The book comprehensively covers a wide range of evolutionary computer vision methods and applications, feature selection and extraction for training and classification, and metaheuristic algorithms in image processing. It further discusses optimized image segmentation, its analysis, pattern recognition, and object detection.Features:Discusses machine learning-based analytics such as GAN networks, autoencoders, computational imaging, and quantum computing.The book aims to get the readers familiar with the fundamentals of computational intelligence as well as the recent advancements in related technologies like smart applications of digital images, and other enabling technologies from the context of image processing and computer vision. It further covers important topics such as image watermarking, steganography, morphological processing, and optimized image segmentation. It will serve as an ideal reference text for senior undergraduate, graduate students, and academic researchers in fields including electrical engineering, electronics, communications engineering, and computer engineering.Covers deep learning algorithms in computer vision.Showcases novel solutions such as multi-resolution analysis in imaging processing, and metaheuristic algorithms for tackling challenges associated with image processing.Highlight optimization problems such as image segmentation and minimized feature design vector.Presents platform and simulation tools for image processing and segmentation.
Author(s): Nitin Mittal, Amit Kant Pandit, Mohamed Abouhawwash, Shubham Mahajan
Publisher: Routledge
Year: 2023
Language: English
Pages: 341
Cover
Half Title
Title Page
Copyright Page
Table of Contents
About the Editors
List of Contributors
Chapter 1 A Review Approach On Deep Learning Algorithms in Computer Vision
1.1 Introduction
1.2 Deep Learning Algorithms
1.2.1 Convolutional Neural Networks
1.2.2 Restricted Boltzmann Machines
1.2.3 Deep Boltzmann Machines
1.2.4 Deep Belief Networks
1.2.5 Stacked (de-Noising) Auto-Encoders
1.2.5.1 Auto-Encoders
1.2.5.2 Denoising Auto Encoders
1.3 Comparison of the Deep Learning Algorithms
1.4 Challenges in Deep Learning Algorithms
1.5 Conclusion and Future Scope
References
Chapter 2 Object Extraction From Real Time Color Images Using Edge Based Approach
2.1 Introduction
2.2 Applications of Object Extraction
2.3 Edge Detection Techniques
2.3.1 Roberts Edge Detection
2.3.2 Sobel Edge Detection
2.3.3 Prewitt’s Operator
2.3.4 Laplacian Edge Detection
2.4 Related Work
2.5 Proposed Model
2.6 Results and Discussion
2.7 Conclusion
References
Chapter 3 Deep Learning Techniques for Image Captioning
3.1 Introduction to Image Captioning
3.1.1 How Does Image Recognition Work?
3.2 Introduction to Deep Learning
3.2.1 Pros of the Deep Learning Algorithm
3.2.2 Customary / Traditional CV Methodology
3.2.3 Limitations/challenges of Traditional CV Methodology
3.2.4 Overcome the Limitations of Deep Learning
3.3 Deep Learning Algorithms for Object Detection
3.3.1 Types of Deep Models for Object Detection
3.4 How Image Captioning Works
3.4.1 Transformer Based Image Captioning
3.4.2 Visual Scene Graph Based Image Captioning
3.4.3 Challenges in Image Captioning
3.5 Conclusion
References
Chapter 4 Deep Learning-Based Object Detection for Computer Vision Tasks: A Survey of Methods and Applications
4.1 Introduction
4.2 Object Detection
4.3 Two-Stage Object Detectors
4.3.1 R-CNN
4.3.2 SPPNet
4.3.3 Fast RCNN
4.3.4 Faster RCNN
4.3.5 R-FCN
4.3.6 FPN
4.3.7 Mask RCNN
4.3.8 G-RCNN
4.4 One-Stage Object Detectors
4.4.1 YOLO
4.4.2 CenterNet
4.4.3 SSD
4.4.4 RetinaNet
4.4.5 EfficientDet
4.4.6 YOLOR
4.5 Discussion On Model Performance
4.5.1 Future Trends
4.6 Conclusion
References
Chapter 5 Deep Learning Algorithms for Computer Vision: A Deep Insight Into Principles and Applications
5.1 Introduction
5.2 Preliminary Concepts of Deep Learning
5.2.1 Artificial Neural Network
5.2.2 Convolution Neural Network (CNNs)
5.3 Recurrent Neural Network (RNNs)
5.4 Overview of Applied Deep Learning in Computer Vision
5.6 Industrial Applications of Computer Vision
5.7 Future Scope in Computer Vision
5.8 Conclusion
References
Chapter 6 Handwritten Equation Solver Using Convolutional Neural Network
6.1 Introduction
6.2 State-Of-The-Art
6.3 Convolutional Neural Network
6.3.1 Convolution Layer
6.3.2 Pooling Layer
6.3.3 Fully Connected Layer
6.3.4 Activation Function
6.4 Handwritten Equation Recognition
6.4.1 Dataset Preparation
6.4.2 Proposed Methodology
6.4.2.1 Dataset Acquisition
6.4.2.2 Preprocessing
6.4.2.3 Recognition Through CNN Model
6.4.2.4 Processing Inside CNN Model
6.4.3 Solution Approach
6.5 Results and Discussion
6.6 Conclusion and Future Scope
References
Chapter 7 Agriware: Crop Suggester System By Estimating the Soil Nutrient Indicators
7.1 Introduction
7.2 Related Work
7.3 Proposed Methodology
7.4 Experimental Results and Discussion
7.5 Conclusion and Future Work
References
Chapter 8 A Machine Learning Based Expeditious Covid-19 Prediction Model Through Clinical Blood Investigations
8.1 Introduction
8.2 Literature Survey
8.3 Methodology
8.3.1 Dataset and Its Preparation
8.3.2 Classification Set Up
8.3.3 Performance Evaluation
8.4 Results and Discussion
8.5 Conclusion
References
Chapter 9 Comparison of Image Based and Audio Based Techniques for Bird Species Identification
9.1 Introduction
9.2 Literature Survey
9.3 Methodology
9.4 System Design
9.4.1 Dataset Used
9.4.2 Image Based Techniques
9.4.3 Audio Based Techniques
9.5 Results and Analysis
9.6 Conclusion
References
Chapter 10 Detection of Ichthyosis Vulgaris Using SVM
10.1 Introduction
10.2 Literature Survey
10.3 Types of Ichthyosis
10.3.1 Ichthyosis Vulgaris
10.3.2 Hyperkeratosis
10.4 Sex-Connected Ichthyosis
10.5 Symptoms
10.6 Complications
10.7 Diagnosis
10.8 Methodology
10.9 Results
10.10 Future Work
10.11 Conclusion
References
Chapter 11 Chest X-Ray Diagnosis and Report Generation: Deep Learning Approach
11.1 Introduction
11.2 Literature Review
11.3 Proposed Methodology
11.3.1 Overview of Deep Learning Algorithms
11.3.2 Data
11.3.3 Feature Extraction
11.3.4 Report Generation
11.3.5 Evaluation Metrics
11.4 Results and Discussions
11.4.1 Feature Extraction
11.4.2 Report Generation
11.5 Conclusion
References
Chapter 12 Deep Learning Based Automatic Image Caption Generation for Visually Impaired People
12.1 Introduction
12.2 Related Work
12.3 Methods and Materials
12.3.1 Data Set
12.3.2 Deep Neural Network Architectures
12.3.2.1 Convolution Neural Networks (CNNs)
12.3.2.2 Long Short-Term Memory (LSTM)
12.3.3 Proposed Model
12.3.3.1 Feature Extraction Models
12.3.3.2 Workflow for Image Caption Generation
12.4 Results and Discussion
12.4.1 Evaluation Metrics
12.4.2 Analysis of Results
12.4.3 Examples
12.5 Discussion and Future Work
12.6 Conclusions
References
Chapter 13 Empirical Analysis of Machine Learning Techniques Under Class Imbalance and Incomplete Datasets
13.1 Introduction
13.2 Related Work
13.2.1 Class Imbalance
13.2.2 Missing Values
13.2.3 Missing Value in Class Imbalance Datasets
13.3 Methodology
13.4 Results
13.4.1 Overall Performance
13.4.2 Effect of Class Imbalance and Missing Values
13.5 Conclusion
References
Chapter 14 Gabor Filter as Feature Extractor in Anomaly Detection From Radiology Images
14.1 Introduction
14.2 Literature Review
14.3 Research Methodology
14.3.1 Data Set
14.3.2 Gabor Filter
14.4 Results
14.5 Discussion
14.6 Conclusion
References
Chapter 15 Discriminative Features Selection From Zernike Moments for Shape Based Image Retrieval System
15.1 Introduction
15.2 Zernike Moments Descriptor (ZMD)
15.2.1 Zernike Moments (ZMs)
15.2.2 Orthogonality
15.2.3 Rotation Invariance
15.2.4 Features Selection
15.3 Discriminative Features Selection
15.4 Similarity Measure
15.5 Experimental Study
15.5.1 Experiment Setup
15.5.2 Performance Measurement
15.5.3 Experiment Results
15.6 Discussions and Conclusions
References
Chapter 16 Corrected Components of Zernike Moments for Improved Content Based Image Retrieval: A Comprehensive Study
16.1 Introduction
16.2 Proposed Descriptors
16.2.1 Invariant Region Based Descriptor Using Corrected ZMs Features
16.2.2 Selection of Appropriate Features
16.2.3 Invariant Contour Based Descriptor Using HT
16.3 Similarity Metrics
16.4 Experimental Study and Performance Evaluation
16.4.1 Measurement of Retrieval Accuracy
16.4.2 Performance Comparison and Experiment Results
16.5 Discussion and Conclusion
References
Chapter 17 Translate and Recreate Text in an Image
17.1 Introduction
17.2 Literature Survey
17.3 Existing System
17.4 Proposed System
17.4.1 Flow Chart
17.4.2 Experimental Setup
17.4.3 Dataset
17.4.4 Text Detection and Extraction
17.4.5 Auto Spelling Correction
17.4.6 Machine Translation and Inpainting
17.5 Implementation
17.5.1 Text Detection and Extraction
17.5.2 Auto Spelling Correction
17.5.2.1 Simple RNN
17.5.2.2 Embed RNN
17.5.2.3 Bidirectional LSTM
17.5.2.4 Encoder Decoder With LSTM
17.5.2.5 Encoder Decoder With Bidirectional LSTM + Levenshtein Distance
17.5.3 Machine Translation
17.5.4 Inpainting
17.6 Result Analysis
17.6.1 Simple RNN
17.6.2 Embed RNN
17.6.3 Bidirectional LSTM
17.6.4 Encoder Decoder With LSTM
17.6.5 Encoder Decoder With Bidirectional LSTM + Levenshtein Distance
17.6.6 BLEU (Bilingual Evaluation Understudy)
17.7 Conclusion
Acknowledgments
References
Chapter 18 Multi-Label Indian Scene Text Language Identification: Benchmark Dataset and Deep Ensemble Baseline
18.1 Introduction
18.2 Related Works
18.3 IIITG-MLRIT2022
18.4 Proposed Methodology
18.4.1 Transfer Learning
18.4.1.1 ResNet50 [37]
18.4.1.2 XceptionNet [39]
18.4.1.3 DenseNet [38]
18.4.1.4 MobileNetV2 [36]
18.4.2 Convolutional Neural Network
18.4.3 Multi-Label Deep Ensemble Via Majority Voting
18.4.4 Weighted Binary Cross Entropy
18.5 Training and Experiment
18.6 Results and Discussion
18.7 Conclusion
References
Chapter 19 AI Based Wearables for Healthcare Applications: A Survey of Smart Watches
19.1 Introduction
19.2 Systematic Review
19.2.1 Criterion to Select Research
19.2.2 Source of Information
19.2.2.1 Search Plan
19.2.2.2 Data Abstraction
19.2.3 Outcomes
19.2.4 Healthcare Applications
19.2.4.1 Activity and Human Motion
19.2.4.2 Healthcare Education
19.2.5 Ideal Smart watch Characteristics
19.2.5.1 Operating System
19.2.5.2 Sensors
19.3 Discussion
19.4 Concluding Remarks
References
Chapter 20 Nature Inspired Computing for Optimization
20.1 Introduction
20.2 Components of Nature-Inspired Computing
20.2.1 Fuzzy Logic Based Computing
20.2.2 Artificial Neural Networks
20.2.3 Search and Optimization Approaches
20.2.3.1 Evolutionary Computing
20.3 Swarm Intelligence
20.3.1 Particle Swarm Optimization (PSO)
20.3.2 Ant Colony Optimization (ACO)
20.3.3 Artificial Bee Colony (ABC)
20.4 Physics Or Chemistry-Based Search and Optimization Approaches
20.4.1 Intelligent Water Drops Algorithm (IWD)
20.4.2 EM (Electromagnetism-Like Mechanism) Algorithm
20.4.3 Gravitational Search Algorithm (GSA)
20.5 Conclusion
References
Chapter 21 Automated Smart Billing Cart for Fruits
21.1 Introduction
21.2 Literature Survey
21.3 Proposed Method
21.3.1 System Design
21.4 Implementation
21.5 Results and Discussions
21.6 Results
21.7 Conclusion
References
Index
