Hybrid Intelligence for Image Analysis and Understanding.

Cover -- Title Page -- Copyright -- Dedication -- Contents -- Editor Biographies -- List of Contributors -- Foreword -- Preface -- About the Companion website -- Chapter 1 Multilevel Image Segmentation Using Modified Genetic Algorithm (MfGA)-based Fuzzy C-Means -- 1.1 Introduction -- 1.2 Fuzzy C-Means Algorithm -- 1.3 Modified Genetic Algorithms -- 1.4 Quality Evaluation Metrics for Image Segmentation -- 1.4.1 Correlation Coefficient ( ) -- 1.4.2 Empirical Measure Q(I) -- 1.5 MfGA-Based FCM Algorithm -- 1.6 Experimental Results and Discussion -- 1.7 Conclusion -- References -- Chapter 2 Character Recognition Using Entropy-Based Fuzzy C-Means Clustering -- 2.1 Introduction -- 2.2 Tools and Techniques Used -- 2.2.1 Fuzzy Clustering Algorithms -- 2.2.1.1 Fuzzy C-means Algorithm -- 2.2.1.2 Entropy-based Fuzzy Clustering -- 2.2.1.3 Entropy-based Fuzzy C-Means Algorithm -- 2.2.2 Sammon's Nonlinear Mapping -- 2.3 Methodology -- 2.3.1 Data Collection -- 2.3.2 Preprocessing -- 2.3.3 Feature Extraction -- 2.3.4 Classification and Recognition -- 2.4 Results and Discussion -- 2.5 Conclusion and Future Scope of Work -- References -- Appendix -- Chapter 3 A Two-Stage Approach to Handwritten Indic Script Identification -- 3.1 Introduction -- 3.2 Review of Related Work -- 3.3 Properties of Scripts Used in the Present Work -- 3.4 Proposed Work -- 3.4.1 Discrete Wavelet Transform -- 3.4.1.1 Haar Wavelet Transform -- 3.4.2 Radon Transform (RT) -- 3.5 Experimental Results and Discussion -- 3.5.1 Evaluation of the Present Technique -- 3.5.1.1 Statistical Significance Tests -- 3.5.2 Statistical Performance Analysis of SVM Classifier -- 3.5.3 Comparison with Other Related Works -- 3.5.4 Error Analysis -- 3.6 Conclusion -- Acknowledgments -- References -- Chapter 4 Feature Extraction and Segmentation Techniques in a Static Hand Gesture Recognition System.

4.1 Introduction -- 4.2 Segmentation Techniques -- 4.2.1 Otsu Method for Gesture Segmentation -- 4.2.2 Color Space-Based Models for Hand Gesture Segmentation -- 4.2.2.1 RGB Color Space-Based Segmentation -- 4.2.2.2 HSI Color Space-Based Segmentation -- 4.2.2.3 YCbCr Color Space-Based Segmentation -- 4.2.2.4 YIQ Color Space-Based Segmentation -- 4.2.3 Robust Skin Color Region Detection Using K-Means Clustering and Mahalanobish Distance -- 4.2.3.1 Rotation Normalization -- 4.2.3.2 Illumination Normalization -- 4.2.3.3 Morphological Filtering -- 4.3 Feature Extraction Techniques -- 4.3.1 Theory of Moment Features -- 4.3.2 Contour-Based Features -- 4.4 State of the Art of Static Hand Gesture Recognition Techniques -- 4.4.1 Zoning Methods -- 4.4.2 F-Ratio-Based Weighted Feature Extraction -- 4.4.3 Feature Fusion Techniques -- 4.5 Results and Discussion -- 4.5.1 Segmentation Result -- 4.5.2 Feature Extraction Result -- 4.6 Conclusion -- 4.6.1 Future Work -- Acknowledgment -- References -- Chapter 5 SVM Combination for an Enhanced Prediction of Writers' Soft Biometrics -- 5.1 Introduction -- 5.2 Soft Biometrics and Handwriting Over Time -- 5.3 Soft Biometrics Prediction System -- 5.3.1 Feature Extraction -- 5.3.1.1 Local Binary Patterns -- 5.3.1.2 Histogram of Oriented Gradients -- 5.3.1.3 Gradient Local Binary Patterns -- 5.3.2 Classification -- 5.3.3 Fuzzy Integrals-Based Combination Classifier -- 5.3.3.1 g Fuzzy Measure -- 5.3.3.2 Sugeno's Fuzzy Integral -- 5.3.3.3 Fuzzy Min-Max -- 5.4 Experimental Evaluation -- 5.4.1 Data Sets -- 5.4.1.1 IAM Data Set -- 5.4.1.2 KHATT Data Set -- 5.4.2 Experimental Setting -- 5.4.3 Gender Prediction Results -- 5.4.4 Handedness Prediction Results -- 5.4.5 Age Prediction Results -- 5.5 Discussion and Performance Comparison -- 5.6 Conclusion -- References.

Chapter 6 Brain-Inspired Machine Intelligence for Image Analysis: Convolutional Neural Networks -- 6.1 Introduction -- 6.2 Convolutional Neural Networks -- 6.2.1 Building Blocks -- 6.2.1.1 Perceptron -- 6.2.2 Learning -- 6.2.2.1 Gradient Descent -- 6.2.2.2 Back-Propagation -- 6.2.3 Convolution -- 6.2.4 Convolutional Neural Networks: The Architecture -- 6.2.4.1 Convolution Layer -- 6.2.4.2 Pooling Layer -- 6.2.4.3 Dense or Fully Connected Layer -- 6.2.5 Considerations in Implementation of CNNs -- 6.2.6 CNN in Action -- 6.2.7 Tools for Convolutional Neural Networks -- 6.2.8 CNN Coding Examples -- 6.2.8.1 MatConvNet -- 6.2.8.2 Visualizing a CNN -- 6.2.8.3 Image Category Classification Using Deep Learning -- 6.3 Toward Understanding the Brain, CNNs, and Images -- 6.3.1 Applications -- 6.3.2 Case Studies -- 6.4 Conclusion -- References -- Chapter 7 Human Behavioral Analysis Using Evolutionary Algorithms and Deep Learning -- 7.1 Introduction -- 7.2 Human Action Recognition Using Evolutionary Algorithms and Deep Learning -- 7.2.1 Evolutionary Algorithms for Search Optimization -- 7.2.2 Action Bank Representation for Action Recognition -- 7.2.3 Deep Convolutional Neural Network for Human Action Recognition -- 7.2.4 CNN Classifier Optimized Using Evolutionary Algorithms -- 7.3 Experimental Study -- 7.3.1 Evaluation on the UCF50 Data Set -- 7.3.2 Evaluation on the KTH Video Data Set -- 7.3.3 Analysis and Discussion -- 7.3.4 Experimental Setup and Parameter Optimization -- 7.3.5 Computational Complexity -- 7.4 Conclusions and Future Work -- References -- Chapter 8 Feature-Based Robust Description and Monocular Detection: An Application to Vehicle tracking -- 8.1 Introduction -- 8.2 Extraction of Local Features by SIFT and SURF -- 8.3 Global Features: Real-Time Detection and Vehicle Tracking -- 8.4 Vehicle Detection and Validation -- 8.4.1 X-Analysis.

8.4.2 Horizontal Prominent Line Frequency Analysis -- 8.4.3 Detection History -- 8.5 Experimental Study -- 8.5.1 Local Features Assessment -- 8.5.2 Global Features Assessment -- 8.5.3 Local versus Global Features Assessment -- 8.6 Conclusions -- References -- Chapter 9 A GIS Anchored Technique for Social Utility Hotspot Detection -- 9.1 Introduction -- 9.2 The Technique -- 9.3 Case Study -- 9.4 Implementation and Results -- 9.5 Analysis and Comparisons -- 9.6 Conclusions -- Acknowledgments -- References -- Chapter 10 Hyperspectral Data Processing: Spectral Unmixing, Classification, and Target Identification -- 10.1 Introduction -- 10.2 Background and Hyperspectral Imaging System -- 10.3 Overview of Hyperspectral Image Processing -- 10.3.1 Image Acquisition -- 10.3.2 Calibration -- 10.3.3 Spatial and Spectral Preprocessing -- 10.3.4 Dimension Reduction -- 10.3.4.1 Transformation-Based Approaches -- 10.3.4.2 Selection-Based Approaches -- 10.3.5 Postprocessing -- 10.4 Spectral Unmixing -- 10.4.1 Unmixing Processing Chain -- 10.4.2 Mixing Model -- 10.4.2.1 Linear Mixing Model (LMM) -- 10.4.2.2 Nonlinear mixing model -- 10.4.3 Geometrical-Based Approaches to Linear Spectral Unmixing -- 10.4.3.1 Pure Pixel-Based Techniques -- 10.4.3.2 Minimum Volume-Based Techniques -- 10.4.4 Statistics-Based Approaches -- 10.4.5 Sparse Regression-Based Approach -- 10.4.5.1 Moore-Penrose Pseudoinverse (MPP) -- 10.4.5.2 Orthogonal Matching Pursuit (OMP) -- 10.4.5.3 Iterative Spectral Mixture Analysis (ISMA) -- 10.4.6 Hybrid Techniques -- 10.5 Classification -- 10.5.1 Feature Mining -- 10.5.1.1 Feature Selection (FS) -- 10.5.1.2 Feature Extraction -- 10.5.2 Supervised Classification -- 10.5.2.1 Minimum Distance Classifier -- 10.5.2.2 Maximum Likelihood Classifier (MLC) -- 10.5.2.3 Support Vector Machines (SVMs) -- 10.5.3 Hybrid Techniques -- 10.6 Target Detection.

10.6.1 Anomaly Detection -- 10.6.1.1 RX Anomaly Detection -- 10.6.1.2 Subspace-Based Anomaly Detection -- 10.6.2 Signature-Based Target Detection -- 10.6.2.1 Euclidean distance -- 10.6.2.2 Spectral Angle Mapper (SAM) -- 10.6.2.3 Spectral Matched Vilter (SMF) -- 10.6.2.4 Matched Subspace Detector (MSD) -- 10.6.3 Hybrid Techniques -- 10.7 Conclusions -- References -- Chapter 11 A Hybrid Approach for Band Selection of Hyperspectral Images -- 11.1 Introduction -- 11.2 Relevant Concept Revisit -- 11.2.1 Feature Extraction -- 11.2.2 Feature Selection Using 2D PCA -- 11.2.3 Immune Clonal System -- 11.2.4 Fuzzy KNN -- 11.3 Proposed Algorithm -- 11.4 Experiment and Result -- 11.4.1 Description of the Data Set -- 11.4.2 Experimental Details -- 11.4.3 Analysis of Results -- 11.5 Conclusion -- References -- Chapter 12 Uncertainty-Based Clustering Algorithms for Medical Image Analysis -- 12.1 Introduction -- 12.2 Uncertainty-Based Clustering Algorithms -- 12.2.1 Fuzzy C-Means -- 12.2.2 Rough Fuzzy C-Means -- 12.2.3 Intuitionistic Fuzzy C-Means -- 12.2.4 Rough Intuitionistic Fuzzy C-Means -- 12.3 Image Processing -- 12.4 Medical Image Analysis with Uncertainty-Based Clustering Algorithms -- 12.4.1 FCM with Spatial Information for Image Segmentation -- 12.4.2 Fast and Robust FCM Incorporating Local Information for Image Segmentation -- 12.4.3 Image Segmentation Using Spatial IFCM -- 12.4.3.1 Applications of Spatial FCM and Spatial IFCM on Leukemia Images -- 12.5 Conclusions -- References -- Chapter 13 An Optimized Breast Cancer Diagnosis System Using a Cuckoo Search Algorithm and Support Vector Machine Classifier -- 13.1 Introduction -- 13.2 Technical Background -- 13.2.1 Morphological Segmentation -- 13.2.2 Cuckoo Search Optimization Algorithm -- 13.2.3 Support Vector Machines -- 13.3 Proposed Breast Cancer Diagnosis System.

13.3.1 Preprocessing of Breast Cancer Image.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.