book

Deep Learning for Multimedia Processing Applications

Name: Deep Learning for Multimedia Processing Applications
ISBN: 9781003828082

by Uzair Aslam Bhatti, Huang Mengxing, Jingbing Li, Sibghat Ullah Bazai, Muhammad Aamir

February 2024

Intermediate to advanced

480 pages

16h 41m

English

CRC Press

Read now

Unlock full access

Cover
Half Title
Title Page
Copyright Page
Contents
Contributors
Chapter 1 A Review on Comparative Study of Image-Denoising in Medical Imaging
1.1 Introduction1.1.1 Evaluation of Image-Denoising Techniques1.1.2 Image-Denoising Techniques1.1.3 Applications1.1.4 Comparison1.2 ConclusionReferences
Chapter 2 Remote-Sensing Image Classification: A Comprehensive Review and Applications
2.1 Introduction2.1.1 Need for This Survey2.1.2 Need for Remote-Sensing Image Classification2.1.3 Significance of Remote-Sensing Image Classification2.1.4 Research Gap for Deep Learning-Based Remote-Sensing Image Classification2.2 Deep Learning Architectures for Remote-Sensing Image Classification2.2.1 Convolutional Neural Networks (CNNs)2.2.2 Fully Convolutional Networks (FCNs)2.2.3 U-Net2.2.4 SegNet2.2.5 DeepLab2.2.6 Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) Networks2.2.7 Autoencoders2.2.8 Generative Adversarial Networks (GANs)2.2.9 Capsule Networks (CapsNets)2.2.10 Attention-Based Mechanisms2.2.11 Graph Convolutional Networks (GCNs)2.2.12 Siamese Networks2.2.13 3D Convolutional Neural Networks (3D-CNNs)2.3 Differences in Deep Learning Architectures for Remote-Sensing Image Classification2.3.1 Architecture2.3.2 Input Data2.3.3 Training Strategy2.3.4 Transfer Learning2.3.5 Optimization2.3.6 Interpretability2.4 Remote-Sensing Data Sources and Characteristics2.4.1 Satellites2.4.2 UAVs2.4.3 Multispectral Sensors2.4.4 Hyperspectral Sensors2.4.5 Synthetic Aperture Radar (SAR)2.4.6 Spatial Resolution2.4.7 Spectral Resolution2.4.8 Temporal Resolution2.4.9 Radiometric Resolution2.5 Application of Deep Learning in Remote Sensing2.5.1 Land Cover Classification2.5.2 Vegetation Monitoring2.5.3 Urban Land-Use Classification2.5.4 HSI Remote Sensing2.6 Challenges for Deep Learning Methods for RS Image Processing2.6.1 High Spatial and Spectral Variability2.6.2 Limited Annotated Data2.6.3 Class Imbalance2.6.4 Intra-Class Variability2.6.5 Spectral Mixing and Shadow Effects2.6.6 Sensor Noise and Atmospheric Interference2.6.7 Computational Complexity2.6.8 Adaptability and Generalization2.7 Limitations2.7.1 Dependence on Image Quality2.7.2 Temporal Variability2.7.3 Generalization and Transferability2.7.4 Scalability2.7.5 Interpretability2.7.6 Labeling Challenges2.7.7 Privacy Concerns2.7.8 Legal and Policy Constraints2.8 Conclusion2.8.1 Future WorkFundingReferences
Chapter 3 Deep Learning Framework for Face Detection and Recognition for Dark Faces Using VGG19 with Variant of Histogram Equalization
3.1 Introduction3.2 Literature Review3.3 Material and Techniques3.3.1 Convolutional Neural Network3.3.2 Histogram Equalization3.3.3 Data Set3.3.4 Proposed Framework3.4 Experiment and Results3.4.1 Evaluation Parameter3.4.2 Experimental Setup3.4.3 Results and Analysis3.5 ConclusionReferences
Chapter 4 A 3D Method for Combining Geometric Verification and Volume Reconstruction in a Photo Tourism System
4.1 Introduction4.2 Literature Review4.3 Method4.3.1 Processing4.3.2 Feature Extraction4.3.3 Feature Matching4.3.4 Geometric Verification4.3.5 Volumetric Reconstruction4.3.6 Triangulation4.3.7 Bundle Adjustment4.4 Experiments4.4.1 Data Set Description4.5 Results and Analysis4.6 ConclusionAcknowledgmentsReferences

Chapter 5 Deep Learning Algorithms and Architectures for Multimodal Data Analysis
5.1 Introduction to Multimodal Data Analysis5.2 Overview of Deep Learning Algorithms and Architectures5.2.1 Pre-Processing of the Multimodal Data5.2.2 The Training Process of Deep Learning Models on Multimodal Data5.2.3 Deep Learning Methods and Blockchain Technology Consortium5.3 Conclusion and Future DirectionsAbbreviationsReferences
Chapter 6 Deep Learning Algorithms: Clustering and Classifications for Multimedia Data
6.1 Introduction6.1.1 Deep Learning and Its Applications in Multimedia Data Analysis6.1.2 Classification Algorithms in Deep Learning Can Be Broadly Classified into the Following Categories6.1.3 Deep Learning for Clustering Multimedia Data6.1.4 Types of Clustering6.1.5 Classification of Clustering Algorithms in Deep Learning6.1.6 List of More Comprehensive Deep Learning Clustering Algorithms6.2 Deep Clustering Algorithm Challenges and the Multimedia Data6.2.1 Convolutional Autoencoders for Clustering Images6.2.2 Deep Convolutional Embedded Clustering for Clustering Images6.2.3 Multimodal Deep Embedded Clustering for Clustering Multimodal Data6.2.4 Case Studies – The Effectiveness of Deep Learning for Clustering Multimodal Data6.3 Deep Learning for Classification of Multimedia Data6.3.1 Incorporating Multimodal Data for Improving Classification Performance6.4 Blockchain Technology and Deep Learning Algorithms in the Context of Multimodal Data6.4.1 Cross-Border Blockchain Technology and Deep Learning Methods6.4.2 Key Attributes of Cross-Border Blockchain Technology6.4.3 Cross-Border and Deep Learning Multimodal Blockchain Technology6.4.4 Future Trends and Applications of the Blockchain and Deep Learning6.5 ConclusionAbbreviationsReferences
Chapter 7 A Non-Reference Low-Light Image Enhancement Approach Using Deep Convolutional Neural Networks
7.1 Introduction7.2 Literature Review7.3 Material and Techniques7.3.1 Retinex Theory7.3.2 Decomposition Network7.3.3 Optimizing the Network7.4 Experiment and Results7.4.1 Experimental Design7.4.2 Subjective Evaluation7.4.3 Objective Evaluation7.4.4 Generalization Ability7.5 ConclusionReferences
Chapter 8 Human Pose Analysis and Gesture Recognition: Methods and Applications
8.1 Introduction8.2 Literature Review8.2.1 Bodily Attached Sensors Based Methods8.2.2 Computer Vision-Based Recognition Systems8.2.3 Pose and Gesture Recognition Using Multiple Sensors8.2.4 Data Fusion in a Multisensory Environment8.2.5 Pose and Gesture Data Set8.3 ConclusionReferences
Chapter 9 Human Action Recognition Using ConvLSTM with Adversarial Noise and Compressive-Sensing-Based Dimensionality Reduction, Concise and Informative
9.1 Introduction9.2 Background9.3 Proposed Model9.3.1 Data Layer9.3.2 Compressive Sensing9.3.3 Feature Learning9.3.4 Sequential Learning9.3.5 Softmax9.3.6 Output Layer9.4 Results and Discussion9.4.1 SVM Classifier9.4.2 ConvLSTM Classifier9.4.3 ConvLSTM with GANs9.4.4 Overall Results9.5 ConclusionsSupplementary MaterialsAcknowledgmentsReferences
Chapter 10 Application of Machine Learning to Urban Ecology
10.1 Introduction10.1.1 Brief Background of Urban Ecology10.1.2 The Importance of Machine Learning in Urban Ecology10.1.3 Objectives of the Chapter10.2 Introduction to Machine Learning10.2.1 Types of Machine Learning Techniques10.2.2 How Machine Learning Can Benefit Urban Ecology10.3 Overview of Urban Ecological Data Sources10.3.1 Preprocessing and Data Fusion Techniques10.4 Applications of Machine Learning in Urban Ecosystem Services10.4.1 Urban Green Space Identification and Monitoring10.4.2 Biodiversity Assessment and Conservation10.4.3 Urban Heat Island Detection and Mitigation10.4.4 Air Quality Monitoring and Prediction10.4.5 Flood Risk Assessment and Management10.5 Applications of Machine Learning in Urban Landscape Planning and Design10.5.1 Landscape Connectivity and Fragmentation Analysis10.5.2 Green Infrastructure Planning10.5.3 Urban Greening and Rewilding Strategies10.5.4 Urban Form Optimization for Ecological Resilience10.5.5 Evaluation of Landscape Design Alternatives10.6 Machine Learning for Socio-Ecological Systems in Urban Environments10.6.1 Analyzing Human-Nature Interactions10.6.2 Environmental Justice and Equitable Access to Green Spaces10.6.3 Public Engagement and Decision-Making Support10.6.4 Community-Based Ecological Monitoring and Management10.7 Challenges and Future Directions10.7.1 Data Quality and Availability10.7.2 Interpreting and Validating Machine Learning Models10.7.3 Integrating Cross-Disciplinary Knowledge10.7.4 Ethical Considerations10.7.5 Climate Change and Urban Ecology10.8 ConclusionReferences
Chapter 11 Application of Machine Learning in Urban Land Use
11.1 Introduction11.1.1 Briefly Introduce the Concept of Machine Learning and Urban Land Use11.1.2 Explain the Significance of Integrating Machine Learning in Urban Planning and Management11.2 Background: Understanding Urban Land Use and Machine Learning11.2.1 Discuss the Basics of Urban Land Use, Including its Importance, Challenges, and Traditional Methods Used in Planning11.2.2 Introduce Machine Learning and Its Key Concepts, Including Algorithms, Training, and Validation11.3 Machine Learning Techniques for Urban Land Use11.3.1 Describe Various Machine Learning Techniques and Their Relevance to Urban Land Use Applications, Such as Classification, Regression, and Clustering Algorithms11.3.2 Explain How Specific Algorithms, Like Convolutional Neural Networks and Support Vector Machines, can be Employed in Urban Land Use Planning11.4 Key Applications of Machine Learning in Urban Land Use11.4.1 Land Use Classification and Monitoring11.4.2 Urban Growth Modeling and Prediction11.4.3 Transport Planning and Optimization11.5 Data Acquisition, Processing, and Integration11.5.1 Discuss the Importance of Quality Data for Effective Machine Learning Applications11.5.2 Explain Various Data Sources Relevant to Urban Land Use, Such as Satellite Imagery, GIS, and Open Data Platforms11.5.3 Describe Data Pre-Processing Techniques, Including Cleaning, Normalization, and Feature Extraction11.6 Future Trends and Opportunities11.6.1 Explore the Future of Machine Learning in Urban Land Use, Including Advances in AI Technology, New Data Sources, and Interdisciplinary Collaboration11.7 Conclusion11.7.1 Summarize the Key Takeaways from this Chapter11.7.2 Reiterate the Significance of Machine Learning in Urban Land Use Planning and Management11.7.3 Encourage Readers to Explore and Implement Machine Learning Solutions to Promote Sustainable Urban DevelopmentReferences
Chapter 12 Application of GIS and Remote-Sensing Technology in Ecosystem Services and Biodiversity Conservation
12.1 Introduction12.1.1 Overview of Ecosystem Services and Biodiversity Conservation12.1.2 Importance of GIS and Remote Sensing in Ecosystem Services and Biodiversity Conservation12.1.3 Scope of the Chapter12.2 Fundamentals of GIS and Remote Sensing12.2.1 Geographic Information Systems (GISs)12.2.2 Remote Sensing12.3 Assessing Ecosystem Services Using GIS and Remote Sensing12.3.1 Provisioning Services12.3.2 Regulating Services12.3.3 Cultural Services12.3.4 Supporting Services12.4 Biodiversity Conservation Through GIS and Remote Sensing12.4.1 Habitat Mapping and Monitoring12.4.2 Species Distribution Modeling12.4.3 Monitoring and Assessing Biodiversity Change12.5 Case Studies and Applications12.5.1 Monitoring Forest Loss and Fragmentation in the Amazon Rainforest12.5.2 Assessing the Impacts of Land-Use Change on Wetland Ecosystems12.5.3 Predicting the Impacts of Climate Change on Mountain Biodiversity12.5.4 Identifying Priority Areas for Coral Reef Conservation12.5.5 Monitoring the Spread of Invasive Species in the Great Lakes Region12.6 Challenges and Future Prospects12.6.1 Challenges12.6.2 Future Prospects12.7 ConclusionReferences
Chapter 13 From Data Quality to Model Performance: Navigating the Landscape of Deep Learning Model Evaluation
13.1 Introduction13.2 Importance of Data Sets, Benchmarks, and Validations13.3 Data Sets for Deep Learning13.3.1 What is a Data Set and Why is it Important in AI?13.3.2 The Impact of Data Quality on Deep Learning Model Performance13.3.3 Overview of Popular Data Sets for Deep Learning Models13.3.4 Advantages and Limitations of Using Publicly Available Data Sets13.3.5 Best Practices for Data Set Creation and Curation13.3.6 Techniques for Ensuring Data Set Diversity and Balance13.3.7 The Role of Data Augmentation in Improving Data Set Quality13.3.8 Techniques for Labeling Data Sets Accurately and Efficiently13.3.9 Quality of Data Set13.4 Benchmarking for Deep Learning Model13.4.1 Importance of Benchmarks in Evaluating the Performance of Deep Learning Models13.4.2 Metrics Used for Benchmarking13.4.3 Famous Benchmarks13.4.4 Considerations for Selecting and Designing Benchmarks for Deep Learning Models13.4.5 Challenges in Interpreting Benchmarks for Deep Learning Models in the Context of Specific Problems13.5 Validations of Deep Learning Models13.5.1 Popular Validation Techniques Used in Deep Learning Research13.5.2 Interpreting Validation Results in the Context of Specific Problems13.6 Challenges and Future Directions13.6.1 Examples of Current Challenges13.6.2 Future Directions for Improving the Development and Use of Data Sets, Benchmarks, and Validations in Deep Learning ResearchReferences
Chapter 14 Deep Learning for the Turnover Intention of Industrial Workers: Evidence from Vietnam
14.1 Introduction14.2 Literature Review14.2.1 Justice in an Organization and Work Interference with Personal Life and Turnover Intention14.2.2 Research Model and Hypothesis14.3 Method14.3.1 Sample14.3.2 Scale14.3.3 Demographics of Respondents14.4 Results14.4.1 Measurement Model14.4.2 Estimation and Evaluation of the Structural Model14.4.3 Hypothesis Testing14.5 ConclusionsReferences
Chapter 15 Deep Learning for Multimedia Analysis
15.1 Introduction15.1.1 Overview of Deep Learning15.1.2 Applications of Deep Learning in Multimedia Analysis15.1.3 Recent Advances in Analysis of Multimedia Using Deep Learning15.2 Literature Review15.3 In-Depth Learning15.3.1 Generative Deep Architectures15.3.2 Discriminative Deep Architectures15.3.3 Hybrid Deep Architectures15.3.4 CNN15.3.5 DNN15.3.6 BM15.3.7 RBM15.4 Multimedia Content Using Deep Learning Applications15.4.1 Convolutional Neural Networks15.4.2 Recurrent Speech and Natural Language Processing15.4.3 Autoencoders are Neural Networks15.4.4 Transfer Learning15.4.5 Reinforcement Learning15.4.6 Bayesian Deep Learning15.5 Challenges and Future Directions15.5.1 Challenges15.5.2 Future Directions15.6 ConclusionsReferences
Chapter 16 Challenges and Techniques to Improve Deep Detection and Recognition Methods for Text Spotting
16.1 Introduction16.2 Challenges in Text Spotting16.2.1 Variable Text Size and Orientation16.2.2 Occlusion16.2.3 Low-Quality Images16.2.4 Large Vocabulary16.2.5 Training Data16.3 Deep Learning in Text Spotting16.3.1 Convolutional Neural Networks (CNNs)16.3.2 Recurrent Neural Networks (RNNs)16.3.3 Convolutional Recurrent Neural Networks (CRNNs)16.3.4 Attention Mechanisms16.3.5 Transfer Learning16.3.6 Lexicons16.3.7 Language Models16.4 Text Spotting Data Sets16.4.1 COCO-Text16.4.2 SynthText16.4.3 Street View Text16.4.4 Total-Text16.4.5 MJSynth16.4.6 MSRA-TD50016.4.7 NTU-UTOI16.4.8 FORU16.4.9 ICDAR'19 MLT16.4.10 Inverse-Text16.5 DL Models used in Text Spotting16.5.1 VGG16.5.2 ResNet16.5.3 Inception16.5.4 DenseNet16.5.5 EfficientNet16.5.6 MobileNet16.5.7 SSD16.6 Loss Functions used in Text Spotting16.6.1 Binary Cross-Entropy Loss16.6.2 L1 or L2 Loss16.6.3 Connectionist Temporal Classification (CTC) Loss16.6.4 Multi-Task Loss16.6.5 Focal Loss16.7 Problem Definition Focused16.8 Proposed Solution Architecture16.8.1 ResNet Architecture16.8.2 Loss Function Design Strategy16.9 Data Set Preparation16.9.1 Data Set Formulation16.9.2 Parameter Settings16.10 Experimental Results and Analysis16.10.1 Environment16.10.2 Comparison Study16.10.3 Ablation Study16.10.4 Key Contribution and Advantages16.11 Conclusion and Future WorkNotesReferences
Chapter 17 Leaf Classification and Disease Detection Based on R-CCN Deep Learning Approach
17.1 Introduction17.2 Literature Review17.3 Proposed Model and Techniques17.3.1 Proposed Model17.3.2 Data Pre-Processing17.3.3 Leaf Transformation Algorithm for Training Data Set17.3.4 RCCN Model17.3.5 Convolutional Neural Network17.3.6 Advancements in Technologies17.3.7 Hardware Equipment17.3.8 Micro USB Power Cable, Power Supply17.3.9 Python Script17.4 Experiment and Results17.4.1 Experiment Process17.4.2 Results and Analysis17.5 ConclusionReferences
Chapter 18 Multimedia Analysis with Deep Learning: Advancements & Challenges
18.1 Introduction18.1.1 Background18.1.2 Purpose of the Study18.1.3 Research Questions18.1.4 Chapter Objectives18.1.5 Chapter Organization18.2 Literature Review18.2.1 Traditional Multimedia Analysis Approaches18.2.2 Deep Learning in Multimedia Analysis18.2.3 Multimodal Learning and Cross-Modal Retrieval18.2.4 Challenges and Future Directions18.3 Methodology18.3.1 Data Set Description18.3.2 Deep Learning Architectures18.3.3 Recurrent Neural Networks (RNNs)18.3.4 Transformers18.3.5 Experimental Setup18.4 Results and Discussion18.4.1 Performance of Deep Learning Models18.4.2 Comparison with Traditional Methods18.4.3 Insights and Analysis18.5 Case Studies18.5.1 Case Study 1: Image Classification18.5.2 Case Study 2: Video Analysis18.5.3 Case Study 3: Multimodal Learning18.6 Challenges and Limitations18.6.1 Data Bias18.6.2 Interpretability18.6.3 Computational Efficiency18.7 Conclusion18.7.1 Key Findings18.7.2 Recommendations for Future ResearchReferences
Index

Content preview from Deep Learning for Multimedia Processing Applications

Contributors

Muhammad Aamir

College of Computer Science

Huanggang Normal University

Huanggang, China

Anuj Abraham

Technology Innovation Institute

Abu Dhabi, United Arab Emirates

Syed Hasan Adil

Faculty of Engineering, Sciences and Technology

Iqra University

Karachi, Pakistan

Raza Muhammad Ahmad

School of Cyberspace Security

Hainan University

Haikou, China

Shakeel Ahmed

College of Material Sciences

Hainan University

Haikou, China

Muhammad Akram

Faculty of Information and Communication Technology

Balochistan University of Information Technology, Engineering and Management Sciences

Quetta, Pakistan

Irfan Ali

Department of Computer Science

University of Agriculture Faisalabad

Faisalabad, Pakistan

Saud Altaf

University Institute of Information Technology ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Deep Learning for Multimedia Processing Applications

Publisher Resources

ISBN: 9781003828082

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Deep Learning for Multimedia Processing Applications

by Uzair Aslam Bhatti, Huang Mengxing, Jingbing Li, Sibghat Ullah Bazai, Muhammad Aamir

Contributors

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.