Autors: Lazarova, M. K., Matov, P. I., Filipova-Petrakieva, S. K., Taralova I., Loiseau J.J.
Title: Apple Leaves Pathologies Detection with Hybrid ResNet and Machine Learning Models
Keywords: apple leaves pathologies, deep learning, machine learning, random forest, Residual neural network, support vectors

Abstract: Nowadays the need for smart agriculture is becoming more deeply embedded in our daily lives. Apple leaves diseases is a common concern in the agriculture sector. The current work presents an approach for classification of apple leaves. Two hybrid models based on residual network (ResNet) and utilizing machine learning methods (Support Vectors Machine and Random Forest) as a final classifier are proposed to improve the classification accuracy. ResNet model uses ResNet50 architecture. The hybrid models are trained on a dataset of 20453 images. Data augmentation technique is applied by use of a pseudo-random number generator to simulate a camera chaotic noise and different environmental factors as temperature fluctuations, ageing, smudging, damage. The results of the apple leaves diseases classification using the suggested hybrid models outperform the classification accuracy of base ResNet model.

References

  1. J. Ignizio, Introduction to expert systems, The development and implementation of rule-based expert systems, McGraw-Hill, 1999.
  2. D. Joy, K. Sreekumar, "A Survey on Expert System in Agriculture", Int. Journal of Computer Science and Information Technologies, vol. 5, no. 6, 2014, pp. 7861-7864.
  3. P. Chakraborty, D. Chakrabarti, "A Brief Survey of Computerized Expert Systems for Crop Protection Being Used in India", Progress in Natural Science, vol. 18, no. 4, 2008, pp. 469-473.
  4. J. Travis, R. Latin, "Development, Implementation, and Adoption of Expert Systems in Plant Pathology", Annual Review of Phytopathology, vol. 29, 1991, pp. 343-360.
  5. M. Saleem, J. Potgieter, and K. M. Arif, "Plant Disease Detection and Classification by Deep Learning", Plants, vol. 8, no. 11, 2019.
  6. S. Filipova-Petrakieva, P. Matov, M. Lazarova, I. Taralova, J. J. Loiseau, "Apple Tree Leaves Diseases Detection Using Residual Network", IEEE 10th International Congress on Information and Communication Technology, 19-21 February 2025, London, under publishing.
  7. D. Rani, K. Shyamala, "Depthwise Separable Convolution Architectures for the Identification of Leaf Diseases in Tomato Crop", International Journal of Creative Research Thoughts, vol. 11, no. 9 2019, pp. e40-e47.
  8. M. Turkoglu, D. Hanbay, and A. Sengur, "Multi-Model LSTM-Based Convolutional Neural Networks for Detection of Apple Diseases and Pests", Journal of Ambient Intelligence and Humanized Computing, vol. 13, pp. 3335-3345, 2022.
  9. S. Mohanty, D. Hughes, and M. Salathe, "Using Deep Learning for Image-Based Plant Disease Detection", Frontiers in Plant Science, vol. 7, 2016.
  10. A. Fuentes, S. Yoon, S. Kim, and D. Park, "A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition", Sensors, vol. 17, no. 9, 2017.
  11. Ch. Yang, I. Taralova, and J. J. Loiseau, "Impacts of the Numerical Calculation Methods on the Chaoticity of the Fractional Chaotic Systems", IFAC-PapersOnLine, vol. 55, no. 40, 2022, pp. 151-156.
  12. Plant Pathology 2020-FGVC7 https: //www. kaggle. com/c/%20plant-pathology-2020-fgvc7/data
  13. S. Filipova-Petrakieva, P. Matov, M. Lazarova, I. Taralova, and J. J. Loiseau, Apple Tree Leaves Diseases Detection Using Residual Network, IEEE 10th International Congress on Information and Communication Technology (ICICT'2025), 19-21 February 2025, London, UK.

Issue

60th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2025 - Proceedings, 2025, Albania, https://doi.org/10.1109/ICEST66328.2025.11098274

Copyright IEEE eXplore Digital Library

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus