Advanced Sensing in Image Processing and IoT

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Editors
Contributors
Chapter 1 Machine Learning–Based Early Fire Detection System Using a Low-Cost Drone
1.1 Introduction
1.1.1 Motivation
1.2 Materials and Methods
1.2.1 Software Design
1.3 Results
1.4 Conclusions
Acknowledgments
Conflicts of Interest
References
Chapter 2 Computer Vision: Practical Approach to Facial Detection Techniques for Security Applications
2.1 Introduction
2.2 Facial Detection
2.3 Facial Detection Techniques
2.3.1 Haar Cascade Classifier
2.3.2 MMOD Face Detector
2.3.3 HOG Face Detector
2.3.4 MTCNN Face Detector
2.3.5 DNN Face Detector
2.4 Results and comparative analysis
2.4.1 Count of Detected Faces and Their Time Analysis
2.4.2 Confusion Matrix
2.4.3 Other Evaluation Parameters
2.4.4 Comparative Analysis
2.5 Conclusion
References
Chapter 3 Image Segmentation: Classification and Implementation Techniques
3.1 Introduction
3.2 How Image Segmentation Works
3.3 Applications of Digital Image Processing
3.3.1 Image Sharpening and Restoration
3.3.2 Medical Field
3.3.2.1 Ultraviolet Imaging
3.3.2.2 Transmission and Encoding
3.3.2.3 Machine/Robot Vision
3.3.2.4 Obstacle Detection
3.3.2.5 Line Follower Robot
3.3.2.6 Color Processing
3.3.2.7 Pattern Recognition
3.3.2.8 Video Processing
3.4 Requirement for Image Segmentation
3.4.1 Face Recognition
3.4.2 Number Plate Identification
3.4.3 Image-Based Search
3.4.4 Medical Imaging
3.5 Types of Image Segmentation
3.5.1 Approach-Based Classification
3.5.1.1 Region-Based Approach (Similarity Detection)
3.5.1.2 Boundary-Based Approach (Discontinuity Detection)
3.5.2 Technique-Based Classification
3.5.2.1 Structural Techniques
3.5.2.2 Stochastic Techniques
3.5.2.3 Combined/Hybrid Techniques
3.6 Image Segmentation Techniques
3.6.1 Thresholding Segmentation
3.6.1.1 Simple Thresholding
3.6.1.2 Otsu’s Binarization
3.6.1.3 Adaptive Thresholding
3.6.2 Edge-Based Segmentation
3.6.2.1 Search-Based Edge Detection
3.6.2.2 Zero Crossing–Based Edge Detection
3.6.3 Region-Based Segmentation
3.6.3.1 Region Growing
3.6.3.2 Region Splitting and Merging
3.6.4 Watershed Segmentation
3.6.5 Clustering-Based Segmentation Algorithms
3.6.5.1 K-Means Clustering
3.6.5.2 Fuzzy C Means
3.6.6 Neural Networks for Segmentation
3.7 Implementation and Pre-Requisites
3.8 Future Scope
3.9 Conclusion
References
Chapter 4 Image Processing with IoT for Patient Monitoring
4.1 Introduction
4.2 IoT in the Medical Domain
4.2.1 Data Communication between Different Layers in IoT
4.2.1.1 Internet of Healthcare Things (IoHT) Network Layer
4.2.1.2 Fog Computing Layer
4.2.1.3 Communication Interface
4.2.1.4 Cloud Layer
4.3 Application Areas of Medical IoT
4.3.1 Patient Monitoring and Tracking
4.3.2 IoT for Big Data
4.3.3 IoT Wearable Devices
4.3.4 Emergency Services
4.3.5 Smart Computing
4.3.6 Smart Nodes
4.4 Image Processing in Medical IoT
4.4.1 Remote Patient Monitoring
4.4.2 Preventive Care and Monitoring
4.4.3 Clinical Monitoring
4.4.4 Medical Service Organization
4.4.5 Different Applications Equipped with Image Processing
4.4.5.1 Proposed System
4.4.5.2 System Description
4.4.5.3 Communication System
4.4.5.4 Disease Recognition
4.4.5.5 Image Acquisition and Pre-Processing
4.4.5.6 Image Segmentation
4.4.5.7 Feature Extraction
4.4.5.8 Advantages of Proposed Application
4.4.5.9 Challenges of Application
4.5 Benefits and Limitations of IoT
4.6 Future Scope
4.7 Conclusion
References
Chapter 5 Theory, Practical Concepts, Strategies and Methods for Emotion Recognition
5.1 Introduction
5.1.1 Human Behavior and Emotions
5.2 Emotion Recognition and Its Types
5.2.1 Types of Emotion Recognition
5.2.2 Literature Review
5.3 Technologies Used In Emotion Recognition:
5.3.1 Image Processing
5.3.1.1 Benefits of Image Processing
5.3.2 OpenCV
5.3.3 Python
5.3.4 Deep Learning and Convolutional Neural Networks
5.4 Methodology
5.4.1 Hands on Approach of Emotion Recognition with CNN
5.4.1.1 Data Source
5.4.1.2 Preprocessing
5.4.1.3 Convolutional Neural Network (CNN) Setup
5.4.1.4 Model Training
5.4.2 Emotion Recognition Using DeepFace Framework
5.4.2.1 Hands on for Installation of DeepFace
5.4.2.2 Functions Used in DeepFace
4.4.2.3 Current Uses
5.5 Applications
5.5.1 Drawbacks
5.6 Test Results
5.6.1 Emotion Recognition Using DeepFace Result
5.6.2 Emotion Recognition Using Convolutional Neural Network
Bibliography
Chapter 6 A Comparative Study of Convolutional Neural Networks for Plant Phenology Recognition
6.1 Introduction
6.2 Related Works
6.3 Background
6.3.1 Deep Learning
6.3.1.1 Deep Learning Usage in Crop Production
6.3.1.2 Various Methods in Plant Subject Area
6.3.2 Convolutional Neural Networks
6.3.2.1 2-D CNNs
6.3.2.2 3-DCNNs
6.3.2.3 Methods of Regularization
6.4 CNN Performance
6.4.1 Comparing CNN with Other Methods
6.4.2 Generalized Productivity
6.5 Materials and Methods
6.5.1 Convolutional Neural Network Models
6.5.2 Datasets of Training and Testing
6.6 Results and Discussion
6.7 Conclusion
References
Chapter 7 IoT and Wearable Sensors for Health Monitoring
7.1 Introduction
7.2 Covid-19: Importance of Wearable Sensing Technology
7.3 Sensors and Types of Sensors
7.3.1 Types of Sensors Used in Wearable Technology
7.3.1.1 Accelerometer
7.3.1.2 Gyroscopes
7.3.1.3 Magnetometers
7.3.1.4 Global Positioning System (GPS)
7.3.1.5 Heart Rate Sensors
7.3.1.6 Pedometers
7.3.1.7 Pressure Sensors
7.3.1.8 Integration of Sensors into Wearables (Microcontroller)
7.4 Internet of Things
7.4.1 Network of the IoT
7.4.2 IoT-Based Wearable Healthcare System
7.5 Future Perspective
7.6 Conclusion
References
Chapter 8 Analysis of Interpolation-Based Image In-Painting Approaches
8.1 Introduction
8.2 Literature Review and Background
8.2.1 Cubic Interpolation
8.2.2 Kriging Interpolation
8.2.3 Radial Basis Functions
8.2.4 High-Dimensional Model Representation and Lagrange Interpolation
8.3 Materials and Methods
8.3.1 Materials
8.3.2 Method
8.3.2.1 Two-Dimensional Cubic Interpolation
8.3.2.2 Kriging Interpolation
8.3.2.3 Interpolation with Radial-Based Functions
8.3.2.4 Interpolation Using High-Dimensional Model Representation
8.4 Results
8.5 Conclusion
References
Chapter 9 Real Time Density–Based Traffic Congestion Detection System Using Image Processing and Fuzzy Logic Controller
9.1 Introduction
9.2 Related Work
9.3 Proposed System Model
9.3.1 Moving Vehicle Detection and Counting System
9.3.2 Parameter Extraction Using SUMO Simulator
9.3.3 Key Features Extraction using Fuzzy C-Means Clustering
9.3.4 Traffic Congestion Level Estimation Using Fuzzy Logic Controller
9.4 Experimental Analysis and Results
9.5 Conclusion
References
Annexure 9.1
Annexure 9.2
Annexure 9.3
Algorithm: Fuzzy C-means clustering [28,29]
Chapter 10 Fundamentals of Face Recognition with IoT
10.1 Introduction
10.2 Process of Face Recognition
10.2.1 Fundamentals of Face Recognition Steps
10.2.1.1 Face Detection
10.2.1.2 Pre-Processing Image
10.2.1.3 Feature Extraction
10.2.1.4 Optimal Feature Selection and Reduction
10.2.1.5 Classification
10.3 System Architecture of IoT and Face Application
10.4 Table of Comparison
10.5 Challenges and Limitations
10.6 Conclusions
References
Chapter 11 IoT for Health Monitoring
11.1 Introduction
11.2 Literature Review
11.3 Proposed Methodology
11.4 Hardware and Software Specification
11.4.1 Arduino Uno
11.4.2 Temperature Sensor
11.4.3 LCD
11.4.4 ESP8266
11.4.5 Power Supply
11.4.6 Pulse Sensors
11.5 Software Specification
11.5.1 Arduino IDE
11.5.2 ThingSpeak (API)
11.6 Results and Discussion
11.6.1 Phases 1 and 2: Patient’sVitals Are CollectedandPushed to the Cloud, Where They Are Graphically Analysed
11.6.2 MATLAB Analysis of 3-Day Body Temperature of Patients
11.6.3 ThingSpeak Dashboard with All the Vital Parameters and Their Graphical Representation
11.6.4 Phase 3: IFTTIntegration of Data from ThingSpeak to Generate Triggers at Particular Threshold Value
11.7 Conclusion and Future Work
References
Chapter 12 Human Behavior Detection using Image Processing and IoT
12.1 Introduction
12.1.1 What Is Computer Vision?
12.1.2 Background of the Research
12.1.3 Objective of the Project
12.1.4 Scope of the Project
12.1.5 Overview of Proposed System
12.1.6 Project Organization
12.2 Literature Review
12.2.1 Local Shape-Based Human Detection
12.2.2 Global Approach
12.2.3 Local Approach: Implicit Shape Model
12.2.4 Dense Descriptors of Image Regions
12.2.5 Work in Human Detection
12.2.6 Different Types of Edge Detector
12.2.6.1 Sobel Operator
12.2.6.2 Roberts Cross Operator
12.2.6.3 Prewitt’s Operator
12.2.6.4 Laplacian of Gaussian
12.2.7 Canny Edge Detection Algorithm
12.2.8 Detection and Tracking Using Combination of Thermal and Visible Imaging
12.2.8.1 Segmentation
12.2.8.2 Classification
12.2.8.3 Summary
12.3 Proposed Human Detection Methodology
12.3.1 Introduction
12.3.2 Proposed System Architecture
12.3.3 Details of Human Detection
12.3.3.1 Human Detection
12.3.3.2 Image Acquisition
12.3.3.3 Gray Scale Conversion
12.3.3.4 Edge Detection
12.3.3.5 Summary
12.4 Experiments, Results, and Discussion
12.4.1 Introduction
12.4.2 Experiment Setup
12.4.3 Experimental Results of Proposed System
12.5 Conclusion and Future Work
12.5.1 Contribution
12.5.2 Limitations and Future Work
12.5.3 Concluding Remarks
References
Chapter 13 A Novel Cross-Slotted Dual-Band Fractal Microstrip Antenna Design for Internet of Things (IoT) Applications
13.1 Introduction
13.2 Related Work
13.3 Fractal Antenna Design and Measurements
13.3.1 Different Stages of Antenna Creation
13.3.2 Parameters for Antenna Characterization
13.4 Simulation Results of Cross-slotted Antenna
13.5 Measurements of Fabricated Cross-Slotted Fractal Antenna
13.5.1 Return Loss and Voltage Standing Wave Ratio
13.6 Conclusion
References
Chapter 14 Examination of Vegetation Health and Its Relation with Normalized Difference Built-Up Index: A Study on Rajarhat Block of North 24 Parganas District of West Bengal, India
14.1 Introduction
14.2 Materials and Methods
14.2.1 Normalised Difference Vegetation Index (NDVI)
14.2.2 Normalized Difference Built-Up Index (NDBI)
14.3 Results and Discussion
14.3.1 NDVI and NDBI Scenario of 1999
14.3.2 NDVI and NDBI Scenario of 2009
14.3.3 NDVI and NDBI Scenario of 2019
14.3.4 Temporal Change of Land Use Classified on the Basis of NDVI Values
14.3.5 Temporal Analysis of NDVI and NDBI
14.3.6 Analysing the Relationship between the NDVI and NDBI of the Study Area
14.4 Conclusion
Acknowledgement
References
Chapter 15 Image Processing Implementation for Medical Images to Detect and Classify Various Diseases on the Basis of MRI and Ultrasound Images
15.1 Introduction to Medical Images
15.1.1 Computed Tomography (CT)
15.1.2 Ultrasound
15.1.3 Magnetic Resonance Imaging (MRI)
15.1.4 Fluoroscopy
15.1.5 Ophthalmic Imaging
15.2 Human Body Diseases Detected by Image Processing Techniques
15.2.1 Kidney Stone
15.2.2 Breast Cancer
15.2.3 Brain Tumor
15.3 Image Processing Techniques to Detect Abnormalities
15.3.1 Image Acquisition
15.3.2 Image Preprocessing (Conversion RGB to Gray)
15.3.3 Image Contrast Enhancement by Intensity Adjustment
15.3.4 Median Filter
15.3.5 Segmentation
15.3.5.1 Clustering Segmentation
15.3.5.2 Threshold Segmentation
15.3.5.3 Morphological Operation for Area Localization
15.4 Classification by Convolution Neural Networks
15.5 Result Analysis
15.6 Conclusion
References
Chapter 16 Benchmarking of Medical Imaging Technologies
16.1 Introduction
16.2 Imaging Techniques
16.2.1 Traditional Film Radiography
16.2.2 Imaging Radiography
16.2.3 Computed Tomography
16.2.4 Magnetic Resonance Imaging (MRI)
16.2.5 Ultrasonography
16.2.6 Atomic Medicine
16.2.7 Scintigraphy
16.2.8 Positron Emission Tomography (PET)
16.3 Other Imaging Techniques
16.3.1 Electrical Impedance Tomography (EIT)
16.3.2 Optical Coherence Tomography (OCT)
16.3.3 Photoacoustic/Thermoacoustic Imaging
16.3.4 Microwave Imaging
16.3.5 Magnetic Resonance Elastography (MRE)
16.4 Requirement for Several Imaging Modalities
16.5 Picture Quality, Image Processing, and Visualization of Images
16.6 Parts of Image Processing System
16.6.1 Picture Processing
16.6.2 Picture Improvement
16.6.3 Shading Handling
16.6.4 Wavelets
16.6.5 Division
16.6.6 Portrayal
16.6.7 Description
16.6.8 Acknowledge
16.7 Radiation Exposure and Radiation Protection in Medical Imaging
16.8 General Applications of Medical Imaging: Imaging towards Diseases
16.8.1 Alzheimer’s Disease (AD)
16.8.2 Malignant Growth
16.8.3 Cardiovascular Diseases
16.8.4 Neonatal Abstinence Disorder (NAD)
16.8.5 Imaging in Drug Development
16.8.6 Imaging in Medical Device Manufacturing
16.9 Conclusion
16.9.1 Future Aspects of Medical Imaging
References
Chapter 17 Application of Image Processing in Plant Leaf Disease Detection
17.1 Introduction
17.2 Contributions in the Field of Leaf Disease Detection
17.3 Leaf Disease Detection Using Convolutional Neural Networks
17.4 Results and Observations
17.5 Conclusion
References
Chapter 18 Monitoring Air Pollution with the Help of Tree Bark and Advanced Technology IoT and AI Techniques at Indore City
18.1 Introduction
18.2 Literature Survey
18.3 Aim and Objective
18.4 Study Area
18.5 Pollution Areas
18.6 Experimental Trees
18.7 Material
18.8 Methods
18.9 Observation
18.10 Results and Discussion
18.11 Challenges and Possibilities
18.12 Conclusion
Acknowledgments
References
Chapter 19 IoT-Based Smart Stick for the Blind: A Review
19.1 Introduction
19.2 System Model
19.2.1 Environment Sensing and Obstacle Detection
19.2.1.1 Some Commonly Used Sensors
19.2.1.2 Some of the Most Commonly Used Microcontroller Boards
19.2.2 Communication Messages and Alerts
19.2.3 Tracking
19.2.4 Other Enhanced Features
19.3 Issues and Challenges
19.4 Conclusion and Future Work
References
Index