Computer Vision and Machine Learning in Agriculture, Volume 3 (Algorithms for Intelligent Systems)

✍ Scribed by Jagdish Chand Bansal (editor), Mohammad Shorif Uddin (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 215
• Category: Library

✦ Synopsis

This book is as an extension of the previous two volumes on “Computer Vision and Machine Learning in Agriculture”. This volume 3 discusses solutions to the problems of agricultural production by rendering advanced machine learning including deep learning tools and techniques. The book contains 13 chapters that focus on in-depth research outputs in precision agriculture, crop farming, horticulture, floriculture, vertical farming, animal husbandry, disease detection, plant recognition, production yield, product quality, defect assessment, and overall automation through robots and drones. The topics covered in the current volume, along with the previous volumes, are comprehensive literature for both beginners and experienced in this domain.

✦ Table of Contents

Preface
Contents
About the Editors
1 Computer Vision and Machine Learning in Agriculture: An Introduction
1 Introduction
2 Application Areas of CV-ML in Agriculture
2.1 Quality Analysis of Seed
2.2 Analysis of Soil
2.3 Precision Irrigation
2.4 Weed Management
2.5 Crop Monitoring
2.6 Livestock Monitoring
2.7 Food Safety
2.8 Yield Estimation
2.9 Supply Chain Management
2.10 Climate Change Adaptation
3 CV-ML in Agriculture (Vol 1 and Vol 2)
4 CV-ML in Agriculture Vol 3
5 Conclusion
References
2 Deep Learning Modeling for Gourd Species Recognition Using VGG-16
1 Introduction
2 Description of Gourd Species
2.1 Sponge Gourd
2.2 Snake Gourd
2.3 Ridge Gourd
3 Literature Review
4 Methodology
4.1 Dataset Preparation
4.2 Preprocessing
4.3 VGG-16 Deployment
4.4 Dense Architecture
5 Experimental Evaluation
5.1 Accuracy
5.2 Precision
5.3 Recall
5.4 F1-Score
6 Analysis of Results
7 System Architecture
8 Conclusion
References
3 Sugarcane Diseases Identification and Detection via Machine Learning
1 Introduction
2 Literature Review
3 Data Summary and Preprocessing
4 Methodology
5 Result
6 Conclusion
References
4 Freshness Identification of Fruits Through the Development of a Dataset
1 Introduction
2 Literature Review
3 Methodology
3.1 Recognition Procedure
3.2 System Architecture
3.3 Data Collection Procedure
3.4 Pre-trained Deep Neural Networks
4 Experimental Results
4.1 Dataset
4.2 Performance Analysis
5 Conclusion
References
5 Rice Leaf Disease Classification Using Deep Learning with Fusion Concept
1 Introduction
2 Literature Survey
3 Dataset Used
4 Typical Deep Learning Architecture
4.1 Fusion Methods
4.2 Data Pre-processing
4.3 Feature Extraction
4.4 Machine Learning Classifiers
5 Experiment and Results
6 Conclusion and Future Scope
References
6 Advances in Deep Learning-Based Technologies in Rice Crop Management
1 Introduction
2 DL-Based Rice Crop Management System
2.1 Rice CNN Models
2.2 Rice Transformers
3 Applications of DL in Rice Crop Management
3.1 Rice Development Stage Analysis
3.2 Rice Disease and Disorder Diagnosis
3.3 Rice Variety Identification
4 Challenges and Future Scopes
5 Conclusion
References
7 AI-Based Agriculture Recommendation System for Farmers
1 Introduction
2 Literature Survey
3 System Design and Architecture
4 Recommendation System for Farmers
4.1 Crop Recommendation System
4.2 Leaf Disease Detection System
4.3 Fertilizer Recommendation System
4.4 Chatbot for Farmers
4.5 Web Application for Farmers
5 Results
6 Conclusion and Future Work
References
8 A New Methodology to Detect Plant Disease Using Reprojected Multispectral Images from RGB Colour Space
1 Introduction
2 Literature Review
3 Data Set
4 Model Architecture
5 Result
6 Conclusion
References
9 Analysis of the Performance of YOLO Models for Tomato Plant Diseases Identification
1 Introduction
2 Literature Review
3 Methodology
3.1 Experimental Environment
3.2 Data Set
3.3 Training, Test and Validation
3.4 Performance Matrix
4 Result
5 Conclusion
References
10 Strawberries Maturity Level Detection Using Convolutional Neural Network (CNN) and Ensemble Method
1 Introduction
2 Materials and Methods
2.1 Acquisition of Image Dataset and Pre-processing
2.2 CNN-Based Detection and Classification
2.3 Comparison Criteria
2.4 Evaluation Matrices
3 Results and Discussion
3.1 Comparison of the Individual CNN Models and Ensemble Models
4 Conclusion
References
11 RGB to Multispectral Remap: A Cost-Effective Novel Approach to Recognize and Segment Plant Disease
1 Introduction
2 Literature Review
3 Dataset
4 Model
5 Result
6 Conclusion
References
12 An Intelligent Vision-Guided Framework of the Unmanned Aerial System for Precision Agriculture
1 Introduction
2 Material and Method
2.1 Sensors
2.2 Target Recognition System
2.3 Main System
2.4 Autopilot Drive System
3 Experimentation and Results
3.1 Experimental Scenario
3.2 Simulation Experiment
4 Discussion
5 Conclusion
References
13 Leveraging Computer Vision for Precision Viticulture
1 Introduction
2 Typical Viticulture Logbook
2.1 Basic Practices
3 Towards Computer Vision-Based Automated Logbook
3.1 Computer Vision-Based Practices
4 Computer Vision-Based Subtasks
4.1 Detection of Vine Parts
4.2 Structural Elements Detection
4.3 Supplementary Detection Subtasks
5 Discussion
6 Conclusions
References
Author Index