Nowadays, audiovisual content is distributed rapidly but also extensively to remote regions via the web in a number of formats, comprising images, audio, video, and textual. Everything is easily accessible and simple for all users thanks to digitized transmission via the World Wide Web. As a consequence, data protection is indeed a required and essential activity. Networking or data security has three primary goals: confidentiality, integrity, and availability. Confidentiality refers to content that is secure yet not accessed by unauthorized individuals. The term "integrity" refers to an information's veracity, while "availability" refers to the ease in which authorized users can access essential data. Information security is insufficient on its own to assure the constant operation of data such as text, audio, video, and electronic images. Although there are several ways to image security available, including encryption, watermarking, digital watermarking, reversible watermarking, cryptography, and steganography. The goal of this book is to transfer secure textual data storage on public networks and IoT devices by concealing secret data in multimedia. It also covers discussions on textual image recognition using machine learning/deep learning-based methods. This book also offers advanced steganography ways for embedding textual data on the cover image, as well as a new way for secure transmission of biological imaging, imaging with machine learning and deep learning, and 2D, 3D imaging in the field of telemedicine.
Author(s): Digvijay Pandey, Rohit Anand, Nidhi Sindhwani, Binay Kumar, Pandey Reecha, Sharma, Pankaj Dadheech
Series: Technology in a Globalizing World
Publisher: Nova Science Publishers, Inc.
Year: 2023
Language: English
Pages: 382
Contents
Preface
Acknowledgments
Chapter 1
The Investigation of Image Processing in Forensic Science
Abstract
1. Introduction
1.1. Computer Tools for Image Processing in Forensic Science
1.2. Softwares Used in Forensic Image Processing
1.2.1. Disk and Data Capture Tools
1.2.2. Autopsy/The Sleuth Kit
1.2.3. X-Ways Forensics
1.2.4. Access Data FTK
1.2.5. En Case
1.2.6. Mandiant Red Line
1.2.7. Paraben Suite
1.2.8. Bulk Extractor
1.2.9. Registry Analysis
1.2.10. Registry Recon
1.2.11. Memory Forensics
1.2.12. Volatility
1.2.13. Windows SCOPE
1.2.14. Wireshark
1.2.15. Network Miner
1.2.16. X Plico
2. Image Reconstruction
3. Mobile Device Forensics
3.1. Oxygen Forensic Detective
3.2. Celle Brite UFED
3.3. XRY
3.4. Linux Distros
3.5. CAINE
3.6. SANS SIFT
3.7. HELIX3
4. Processing of Forensic Digital Image
5. Different Types of Digital Image Evidence
6. Use of Digital Image Forensics Techniques
7. Lifecycle of Digital Image
8. Factors Affecting the Digital Image Lifecycle
9. Core Functionalities of Image Forensics Software
10. Forensic Image Analysis
10.1. Photo Image Comparison
10.2. Image Content Analysis (ICE)
10.3. Image Authentication
10.4. Image Enhancement and Restoration
11. Photogrammetry
12. Pros and Cons of Digital Image Forensics
12.1. Pros
12.2. Cons
13. Image Processing for Digital Forensics
Conclusion and Future Outlook
References
Chapter 2
Integrating IoT Based Security with Image Processing
Abstract
1. Introduction
1.1. Internet of Things
1.1.1. Features of IOT
1.1.2. A Comparison between Traditional Internet and IoT
1.1.3. Pros & Cons of IoT
1.1.4. Applications of IoT
1.1.5. Security Flaws of IoT
1.2. Image Processing
1.2.1. Characteristics of Digital Image Processing (DIP)
1.2.2. Applications of DIP
1.2.3. Architecture/Working
1.3. CBIR
1.3.1. Applications of CBIR
1.4. Camera Surveillance and Machine Vision
1.5. Machine Vision
2. Literature Review
3. Problem Statement
4. Proposed Model
4.1. Role of Canny Edge Detection in Reducing Image Size
5. Results and Discussion
5.1. Comparison of Size during Image Processing in IoT Environment
5.2. Comparison of Time Taken during Image Processing in IoT Environment
Conclusion and Future Outlook
References
Chapter 3
Pattern Analysis for Feature Extraction in Multi-Resolution Images
Abstract
1. Introduction
1.1. Pattern Class
1.2. Analysis
1.3. Pattern Analysis
1.3.1. Pattern Recognition
1.4. Problem Definition
1.5. Pattern Analysis Algorithm
1.6. Feature Extraction
2. Literature Review
3. Implementation
3.1. Sobel Edge Detector
3.2. Prewitt Edge Detector
3.3. Laplacian Edge Detector
3.4. Canny Edge Detector
Conclusion
References
Chapter 4
The Design of Microstrip Patch Antenna for 2.4 GHz IoT Based RFID and Image Identification for Smart Vehicle Registry
Abstract
1. Introduction
2. Smart Vehicle Registry
3. Background
4. Design Parameters
4.1. Design Eqation of Inset Feed Microstrip Patch Antenna
4.2. Design of Microstrip
5. Modeling and Analysis
6. Results and Discussion
7. Other Applications
Conclusion and Future Outlook
References
Chapter 5
Kidney Stone Detection from Ultrasound Images Using Masking Techniques
Abstract
1. Introduction
2. Ultrasound Images
3. Contrast Enhancement
4. Proposed Optimum Wavelet Based Masking
4.1. Proposed OWBM Algorithm
5. Cuckoo Search Algorithm
5.1. The Traditional Cuckoo Search Algorithm
5.2 Need of Adaptive Rebuilding of Worst Nests (ARWN)
5.3. Enhanced Cuckoo Search Algorithm
5.4. Image Segmentation
5.5. Thresholding
6. Results and Discussion
Conclusion and Future Outlook
References
Chapter 6
Biometric Technology and Trends
Abstract
1. Introduction
2. History
3. Conventional Biometrics and Modern Age Biometrics Distinguished
4. Biometrics- Trends and Prospects
5. Types of Biometric
6. Trustworthiness and Challenges of Biometrics
7. Challenges and Countermeasures
7.1. Biometric Template Protection
7.2. Error Correction Methods
7.3. Other No Cryptographic Approaches
8. Biometric Technology in Different Spheres of Life
8.1. Commercial Applications
8.2. Law Enforcement and Public Security (Criminal/Suspect Identification)
8.3. Military (Enemy/Ally Identification)
8.4. Border, Travel, and Migration Control (Traveler/Migrant/Passenger Identification)
8.5. Civil Identification (Citizen/Resident/Voter Identification)
8.6. Healthcare and Subsidies (Patient/Beneficiary/Healthcare Professional Identification)
8.7. Physical and Logical Access (Owner/User/Employee/ Contractor/Partner Identification)
8.8. Technological Utilization
8.8.1. Mobile Phones/Tablets
8.8.2. Laptops/PCs
8.8.3. Automobiles
Conclusion and Future Outlook
References
Chapter 7
Comparison of Digital Image Watermarking Methods: An Overview
Abstract
1. Introduction
2. Watermarking
2.1. Classification of Digital Watermarking Techniques
2.1.1. Robust and Fragile Watermarking
2.1.2. Public and Private Watermarking
2.1.3. Asymmetric and Symmetric Watermarking
2.1.4. Steganographic and Non-Steganographic Watermarking
2.1.5. Visible and Invisible Watermarking
2.2. Requirements
2.3. Techniques
2.4. Applications
2.4.1. Copyright Protection
2.4.2. Copyright Authentication
2.4.3. Fingerprinting and Digital Signatures
2.4.4. Copy Protection and Device Control
2.4.5. Broadcast Monitoring
3. Performance Metrics
3.1. Signal to Noise Ratio (SNR)
3.2. Peak Signal to Noise Ratio (PSNR)
3.3. Weighted Peak Signal to Noise Ratio (WPSNR)
3.4. Effectiveness
3.5. Efficiency
4. Comparison of Watermarking Techniques
Conclusion and Future Outlook
References
Chapter 8
Novel Deep Transfer Learning Models on Medical Images: DINET
Abstract
1. Introduction
1.1. Medical Image Classification: Transfer Learning
2. Literature Review
3. Methodology
3.1. Datasets
3.2. Deep CNN Phase
3.3. Implementation Details
4. Experiment Results
4.1. Implementation Details
4.2. Experiments
4.3. Evaluation Procedures and Techniques
4.4. Results
5. Discussion
Conclusion
Limitations
Future Outlook
References
Chapter 9
A Review of the Application of Deep Learning in Image Processing
Abstract
1. Introduction
1.1. Basic Network Structure: Multi-Layer Perception (MLP)
1.2. Convolutional Neural Network (CNN)
2. Network Structure Improvements
2.1. Improvement of Convolutional Neural Network
2.1.1. AlexNet Model
2.1.2. ZFNet Model
2.1.3. Deep Residual Network (ResNet)
2.2. Improvement of Recurrent Neural Network
2.2.1. Long and Short-Term Memory Network (LSTM)
2.2.2. Hierarchical RNN
2.2.3. Bi-Directional RNN
2.2.4. Multi-Dimensional RNN
3. Applications of Deep Learning in Image Processing
3.1. Speech Processing
3.2. Computer Vision
3.3. Natural Language Processing
4. Existing Problems and Future Directions of Deep Learning
4.1. Training Problem
4.1.1. The Gradient Disappearance Problem
4.1.2. Use Large-Scale Labelled Training Datasets
4.1.3. Distributed Training Problem
4.2. Landing Problem
4.2.1. Too Many Hyper-Parameters
4.2.2. Reliability is Insufficient
4.2.3. Poor Interpretability
4.2.4. Model Size Is Too Large
4.3. Functional Problem
4.3.1. Lack of Ability to Solve Logical Problems
4.3.2. Small Data Challenges
4.3.3. Unable to Handle Multiple Tasks Simultaneously
4.3.4. Ultimate Algorithm
4.4. Domain Issues
4.4.1. Image Understanding Issues
4.4.2. Natural Language Processing Issues
Conclusion
References
Chapter 10
The Survey and Challenges of Crop Disease Analysis Using Various Deep Learning Techniques
Abstract
1. Introduction
2. Literature Survey
2.1. Leaf Diseases
2.1.1. Grape
2.1.2. Citrus
2.1.3. Apple
2.1.4. Other
3. Four Phase Technique
3.1. Data Collection
3.2. Data Augmentation
3.3. Data Detection and Classification
3.4. Optimization
4. Issues Related to Plant Disease Identification
Conclusion and Future Outlook
References
Chapter 11
Image Processing and Computer Vision: Relevance and Applications in the Modern World
Abstract
1. Introduction
1.1. Digital Image Processing
1.2. Image Acquisition
1.3. Digital Histogram Plots
1.4. Characteristics
2. Image Storage and Manipulation
2.1. Image Segmentation
2.2. Feature Extraction
2.3. Multi-Scale Signal Analysis
2.4. Pattern Recognition
2.5. Projection
3. Image Processing Techniques
3.1. Anisotropic Diffusion
3.2. Hidden Markov Models
3.3. Image Editing
3.4. Image Restoration
3.5. Independent Component Analysis
3.6. Linear Filtering
3.7. Neural Networks
3.8. Point Feature Matching
3.9. Principal Components Analysis
4. Newer Applications of Image Processing
4.1. Active Learning Participation
4.2. Workplace Surveillance
4.3. Building Recognition
4.4. Image Change Detection
4.5. Human Race Detection
4.6. Rusting of Steel
4.7. Object Deformation
4.8. Tourism Management
Conclusion and Future Outlook
References
Chapter 12
Optimization Practices Based on the Environment in Image Processing
Abstract
1. Introduction
2. Environment-Based Optimization Techniques
2.1. Evolutionary Algorithms
2.1.1. Genetic Algorithm (GA)
2.2. Swarm Intelligence Algorithms in Image Processing
2.2.1. Bat Algorithm in Image Processing
2.2.2. Ant Colony Optimization (ACO) in Image Processing
2.2.3. Artificial Honey Bee (ABC) Optimization in Image Processing
2.2.4. Cuckoo Optimization in Image Processing
2.2.5. Firefly Optimization Algorithm in Image Processing
2.2.6. Elephant Herding Optimization (EHO) Algorithm in Image Processing
2.2.7. Grey Wolf Optimization Algorithm in Image Processing
Conclusion
References
Chapter 13
Simulating the Integration of Compression and Deep Learning Approaches in IoT Environments for Security Systems
Abstract
1. Introduction
1.1. Deep Learning
1.2. IoT
1.3. Compression
1.3.1. Lossless Compression
1.3.2. Lossy Compression
1.4. Role of Compression in IoT
1.5. Role of Security in IoT
1.6. Different Types of Cyber Crimes
1.7. Status of Cyber Crimes
1.8. Advantages of Cyber Security
1.9. Disadvantages of Cyber Security
1.10. Different Cyber Attacks
1.10.1. Ransom-Ware
1.10.2. Brute Force Attack
1.10.3. Man in Middle Attack
1.10.4. Man in the Middle Attack Prevention
1.10.5. SQL Injection
1.10.6. Solution for SQL Injection Attacks
1.11. Role of Encryption in Cyber Security
1.12. Role of Firewall in Cyber Security
1.13. Intrusion Detection System (IDS)
1.14. Role of Machine Learning in Cyber Security
2. Literature Review
3. Problem Statement
4. Proposed Work
4.1. Features of Proposed Model
5. Results and Discussion
5.1. Confusion Matrix of Unfiltered Dataset
5.2. Confusion Matrix of Filtered Dataset
5.3. Comparison Analysis
5.3.1. Accuracy
5.3.2. Precision
5.3.3. Recall Value
5.3.4. F1-Score
Conclusion and Future Outlook
References
Chapter 14
A Review of Various Text Extraction Algorithms for Images
Abstract
1. Introduction
2. Literature Review
2.1. Comprehensive Study of the Existing Work
Conclusion and Future Outlook
References
Chapter 15
Machine Learning in the Detection of Diseases
Abstract
1. Introduction
2. Types of Machine Learning Techniques
3. Machine Learning Algorithms
3.1. K Nearest Neighbor Algorithm (KNN)
3.2. K-Means Clustering Algorithm
3.3. Support Vector Machine
3.4. Naive Bayes Algorithm
3.5. Decision Tree Algorithm
3.6. Logistic Regression (LR)
4. Diagnosis of Diseases by Using Different Machine Learning Algorithms
4.1. Heart Disease
4.1.1. Analysis
4.2. Diabetes Disease
4.2.1. Analysis
4.3. Liver Disease
4.3.1. Analysis
4.4. Dengue
4.4.1. Analysis
4.5. Hepatitis Disease
5. Discussion and Analysis of Machine Learning Techniques
6. Benefits of Machine Learning in Diagnosis of Diseases
6.1. Recognizes and Examines Ailments
6.2. Drug Improvement and Gathering
6.3. Clinical Imaging Diagnostics
6.4. Altered Medicine
6.5. Prosperity Record with Knowledge
6.6. Research and Clinical Fundamentals
6.7. Data Grouping
6.8. Drug Things
7. Challenges of Machine Learning in Detection and Diagnosis of Diseases
7.1. Data Irregularity
7.2. Absence of Qualified Pioneers
7.3. Supplier Scorn
7.4. Data Security
Conclusion and Outlook
References
Chapter 16
Applications for Text Extraction of Complex Degraded Images
Abstract
1. Introduction
1.1. Noise
1.1.1. Gaussian Noise
2. Impulse Noise
2.1. Pre-Processing Methods
3. Blurring
3.1. Gaussian Filter
3.2. Median Filter
4. Thresholding
4.1. Global Thresholding
5. Morphological Operations
5.1. Dilation
5.2. Erosion
5.3. Opening and Closing
6. Methodology
7. Experimental Analysis
8. Results and Discussion
Conclusion and Future Outlook
References
Index
About the Editors
Blank Page
Blank Page
