15 Plant leaf disease classification based on feature selection and deep neural network
-
Tan Pham Nhat
Abstract
Today, deep learning (DL) has transformed many major industries. Agriculture is one such field where DL scientists and researchers are working with farmers to help them utilize the shrinking resources due to urbanization. However, plant disease, especially crop plants, is a major threat to the global food security. Many types of disease directly affect the quality of the fruits, grains, and so on leading to the decrease of agricultural productivity. The conventional method of identifying plant disease is through direct observation by naked eyes. This process is unreliable and subjected to human errors. In recent years, several works on DL techniques for leaf disease identification have been proposed. Most of them built their models based on limited resolution images on convolutional neural networks (CNNs). In this chapter, we want to focus on early disease recognition, which requires higher resolution images. After a preprocessing step using a contrast enhancement method, all the diseased blobs are segmented for the whole dataset. A list of several measurement- based features that represents the blobs are selected based on principle component analysis. The features are used as inputs for a standard feed-forward neural network. Our results show competitive classification results not only with other DL models such as CNNs but also with a simpler network structure.
Abstract
Today, deep learning (DL) has transformed many major industries. Agriculture is one such field where DL scientists and researchers are working with farmers to help them utilize the shrinking resources due to urbanization. However, plant disease, especially crop plants, is a major threat to the global food security. Many types of disease directly affect the quality of the fruits, grains, and so on leading to the decrease of agricultural productivity. The conventional method of identifying plant disease is through direct observation by naked eyes. This process is unreliable and subjected to human errors. In recent years, several works on DL techniques for leaf disease identification have been proposed. Most of them built their models based on limited resolution images on convolutional neural networks (CNNs). In this chapter, we want to focus on early disease recognition, which requires higher resolution images. After a preprocessing step using a contrast enhancement method, all the diseased blobs are segmented for the whole dataset. A list of several measurement- based features that represents the blobs are selected based on principle component analysis. The features are used as inputs for a standard feed-forward neural network. Our results show competitive classification results not only with other DL models such as CNNs but also with a simpler network structure.
Chapters in this book
- Frontmatter I
- Preface VII
- Acknowledgments IX
- Contents XI
- List of contributors XIII
-
Part I: Machine learning and Internet of things in agriculture
- 1 Smart farming: using IoT and machine learning techniques 3
- 2 Food security and farming through IoT and machine learning 21
- 3 An innovative combination for new agritechnological era 41
- 4 Recent advancements and challenges of artificial intelligence and IoT in agriculture 65
- 5 Technological impacts and challenges of advanced technologies in agriculture 83
-
Part II: Applications of Internet of things in agriculture
- 6 IoT-based platform for smart farming – Kaa 109
- 7 Internet of things platform for smart farming 131
- 8 Internet of things platform for smart farming 159
- 9 Internet of things platform for smart farming 169
-
Part III: Applications of machine learning in agriculture
- 10 Kisan-e-Mitra: a tool for soil quality analyzer and recommender system 205
- 11 Artificial intelligence for plant disease detection: past, present, and future 223
- 12 Wheat rust disease identification using deep learning 239
- 13 Image-based hibiscus plant disease detection using deep learning 251
- 14 Rainfall prediction by applying machine learning technique 275
- 15 Plant leaf disease classification based on feature selection and deep neural network 293
- 16 Using deep learning for image-based plant disease detection 323
- 17 Using deep learning for image-based plant disease detection 355
- 18 Using deep learning for image-based plant disease detection 369
- Index 403
Chapters in this book
- Frontmatter I
- Preface VII
- Acknowledgments IX
- Contents XI
- List of contributors XIII
-
Part I: Machine learning and Internet of things in agriculture
- 1 Smart farming: using IoT and machine learning techniques 3
- 2 Food security and farming through IoT and machine learning 21
- 3 An innovative combination for new agritechnological era 41
- 4 Recent advancements and challenges of artificial intelligence and IoT in agriculture 65
- 5 Technological impacts and challenges of advanced technologies in agriculture 83
-
Part II: Applications of Internet of things in agriculture
- 6 IoT-based platform for smart farming – Kaa 109
- 7 Internet of things platform for smart farming 131
- 8 Internet of things platform for smart farming 159
- 9 Internet of things platform for smart farming 169
-
Part III: Applications of machine learning in agriculture
- 10 Kisan-e-Mitra: a tool for soil quality analyzer and recommender system 205
- 11 Artificial intelligence for plant disease detection: past, present, and future 223
- 12 Wheat rust disease identification using deep learning 239
- 13 Image-based hibiscus plant disease detection using deep learning 251
- 14 Rainfall prediction by applying machine learning technique 275
- 15 Plant leaf disease classification based on feature selection and deep neural network 293
- 16 Using deep learning for image-based plant disease detection 323
- 17 Using deep learning for image-based plant disease detection 355
- 18 Using deep learning for image-based plant disease detection 369
- Index 403
