Copertina

Intelligent fractal-based image analysis : applications in pattern recognition and machine vision /

Fractals are infinite, complex patterns used in modeling physical and dynamic systems. Fractal theory research has increased across different fields of applications including engineering science, health science, and social science. Recent literature shows the vital role fractals play in digital imag...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Altri autori: Nayak, Soumya Ranjan
Natura: eBook
Lingua:inglese
Pubblicazione: London : Academic Press, 2024.
Serie:Cognitive data science in sustainable computing
Soggetti:
Image analysis.
Analyse d'images.
Image analysis
Accesso online:ScienceDirect
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Sommario:
  • Front Cover
  • Intelligent Fractal-Based Image Analysis
  • Copyright
  • Contents
  • Contributors
  • Foreword
  • Preface
  • Acknowledgments
  • I Intelligent fractal-based image analysis
  • 1 A deep insight into intelligent fractal-based image analysis with pattern recognition
  • 1.1 Introduction
  • 1.2 Approaches and applications of pattern recognition
  • 1.2.1 Applications of pattern recognition
  • 1.2.1.1 Healthcare
  • 1.2.1.2 Speech recognition
  • 1.2.1.3 Agriculture
  • 1.3 Various approaches of image analysis
  • 1.3.1 Feature extraction
  • 1.3.2 Segmentation
  • 1.3.3 Classification
  • 1.4 Fractal based image analysis
  • 1.4.1 Image compression using fractal features
  • 1.4.2 Texture segmentation using fractal features
  • 1.4.3 Feature extraction using fractal dimensions
  • 1.4.4 Intelligent approaches for analysis of fractal features
  • 1.5 Critical analysis
  • 1.5.1 Percentage of work carried out using various pattern recognition approaches
  • 1.5.2 Application of pattern recognition approaches in various application domains
  • 1.5.3 Contribution of work using distinct approaches of image analysis
  • 1.5.4 Growth of publications in fractal based image analysis
  • 1.6 Conclusion
  • References
  • 2 Analysis of Mandelbrot set fractal images using a machine learning based approach
  • 2.1 Introduction
  • 2.2 Related works
  • 2.3 Methodology
  • 2.4 Results and discussion
  • 2.5 Conclusions
  • References
  • 3 Chaos-based image encryption
  • 3.1 Chaos-based image encryption studies and encryption/decryption processes
  • 3.1.1 Literature review
  • 3.1.2 Explanation of the basic processes of chaos-based image encryption and decryption
  • 3.2 The evaluation methods
  • 3.2.1 Randomness tests
  • 3.2.2 Statistical evaluation methods
  • 3.2.2.1 Correlation
  • 3.2.2.2 Entropy
  • 3.2.2.3 Histogram
  • 3.2.2.4 Contrast
  • 3.2.2.5 Homogeneity
  • 3.2.2.6 Energy.
  • 3.2.2.7 Encryption quality
  • 3.2.2.8 MAD (mean absolute deviation) or mean absolute error (MAE)
  • 3.2.2.9 Differential attack
  • 3.2.2.10 MSE (mean square error) and PSNR (peak signal to noise ratio)
  • 3.2.3 Key evaluation methods
  • 3.2.3.1 Keyspace analysis
  • 3.2.3.2 Key sensitivity analysis
  • 3.3 The security evaluation of chaos-based image encryption
  • 3.4 A case study: chaos-based medical image encryption
  • References
  • 4 Fractal feature based image classification
  • 4.1 Introduction
  • 4.2 Related works
  • 4.3 Materials and method
  • 4.3.1 Proposed methodology
  • 4.3.2 Dataset used
  • 4.3.3 Data augmentation
  • 4.3.4 Feature extraction
  • 4.3.4.1 Hausdorff dimension
  • 4.3.4.2 Smoothness
  • 4.3.4.3 GLCM
  • 4.4 Experimental analysis
  • 4.4.1 Data aggregation
  • 4.4.2 Exploratory data analysis and normalization
  • 4.4.3 Classification methods and performance metrics
  • 4.4.3.1 Classification methods
  • 4.4.3.2 Classification techniques
  • 4.4.4 Results
  • 4.4.4.1 Accuracy loss curve for ANN
  • 4.5 Conclusions
  • References
  • II Recognition model using fractal features
  • 5 The study of source image and its futuristic quantum applications: an insight from fractal analysis
  • 5.1 Introduction
  • 5.2 Source description and correlation functions
  • 5.3 Methods explanation for coherent droplets
  • 5.4 Formulation within partially chaos emission
  • 5.5 Model results and discussion
  • 5.5.1 Source performance with three-particle correlations
  • 5.5.2 Source analysis with four-particle correlations
  • 5.6 Summary and conclusions
  • Acknowledgments
  • References
  • 6 Deep CNNS and fractal-based sequence learning for violence detection in surveillance videos
  • 6.1 Introduction
  • 6.1.1 Related work
  • 6.1.1.1 Conventional learning-based VD methods
  • 6.1.1.2 VD methods using deep learning
  • 6.1.2 Violence detection working flow.
  • 6.1.3 Recurrent neural network
  • 6.1.4 Long short-term memory
  • 6.1.5 Gated recurrent unit (GRU)
  • 6.2 Violence detection methods
  • 6.3 Discussion on experimental results
  • 6.4 Challenges and future research guidelines
  • 6.5 Conclusion
  • References
  • 7 Wavelets for anisotropic oscillations in nanomaterials
  • 7.1 Introduction
  • 7.2 On the regularity of functions
  • 7.3 Some formal calculus of oscillating singularities
  • 7.3.1 Case 1
  • 7.3.2 Case 2
  • 7.3.3 Case 3
  • 7.3.4 Case 4
  • 7.4 Wavelet characterization of the regularity
  • 7.5 An application on nanomaterials
  • 7.5.1 AI ML and nanotechnology brief history
  • 7.5.2 Fractal processing of nanomaterials
  • 7.5.3 The (anisotropic) oscillations in nanomaterials
  • 7.6 Conclusions
  • 7.7 Appendix
  • Wavelet toolkit review
  • Acknowledgment
  • References
  • 8 Comparative analysis of approaches to optimize fractal image compression
  • 8.1 Introduction
  • 8.2 Theoretical framework
  • 8.3 Factor affecting FIC
  • 8.4 Approaches for accelerate FIC
  • 8.4.1 Block classification
  • 8.4.2 Partitioning of image blocks
  • 8.4.3 Nearest-neighbor search
  • 8.4.4 Clustering
  • 8.4.5 Vector quantization
  • 8.4.6 Discrete cosine transforms
  • 8.4.7 Variance-based FIC
  • 8.4.8 Spatial correlation
  • 8.4.9 Iteration-free convergence
  • 8.4.10 Local search or no-search method
  • 8.4.11 Parallel algorithm
  • 8.4.12 Wavelet fractal hybrid encoder
  • 8.4.13 Genetic algorithm
  • 8.5 Summary and analysis of review
  • 8.6 Conclusions
  • References
  • III Fractals in disease identification and control
  • 9 Alzheimer disease (AD) medical image analysis with convolutional neural networks
  • 9.1 Introduction
  • 9.2 Brain amyloidosis and medical imaging
  • 9.2.1 Structural magnetic resonance imaging (sMRI)
  • 9.2.2 Functional magnetic resonance imaging (fMRI)
  • 9.2.3 Computed tomography (CT).
  • 9.2.4 Positron emission tomography (PET)
  • 9.3 CNNs in the field of medicine and their basic architecture
  • 9.3.1 Input layer
  • 9.3.2 Convolutional layer
  • 9.3.3 ReLU layer
  • 9.3.4 Pooling layer
  • 9.3.5 Fully connected layers
  • 9.3.6 Output layer
  • 9.4 Brain medical imaging and CNN
  • 9.4.1 Background knowledge on machine learning (ML) and deep learning (DL)
  • 9.4.2 ML-based approaches for AD diagnosis
  • 9.4.3 DL-based approaches for AD diagnosis
  • References
  • 10 An intelligent fractal-dimension-based model for brain-tumor MRI analysis
  • 10.1 Introduction
  • 10.2 Background
  • 10.2.1 Fractal dimension
  • 10.2.2 Tumor detection and MRI images
  • 10.3 Dataset
  • 10.4 Proposed algorithm
  • 10.5 Results and experiment
  • 10.6 Conclusions
  • References
  • 11 Fractal dimension analysis using hybrid RDBC and IDBC for gray scale images
  • 11.1 Introduction
  • 11.2 Literature review
  • 11.2.1 Preliminaries
  • 11.2.1.1 Fractal dimensions (FD)
  • 11.2.1.2 Estimation of fractal dimensions
  • 11.2.1.3 Differential box counting (DBC)
  • 11.2.1.4 Relative differential box counting (RDBC)
  • 11.2.1.5 Improved differential box counting (IDBC)
  • 11.2.2 Issues in the various box-counting methods
  • 11.3 Proposed methodology
  • 11.3.1 Algorithm steps
  • 11.4 Experimental results
  • 11.5 Conclusion
  • References
  • 12 Preliminary analysis and survey of retinal disease diagnosis through identification and segmentation of bright and dark l...
  • 12.1 Introduction
  • 12.2 Retinal imaging modalities
  • 12.3 Fundus imaging
  • 12.3.1 Fundus image formation
  • 12.4 Eye anatomy and retinal diseases
  • 12.4.1 Normal retina
  • 12.4.2 Retinal lesions associated with various retinal diseases
  • 12.5 Current challenges and needs in computer aided retinal disease analysis
  • 12.5.1 Need and challenges in computer aided retinal disease detection method.
  • 12.5.2 Need and challenges in retinal image enhancement
  • 12.5.3 Need and challenges in characterization of anatomical structures and lesions
  • 12.5.3.1 Segmentation of retinal blood vasculature
  • 12.5.3.2 Detection of the optic disk
  • 12.5.3.3 Segmentation of retinal lesions
  • 12.5.4 Need and challenges in computer aided classification and grading method
  • 12.6 State-of-the-art for retinal disease diagnosis
  • 12.7 Conclusions
  • References
  • Index
  • Back Cover.

Documenti analoghi