an innovative handcrafted spatial feature extraction method and knowledge distillation process,” Ecological Informatics, vol. 91, pp. 103365–103365, Nov. 2025, doi: https://doi.org/10.1016/j.ecoinf.2025.103365
H. B. Patel and N. J. Patil, “Enhanced CNN for fruit disease detection and grading classification using SSDAE-SVM for postharvest fruits,” in IEEE Sensors Journal, vol. 24, no. 5, pp. 6719–6732, Mar. 2024, doi: https://doi.org/10.1109/JSEN.2023.3342833
J. Lu, X. Liu, X. Ma, J. Tong, and J. Peng, “Improved MobileNetV2 crop disease identification model for intelligent agriculture,” PeerJ. Computer science, Sep. 2023, doi: https://doi.org/10.7717/peerj-cs.1595
V. Yamaçli and M. K. Yildirim, “Plant disease detection by using Mobilentv2 and Xception on filtered and enhanced images,” Engineering and Technology Journal, vol. 9, no. 1, pp. 3266–3270, Jan. 2024, doi: https://everant.org/index.php/etj/article/view/1143
M. Zheltyakova, A. Korotkov, R. Masharipov, A. Myznikov, M. Didur, Denis Cherednichenko et al., “Social interaction with an anonymous opponent requires increased involvement of the theory of mind neural system: An fMRI study,” Frontiers in Behavioral Neuroscience, vol. 16, May 2022, doi: https://doi.org/10.3389/fnbeh.2022.807599
V. Boppana, S. Davuluri, R. Reddi, N. Syda, MVP U. Rao, A. Kasukurthi et al., “Plant disease detection using hybrid MobileNetV2- Compact CNN architecture with LIME integration,” Journal of Information Systems Engineering & Management, vol. 10, no. 13s, pp. 554–568, Feb. 2025, doi: https://doi.org/10.52783/jisem.v10i13s.2111
T. Thorat, B. K. Patle, M. Wakchaure, and L. Parihar, “Advancements in techniques used for identification of pesticide residue on crops,” Journal of Natural Pesticide Research, vol. 4, Jun. 2023, doi: https://doi.org/10.1016/j.napere.2023.100031
S. Duhan, P. Gulia, N. S. Gill, and E. Narwal, “RTR_Lite_MobileNetV2: A lightweight and efficient model for plant disease detection and classification,” Current Plant Biology, vol. 42, Jun. 2025, doi: https://doi.org/10.1016/j.cpb.2025.100459
U. Das, N. S. Baruah, B. Das, and R. Borgohain, “Detection of diseases in fruits using image processing techniques,” ADBU Journal of Electrical and Electronics Engineering, vol. 5, no. 2, pp. 7–17, Sep. 2023.
J. Jhansi, M. S. Jyothi, M. Siddipriya, S. Imamshavali, S. D. G. Shajiya, and S. M. Inus, “IOT and ML based pesticide residue detection in fruits and vegetables,” International Journal of Scientific Research in Science and Technology, vol. 11, no. 11, pp. 702–710, Apr. 2024, doi: https://doi.org/10.32628/ijsrst
L. Kujur, V. Gupta, and A. Singhal, “A hybrid multi-optimizer approach using CNN and GB for accurate prediction of citrus fruit diseases,” Discover Applied Sciences, vol. 7, Feb. 2025, doi: https://doi.org/10.1007/s42452-025-06593-2
M. A. Jahin, S. Shahriar, M. F. Mridha, Md. J. Hossen, Md. J. Hossen, and N. Dey, “Soybean disease detection via interpretable hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with cross-modal attention,” arXiv.org, May 2025, doi: https://doi.org/10.48550/arXiv.2503.01284
J. Ahmmed, F. Ahmed, R. H. Shohan, M. M. Rana, M. Hasan, “Fine-tuned CNN-based approach for multi-class mango leaf disease detection,” arXiv.org, Oct. 2022. doi: https://doi.org/10.48550/arXiv.2510.05326
K. Saddami, Y. Nurdin, M. Zahramita, M. S. Safiruz, “Advancing green AI: Efficient and accurate lightweight CNNs for rice leaf disease identification,” arXiv.org, Aug. 2023, doi: https://doi.org/10.48550/arXiv.2408.01752
Z. Huang, Z. Jiang, Z. Zheng, X. Zhang, X. Wei, J. Chen et al., “Methyl 3,4-dihydroxybenzoate inhibits RANKL-induced osteoclastogenesis via Nrf2 signaling in vitro and suppresses LPS-induced osteolysis and ovariectomy-induced osteoporosis in vivo,” Acta Biochim Biophys Sin, vol. 54, no. 8, pp. 1068–1079, Aug. 2022, doi: https://doi.org/10.3724/abbs.2022087
