Intro
Preface
Contents
About the Authors
Chapter 1: Introduction
1.1 Motivation
1.2 Prior Work About Agricultural Pest Recognition and Detection
1.2.1 Traditional Manual Methods
1.2.2 Research on Pest Recognition Method Based on Machine Learning Method
1.2.3 Pest Recognition and Detection Methods Based on Deep Learning Technology
1.2.3.1 Pest Recognition and Detection Based on Fixed Equipment
1.2.3.2 Research on Pest Recognition Based on Unmanned Aerial Vehicle Dataset
1.2.3.3 Research on Pest Identification on Mobile Terminal Device Dataset

1.2.4 Pest Datasets
1.2.5 Problems of Pest Detection
1.3 Plant Disease Detection Methods
1.3.1 Plant Disease Recognition Method Based on Traditional Machine Learning
1.3.2 Plant Disease Detection Method Based on Deep Learning Technology
1.3.2.1 Disease Recognition Methods
1.3.2.2 Disease Segmentation Methods
1.3.2.3 Disease Detection Methods
1.3.3 Plant Disease Dataset
1.3.4 Problems of Current Disease Detection Methods
1.4 Organization of the Book
References
Chapter 2: Deep Learning Technology
2.1 Neural Networks
2.1.1 Neurons and Neural Network Models

2.1.1.1 Neuron Model
2.1.1.2 Neural Network Model
2.1.2 Forward and Backward Propagation
2.1.2.1 Forward Propagation
2.1.2.2 Backward Propagation
2.1.2.3 Gradient Descent
2.1.3 Activation Function
2.1.3.1 Sigmoid Activation Function
2.1.3.2 Tanh Activation Function
2.1.3.3 ReLU Activation Function
2.1.4 Loss Function
2.1.4.1 Cross-Entropy Loss Function
2.1.4.2 Mean Squared Error Loss Function
2.1.4.3 Smooth L1 Loss Function
2.1.5 Optimizer
2.1.5.1 Momentum Stochastic Gradient Descent
2.2 Convolutional Neural Networks

2.2.1 Neural Networks and Image Processing
2.2.2 Convolutional Neural Network
2.2.3 Convolutional Layer
2.2.4 Pooling Layer
2.3 Image Recognition Technology
2.3.1 History of Image Recognition Technology
2.3.2 Image Recognition Based on Traditional Machine Learning
2.3.2.1 Image Preprocessing
Image Denoising
Image Enhancement
Image Segmentation
2.3.2.2 Traditional Image Feature Extraction
2.3.2.3 Classifiers Based on Traditional Machine Learning
KNN (K-Nearest Neighbor)
SVM (Support Vector Machines)

2.3.3 Image Recognition Based on Deep-Learning Technology
2.3.3.1 Naive Convolutional Neural Network: AlexNet and VGGNet
2.3.3.2 Wider Convolutional Neural Networks: GoogLeNet
2.3.3.3 Deeper Convolutional Neural Networks: ResNet, DenseNet
2.3.3.4 Light-Weight Convolutional Neural Network: MobileNet
2.3.4 Introduction to Image Recognition Based on Few-Shot Learning
2.4 Object Detection Methods Based on Deep Learning
2.4.1 Framework of Object Detection Networks
2.4.1.1 Feature Extraction Network (Backbone Network)
CNN-Based Backbones