Hybrid Techniques in Mango Leaf Disease Identification: Evaluating Neural Networks and Support Vector Machines

Year : 2024 | Volume : 14 | Issue : 03 | Page : 19 27
    By

    Anshik Kushwah,

  • Dr. Mayank Pathak,

  1. M. Tech Scholar, Department of Computer Science and Engineering, Technocrats Institute of Technology, Anandnagar,Bhopal, Madhya Pradesh,, India
  2. Professor,, Department of Computer Science and Engineering, Technocrats Institute of Technology, Anandnagar,Bhopal,, Madhya Pradesh,, India

Abstract

Mango leaf diseases pose a significant threat to mango production, impacting both yield and fruit quality. Early and accurate detection of these diseases is crucial for effective management. This paper evaluates the use of hybrid techniques, specifically the integration of neural networks (NNs) and support vector machines (SVM), in the identification and classification of mango leaf diseases. NN excel in extracting complex features from images, while SVMs are robust classifiers, especially in handling non-linear separable data. The hybrid approach leverages the strengths of both models to achieve high accuracy and generalization. This study reviews various models, including ensemble stacked deep learning models, lightweight convolutional neural networks (CNN), and hybrid CNN-SVM approaches, and compares their effectiveness in detecting diseases like powdery mildew, Anthracnose, and others. Results demonstrate that hybrid models outperform traditional methods, achieving accuracy rates as high as 99.87%. However, challenges such as high computational costs, the need for region-specific datasets, and balancing model complexity with accuracy remain. The findings underscore the potential of hybrid models in enhancing disease detection systems, contributing to improved crop management and reduced losses in mango production.

Keywords: Mango Leaf Disease, Neural Networks, Support Vector Machines, Hybrid Models, Machine Learning, Deep Learning, Disease Detection, Agriculture, Image Processing.

[This article belongs to Trends in Opto-electro & Optical Communication ]

How to cite this article:
Anshik Kushwah, Dr. Mayank Pathak. Hybrid Techniques in Mango Leaf Disease Identification: Evaluating Neural Networks and Support Vector Machines. Trends in Opto-electro & Optical Communication. 2024; 14(03):19-27.
How to cite this URL:
Anshik Kushwah, Dr. Mayank Pathak. Hybrid Techniques in Mango Leaf Disease Identification: Evaluating Neural Networks and Support Vector Machines. Trends in Opto-electro & Optical Communication. 2024; 14(03):19-27. Available from: https://journals.stmjournals.com/toeoc/article=2024/view=183816


Browse Figures

References

  1. Asha Rani KP, Gowrishankar S. ConvNeXt-based mango leaf disease detection: Differentiating pathogens and pests for improved accuracy. Int J Adv Comput Sci Appl. 2023;14(6). doi: 10.14569/IJACSA.2023.0140608.
  2. Rizvee RA, Orpa TH, Ahnaf A, Kabir MA, Ahmmad Rashid MR, Islam MM, et al. LeafNet: A proficient convolutional neural network for detecting seven prominent mango leaf diseases. J Agric Food Res. 2023;14:100787. DOI: 10.1016/j.jafr.2023.100787.
  3. Sanath Rao US, Swathi R, Sanjana V, Arpitha L, Chandrasekhar K, Chinmayi PK, et al. Deep learning precision farming: Grapes and mango leaf disease detection by transfer learning. Glob Transit Proc. 2021;2:535–44. DOI: 10.1016/j.gltp.2021.08.002.
  4. Mia MR, Roy S, Das SK, Rahman MA. Mango leaf disease recognition using neural network and support vector machine. Iran J Comput Sci. 2020;3:185–93. DOI: 10.1007/s42044-020-00057-z.
  5. Tusher AN, Islam MT, Sammy MSR, Hasna SA, Chakraborty NR. Automatic recognition of plant leaf diseases using deep learning (multilayer CNN) and image processing. In: Chen JIZ, Tavares JMRS, Shi F, editors. Third International Conference on Image Processing and Capsule Networks. ICIPCN 2022. Lecture Notes in Networks and Systems. Cham: Springer; 2022. p. 130–42. doi: 10.1007/978-3-031-12413-6_11.
  6. Rizvee RA, Orpa TH, Ahnaf A, Kabir MA, Ahmmad Rashid MR, Islam MM, et al. LeafNet: A proficient convolutional neural network for detecting seven prominent mango leaf diseases. J Agric Food Res. 2023;14:100787. DOI: 10.1016/j.jafr.2023.100787.
  7. Thaseentaj S, Ilango SS. Deep convolutional neural networks for south Indian mango leaf disease detection and classification. Comput Mater Continua. 2023;77:3593–618. DOI: 10.32604/cmc.
    042496.
  8. Gautam V, Ranjan RK, Dahiya P, Kumar A. ESDNN: A novel ensembled stack deep neural network for mango leaf disease classification and detection. Multimed Tools Appl. 2024;83:10989–1015. DOI: 10.1007/s11042-023-16012-6.
  9. Hari P, Singh MP. A lightweight convolutional neural network for disease detection of fruit leaves. Neural Comput Appl. 2023;35:14855–66. DOI: 10.1007/s00521-023-08496-y.
  10. Jayanthi B, Kumar LS. Comparison of convolutional neural networks architectures for mango leaf classification. Int J Comput Vis Robot. 2024;14:84–98. DOI: 10.1504/IJCVR.2024.135131.
  11. Banerjee D, Kukreja V, Hariharan S, Jain V. Enhancing mango fruit disease severity assessment with CNN and SVM-based classification. In: IEEE 8th International Conference for Convergence in Technology (I2CT); 2023 Apr; Lonavla, India. p. 1–6. DOI: 10.1109/I2CT57861.2023.1012
  12. Mir TA, Banerjee D, Chauhan R, Singh M, Yamsani N. Forecasting anthracnose severity levels in mango leaf using hybrid models. In: IEEE 9th International Conference for Convergence in Technology (I2CT); 2024; Pune, India. p. 1–6. DOI: 10.1109/I2CT61223.2024.10543795.
  13. Varma T, Mate P, Azeem NA, Sharma S, Singh B. Automatic mango leaf disease detection using different transfer learning models. Multimed Tools Appl. 2024. DOI: 10.1007/s11042-024-19265-x.
  14. Vijay CP, Pushpalatha K. DV-PSO-Net: A novel deep mutual learning model with heuristic search using particle swarm optimization for mango leaf disease detection. J Integr Sci Technol. 2024;12:804. DOI: 10.62110/sciencein.jist.2024.v12.804.
  15. Deena G, Raja K, Azhagiri M, Breen WA, Prema S. Application of support vector classifier for mango leaf disease classification. Sci Temper. 2023;14:1163–9. DOI: 10.58414/SCIENTIFIC
    2023.14.4.16.
  16. Admass WS, Munaye YY, Bogale GA. Convolutional neural networks and histogram-oriented gradients: A hybrid approach for automatic mango disease detection and classification. Int J Inf Technol. 2024;16:817–29. DOI: 10.1007/s41870-023-01605-z.
  17. Bezabh YA, Ayalew AM, Abuhayi BM, Demlie TN, Awoke EA, Mengistu TE. Classification of mango disease using ensemble convolutional neural network. Smart Agric Technol. 2024;8:100476. DOI: 10.1016/j.atech.2024.100476.
  18. Pandiyaraju V, Venkatraman S, Abeshek A, Aravintakshan SA, Pavan Kumar S. Mango leaf disease detection and classification using spatial attention enabled ensemble classification. 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS); 2024; Chennai, India. p. 1–8. doi: 10.1109/ADICS58448.2024.10533513.
  19. Singh P, Singh P, Farooq U, Khurana SS, Verma JK, Kumar M. RETRACTED ARTICLE: CottonLeafNet: Cotton plant leaf disease detection using deep neural networks. Multimed Tools Appl. 2023;82:37151–76. DOI: 10.1007/s11042-023-14954-5.
  20. Sema W, Yayeh Y, Andualem G. Automatic detection and classification of mango disease using convolutional neural network and histogram oriented gradients. 2023. DOI: 10.21203/rs.3.rs-3073109/v1.
  21. Pathak AK, Saikia P, Dutta S, Sinha S, Ghosh S. Development of a robust CNN model for mango leaf disease detection and classification: A precision agriculture approach. ACS Agric Sci Technol. 2024;4(8):806–17. doi: 10.1021/acsagscitech.4c00122.
  22. Kumar S, Gupta B, Grover R, Chhabra M. Effective machine learning model for disease recognition and categorization of mango leaves. In: International Conference on Computational Intelligence and Computing Applications (ICCICA); 2024; Samalkha, India. p. 292–6. DOI: 10.1109/ICCICA
    2024.10585260.
Regular Issue Subscription Review Article
Volume 14
Issue 03
Received 17/10/2024
Accepted 22/10/2024
Published 18/11/2024
402

Login


My IP

PlumX Metrics