Home Technology 18 Using deep learning for image-based plant disease detection
Chapter
Licensed
Unlicensed Requires Authentication

18 Using deep learning for image-based plant disease detection

  • Punam Bedi , Pushkar Gole and Sumit Kumar Agarwal
Become an author with De Gruyter Brill
Explore this Subject How to publish with us
Internet of Things and Machine Learning in Agriculture
This chapter is in the book Internet of Things and Machine Learning in Agriculture

Abstract

Food is one of the basic needs of human life. The demand for food is increasing due to an exponential increase in the world’s population. To overcome such a massive demand for food, agricultural practitioners suggested the use of different insecticides and pesticides to increase the yield of the crops. The use of these insecticides and pesticides increases the yield of plants, but using these in large amounts can degrade the quality of the soil, which makes crops more prone to different diseases. These diseases can negatively affect the crop yield and reduce the profit of the farmers. If the farmers can sense the plant diseases in the initial stages, it is possible to take necessary actions to remedy the situation. However, detecting diseases in a large field of crops with naked eyes is a challenging task. Thus, to simplify this process, there is a need for a system for automatic detection of plant diseases. This system can be build using various artificial intelligence (AI) techniques. Deep learning is a class of algorithms in AI which is widely used in numerous domains nowadays. This chapter describes a solution to the problem of plant disease detection using deep learning techniques. This chapter includes an explanation about convolutional neural networks (CNNs), their fundamental building blocks, and the details of different modern CNN architectures such as LeNet-5 and AlexNet. A complete implementation of an automated disease detection system for peach plant using LeNet-5 architecture is also described. At the end of this chapter, an experimental analysis based on the train and the test accuracies of disease detection systems using different modern CNN architectures is presented. All these implementations use data from a very famous dataset named PlantVillage.

Abstract

Food is one of the basic needs of human life. The demand for food is increasing due to an exponential increase in the world’s population. To overcome such a massive demand for food, agricultural practitioners suggested the use of different insecticides and pesticides to increase the yield of the crops. The use of these insecticides and pesticides increases the yield of plants, but using these in large amounts can degrade the quality of the soil, which makes crops more prone to different diseases. These diseases can negatively affect the crop yield and reduce the profit of the farmers. If the farmers can sense the plant diseases in the initial stages, it is possible to take necessary actions to remedy the situation. However, detecting diseases in a large field of crops with naked eyes is a challenging task. Thus, to simplify this process, there is a need for a system for automatic detection of plant diseases. This system can be build using various artificial intelligence (AI) techniques. Deep learning is a class of algorithms in AI which is widely used in numerous domains nowadays. This chapter describes a solution to the problem of plant disease detection using deep learning techniques. This chapter includes an explanation about convolutional neural networks (CNNs), their fundamental building blocks, and the details of different modern CNN architectures such as LeNet-5 and AlexNet. A complete implementation of an automated disease detection system for peach plant using LeNet-5 architecture is also described. At the end of this chapter, an experimental analysis based on the train and the test accuracies of disease detection systems using different modern CNN architectures is presented. All these implementations use data from a very famous dataset named PlantVillage.

Chapters in this book

  1. Frontmatter I
  2. Preface VII
  3. Acknowledgments IX
  4. Contents XI
  5. List of contributors XIII
  6. Part I: Machine learning and Internet of things in agriculture
  7. 1 Smart farming: using IoT and machine learning techniques 3
  8. 2 Food security and farming through IoT and machine learning 21
  9. 3 An innovative combination for new agritechnological era 41
  10. 4 Recent advancements and challenges of artificial intelligence and IoT in agriculture 65
  11. 5 Technological impacts and challenges of advanced technologies in agriculture 83
  12. Part II: Applications of Internet of things in agriculture
  13. 6 IoT-based platform for smart farming – Kaa 109
  14. 7 Internet of things platform for smart farming 131
  15. 8 Internet of things platform for smart farming 159
  16. 9 Internet of things platform for smart farming 169
  17. Part III: Applications of machine learning in agriculture
  18. 10 Kisan-e-Mitra: a tool for soil quality analyzer and recommender system 205
  19. 11 Artificial intelligence for plant disease detection: past, present, and future 223
  20. 12 Wheat rust disease identification using deep learning 239
  21. 13 Image-based hibiscus plant disease detection using deep learning 251
  22. 14 Rainfall prediction by applying machine learning technique 275
  23. 15 Plant leaf disease classification based on feature selection and deep neural network 293
  24. 16 Using deep learning for image-based plant disease detection 323
  25. 17 Using deep learning for image-based plant disease detection 355
  26. 18 Using deep learning for image-based plant disease detection 369
  27. Index 403
https://doi.org/10.1515/9783110691276-018

Chapters in this book

  1. Frontmatter I
  2. Preface VII
  3. Acknowledgments IX
  4. Contents XI
  5. List of contributors XIII
  6. Part I: Machine learning and Internet of things in agriculture
  7. 1 Smart farming: using IoT and machine learning techniques 3
  8. 2 Food security and farming through IoT and machine learning 21
  9. 3 An innovative combination for new agritechnological era 41
  10. 4 Recent advancements and challenges of artificial intelligence and IoT in agriculture 65
  11. 5 Technological impacts and challenges of advanced technologies in agriculture 83
  12. Part II: Applications of Internet of things in agriculture
  13. 6 IoT-based platform for smart farming – Kaa 109
  14. 7 Internet of things platform for smart farming 131
  15. 8 Internet of things platform for smart farming 159
  16. 9 Internet of things platform for smart farming 169
  17. Part III: Applications of machine learning in agriculture
  18. 10 Kisan-e-Mitra: a tool for soil quality analyzer and recommender system 205
  19. 11 Artificial intelligence for plant disease detection: past, present, and future 223
  20. 12 Wheat rust disease identification using deep learning 239
  21. 13 Image-based hibiscus plant disease detection using deep learning 251
  22. 14 Rainfall prediction by applying machine learning technique 275
  23. 15 Plant leaf disease classification based on feature selection and deep neural network 293
  24. 16 Using deep learning for image-based plant disease detection 323
  25. 17 Using deep learning for image-based plant disease detection 355
  26. 18 Using deep learning for image-based plant disease detection 369
  27. Index 403
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2026 De Gruyter Brill
Downloaded on 23.2.2026 from https://www.degruyterbrill.com/document/doi/10.1515/9783110691276-018/html
Scroll to top button