Advance Concepts of Image Processing and Pattern Recognition. Effective Solution for Global Challenges

Description

Preface Contents About the Editors 1 Hybrid Evolutionary Technique for Contrast Enhancement of Color Images 1.1 Introduction 1.2 Evolutionary Techniques Background 1.2.1 Artificial Bee Colony (ABC) Technique 1.2.2 Cuckoo Search Algorithm (CSA) 1.3 Proposed Hybrid Image Contrast Enhancement Technique 1.4 Results and Discussion 1.5 Image Quality Measurement 1.6 Image Error Measurement 1.7 Conclusion References 2 Computer Vision for Agro-Foods: Investigating a Method for Grading Rice Grain Quality in Sri Lanka 2.1 Introduction 2.2 Literature Review 2.3 Materials and Methods 2.4 Results 2.5 Conclusion References 3 A Study on Image Restoration and Analysis 3.1 Introduction 3.2 Image Restorations and Analysis 3.2.1 Basic Requirement for Image Restoration and Analysis 3.2.2 Noise Models in Image 3.2.3 Spatial and Frequency Properties 3.3 Operation of Probability Density Function 3.3.1 Gaussian Noise Model 3.3.2 Rayleigh Noise Model 3.3.3 Erlang (Gamma) Noise Model 3.3.4 Exponential Noise Distribution 3.3.5 Impulse (Salt and Pepper) Noise Model 3.4 Problems in Image Enhancement 3.5 Methods Used in Image Restoration 3.5.1 Inverse Filtering 3.5.2 Weiner Filter 3.5.3 Algorithm for Using Weiner Filter 3.5.4 Lucy–Richardson Algorithm 3.5.5 Lucy–Richardson Algorithm 3.5.6 Regularized Filter Used in Image Restoration 3.5.7 Algorithm for Regularized Filter Implement on Sample Image 3.6 Blind Deconvolution for Blur Image 3.6.1 Blind Deconvolution Algorithms for Sample Image 3.6.2 Methodologies Implemented on Blur and Noisy Sample Image 3.6.3 Wavelet Transformation in 2-D 3.6.4 Estimation Method of Signal-to-Noise Ratio (SNR) 3.6.5 Estimation of the Gaussian Point Spread Function (PSF) 3.6.6 Comparison of Mean Square Error (MSE) 3.7 Analysis of the Image Restoration Methods 3.7.1 Mean Square Error (MSE) Comparison 3.7.2 Peak-Signal-to-Noise Ratio (Peak-SNR) Comparison 3.7.3 Signal-to-Noise Ratio (SNR) Comparison 3.8 Conclusion and Feature Work References 4 Application of Deep Learning and Machine Learning in Pattern Recognition 4.1 Introduction 4.2 Literature Review 4.3 Pattern Recognition (PR) Problem 4.3.1 Pattern Recognition (PR) Process 4.3.2 Loop-Back Routes Between Stages 4.3.3 Training Data, Testing Data, and Algorithms 4.4 Artificial Intelligence Techniques for Pattern Recognition 4.4.1 Machine Learning (ML) Techniques 4.4.2 Deep Learning (DL) Techniques 4.5 Component of Pattern Recognition (PR) System in Real World 4.6 Scope and Applications of PR in Different Domains 4.7 Important PR Tools Used in Recent Times 4.8 Summary and Conclusion References 5 Brain Tumor Classification Using Hybrid Artificial Neural Network with Chicken Swarm Optimization Algorithm in Digital Image Processing Application 5.1 Introduction 5.2 Literature Review 5.3 System Design 5.3.1 Preprocessing 5.3.2 Segmentation 5.3.3 Feature Extraction 5.3.4 Classification 5.4 Result and Discussion 5.5 Conclusion 5.6 Research Scope References 6 Detection and Classification of Breast Cancer Using CNN 6.1 Introduction 6.2 Literature Survey 6.3 Methodology 6.3.1 Dataset Description 6.3.2 System Architecture 6.3.3 Data Collection 6.3.4 Preprocessing 6.3.5 CNN Model Design 6.3.6 Training and Testing 6.4 Result and Discussion 6.5 Conclusion References 7 De-Noising of Poisson Noise Corrupted CT Images by Using Modified Anisotropic Diffusion-Based PDE Filter 7.1 Introduction 7.2 General Frame for CT Image Restoration 7.2.1 MAP Methodology 7.2.2 Minimization Framework 7.2.3 Methods and Models 7.2.4 Anisotropic Diffusion (Yu and Acton 2002)-Based Method 7.2.5 Digitization of the Proposed Model 7.3 Results and Discussions 7.4 Conclusion References 8 Computer-Aided Diabetic Retinopathy Diagnosis Using Conventional and Deep Learning Techniques—A Comparison 8.1 Introduction 8.2 Deep Learning 8.2.1 Deep Learning Applications 8.2.2 Deep Learning in Medical Image Processing 8.2.3 Convolutional Neural Network (CNN) 8.3 Diabetic Eye Diseases 8.3.1 Diabetic Retinopathy 8.3.2 Diabetic Macular Edema (DME) 8.3.3 Glaucoma 8.3.4 Cataracts 8.4 A Review on Retinal Image Databases 8.5 Diagnosing Diabetic Eye Diseases 8.5.1 Diagnosing Without Deep Learning Techniques 8.5.2 Diagnosing with Deep Learning Techniques 8.6 Statistical Comparisons on with and Without Using Deep Learning Techniques 8.7 Future Directions 8.8 Conclusion References 9 Speckle Reduction in Ultrasound Images Using Hybridization of Wavelet-Based Novel Thresholding Approach with Guided Filter 9.1 Introduction 9.2 Literature Survey 9.3 Wavelet Thresholding 9.4 Guided Filter 9.5 Proposed Hybrid Method 9.6 Experimental Setup 9.6.1 Synthetic Images (Test Image-1) 9.6.2 Kidney Phantom (Test Image-2) and Cyst Phantom (Test Image-3) 9.6.3 Real Ultrasound Images (Test Image-4) 9.7 Image Quality Metrics 9.8 Experiment Results and Discussions for Synthetic Images (Test Image-1) 9.9 Experiment Results for Kidney Phantom (Test Image-2) 9.10 Experiment Results and Discussions for Cyst Phantom (Test Image-4) 9.11 Experiment Results and Discussions for Real Ultrasound Images (Test Image-4) 9.12 Conclusion References 10 Poisson Noise-Adapted Total Variation-Based Filter for Restoration and Enhancement of Mammogram Images 10.1 Introduction 10.2 Numerical Result 10.3 Results 10.4 Conclusion References 11 Implementation of Mathematical Morphology Technique in Binary and Grayscale Image 11.1 Introduction 11.2 System Model 11.2.1 Dilation 11.2.2 Erosion 11.2.3 Opening and Closing 11.3 Simulation Results 11.4 Conclusion References 12 Design of Advanced Security System Using Vein Pattern Recognition and Image Segmentation Techniques 12.1 Introduction 12.2 Related Works 12.3 Methodology 12.4 Proposed System 12.5 Results and Discussion 12.6 Conclusion References