Linked e-resources
Details
Table of Contents
Intro; Preface; Contents; Computer Vision; 1 Denoising of Ultrasound Medical Images Using the DM6437 High-Performance Digital Media Processor; Abstract; 1.1 Introduction; 1.2 Literature Review; 1.3 Methods; 1.3.1 Ultrasound Image Formation; 1.3.1.1 B-Mode; 1.3.1.2 Speckle Noise; 1.3.2 Despeckling Filters; 1.3.2.1 Median Filter; 1.3.2.2 Lee Filter; 1.3.2.3 Kuan Filter; 1.3.2.4 Frost Filter; 1.3.2.5 SRAD Filter; 1.3.3 Description of the TMS320DM6437 Digital Media Processor; 1.3.3.1 DSP Core Description; 1.3.3.2 Evaluation Module; 1.3.3.3 Memory Map; 1.3.4 Metrics; 1.4 Results
1.4.1 Experiments on Synthetic Data1.4.2 Experiments on Real Data; 1.5 Conclusions; References; 2 Morphological Neural Networks with Dendritic Processing for Pattern Classification; Abstract; 2.1 Introduction; 2.2 Basics on MNNDPs; 2.3 Training Algorithms; 2.3.1 Elimination and Merging Methods; 2.3.1.1 Elimination Method; 2.3.1.2 Merging Method; 2.3.2 Divide and Conquer Methods; 2.3.2.1 Divide and Conquer Method; 2.3.2.2 Linear Divide and Conquer Method; 2.3.3 Evolutionary-Based Methods; 2.3.4 Other Related Works; 2.4 Comparison; 2.4.1 Results with Synthetic Data; 2.4.2 Results with Real Data
2.5 Summary, Conclusions, and Present and Future ResearchAcknowledgements; References; 3 Mobile Augmented Reality Prototype for the Manufacturing of an All-Terrain Vehicle; Abstract; 3.1 Introduction; 3.2 All-Terrain Vehicles; 3.3 Literature Review; 3.4 Proposed Methodology; 3.4.1 Selection of Development Tools; 3.4.2 Selection and Design of 3D Models; 3.4.3 Markers Design; 3.4.4 Development of the MAR Application; 3.4.4.1 Welding Inspection; 3.4.4.2 Measuring Critical Dimensions; 3.4.4.3 Accessories Mounting; 3.4.5 GUI Design; 3.4.5.1 Scene Creation in Unity; 3.5 Experimental Results
3.5.1 Scope of Markers Detection3.5.2 Survey for Users; 3.5.3 Discussion; 3.6 Conclusions; References; 4 Feature Selection for Pattern Recognition: Upcoming Challenges; Abstract; 4.1 Introduction; 4.2 Theoretical Context and State of the Art; 4.2.1 Statistical-Based Methods for Feature Selection; 4.2.1.1 Statistical Measures; 4.2.1.2 Statistical-Based Methods: State of the Art; 4.2.2 Information Theory-Based Methods; 4.2.2.1 Basic Concepts; 4.2.2.2 Information Theory-Based Methods: State of the Art; 4.2.3 Similarity-Based Methods; 4.2.3.1 Similarity-Basic Concepts
4.2.3.2 Similarity-Based Methods: State of the Art4.2.4 Neural Networks-Based Feature Selection; 4.2.4.1 Basic Concepts; 4.2.4.2 Artificial Neural Networks Methods for Feature Selection: State of the Art; 4.2.5 Sparse Learning Methods for Feature Selection; 4.2.5.1 Introductory Concepts; 4.2.5.2 Sparse Learning-Based Methods: State of the Art; 4.3 Summary of Methods and Their Capability to Handle Chronologically Linked Data; 4.4 Upcoming Challenges; 4.4.1 Characteristics of Chronologically Linked Data; 4.4.2 Challenges for Feature Selection Algorithms; 4.5 Conclusions; References
1.4.1 Experiments on Synthetic Data1.4.2 Experiments on Real Data; 1.5 Conclusions; References; 2 Morphological Neural Networks with Dendritic Processing for Pattern Classification; Abstract; 2.1 Introduction; 2.2 Basics on MNNDPs; 2.3 Training Algorithms; 2.3.1 Elimination and Merging Methods; 2.3.1.1 Elimination Method; 2.3.1.2 Merging Method; 2.3.2 Divide and Conquer Methods; 2.3.2.1 Divide and Conquer Method; 2.3.2.2 Linear Divide and Conquer Method; 2.3.3 Evolutionary-Based Methods; 2.3.4 Other Related Works; 2.4 Comparison; 2.4.1 Results with Synthetic Data; 2.4.2 Results with Real Data
2.5 Summary, Conclusions, and Present and Future ResearchAcknowledgements; References; 3 Mobile Augmented Reality Prototype for the Manufacturing of an All-Terrain Vehicle; Abstract; 3.1 Introduction; 3.2 All-Terrain Vehicles; 3.3 Literature Review; 3.4 Proposed Methodology; 3.4.1 Selection of Development Tools; 3.4.2 Selection and Design of 3D Models; 3.4.3 Markers Design; 3.4.4 Development of the MAR Application; 3.4.4.1 Welding Inspection; 3.4.4.2 Measuring Critical Dimensions; 3.4.4.3 Accessories Mounting; 3.4.5 GUI Design; 3.4.5.1 Scene Creation in Unity; 3.5 Experimental Results
3.5.1 Scope of Markers Detection3.5.2 Survey for Users; 3.5.3 Discussion; 3.6 Conclusions; References; 4 Feature Selection for Pattern Recognition: Upcoming Challenges; Abstract; 4.1 Introduction; 4.2 Theoretical Context and State of the Art; 4.2.1 Statistical-Based Methods for Feature Selection; 4.2.1.1 Statistical Measures; 4.2.1.2 Statistical-Based Methods: State of the Art; 4.2.2 Information Theory-Based Methods; 4.2.2.1 Basic Concepts; 4.2.2.2 Information Theory-Based Methods: State of the Art; 4.2.3 Similarity-Based Methods; 4.2.3.1 Similarity-Basic Concepts
4.2.3.2 Similarity-Based Methods: State of the Art4.2.4 Neural Networks-Based Feature Selection; 4.2.4.1 Basic Concepts; 4.2.4.2 Artificial Neural Networks Methods for Feature Selection: State of the Art; 4.2.5 Sparse Learning Methods for Feature Selection; 4.2.5.1 Introductory Concepts; 4.2.5.2 Sparse Learning-Based Methods: State of the Art; 4.3 Summary of Methods and Their Capability to Handle Chronologically Linked Data; 4.4 Upcoming Challenges; 4.4.1 Characteristics of Chronologically Linked Data; 4.4.2 Challenges for Feature Selection Algorithms; 4.5 Conclusions; References