
Progress in Computer Recognition Systems
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This book highlights recent research on computer recognition systems, one of the most promising directions in artificial intelligence. Offering the most comprehensive study on this field to date, it gathers 36 carefully selected articles contributed by experts on pattern recognition.
Presenting recent research on methodology and applications, the book offers a valuable reference tool for scientists whose work involves designing computer pattern recognition systems. Its target audience also includes researchers and students in computer science, artificial intelligence, and robotics.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Contents
- Graph Grammar Models in Syntactic Pattern Recognition
- 1 Introduction
- 2 Graph Grammars in Syntactic Pattern Recognition
- 3 Computational Complexity of Graph Parsers
- 4 Graph Parsing Schemes in Syntactic Pattern Recognition
- 5 Concluding Remarks
- References
- Computer Vision Methods for Non-destructive Quality Assessment in Additive Manufacturing
- 1 Introduction
- 2 Vision Based Monitoring of 3D Printing Process
- 3 Quality Assessment of 3D Printed Surfaces
- 3.1 Visual Feedback for Quality Monitoring
- 3.2 Description of Experimental Setup
- 3.3 Overview of Investigated Approaches
- 3.4 Discussion of the Most Essential Results
- 4 Concluding Remarks
- References
- Combined kNN Classifier for Classification of Incomplete Data
- 1 Introduction
- 2 Method
- 3 Experiment
- 4 Results
- 5 Conclusions
- References
- Object Detection in Design Diagrams with Machine Learning
- 1 Introduction
- 2 Related Works
- 3 Yolo for Object Detection in Engineering Drawings
- 3.1 Artificial Apros Experiments
- 3.2 Experiments with Real Pöyry Data
- 4 Learnings
- 5 Conclusions
- References
- Separation of Speech from Speech Interference Based on EGG
- 1 Introduction
- 2 Related Works
- 3 The Proposed System
- 3.1 SUV Separation from Mixture
- 3.2 Voiced Speech Separation
- 3.3 Unvoiced Speech Separation
- 3.4 SUV Re-synthesis
- 4 Dataset
- 5 Experiments and Results
- 5.1 Objective Evaluation Criteria
- 5.2 Subjective Evaluation Measures
- 6 Conclusion
- References
- Improving the Quality of Clustering-Based Diagnostic Rules by Lowering Dimension of the Cluster Prototypes
- 1 Introduction
- 2 Rule-Based Diagnosis Support
- 3 Prototype-Based Rule Premise Conditions
- 4 Experiments
- 5 Discussion and Conclusions
- References
- Exploiting Label Interdependencies in Multi-label Classification
- 1 Introduction
- 2 Related Work
- 3 Materials and Methods
- 3.1 Proposed Approach
- 3.2 Evaluation
- 4 Experiments and Discussion
- 5 Conclusions
- References
- Toward Shareable Multi-abstraction-level Feature Extractor Based on a Bayesian Network
- 1 Introduction
- 1.1 Motivation
- 1.2 Shareable Feature Extractor
- 1.3 Related Work
- 2 Multi-abstraction-level Feature Extractor Using a Bayesian Network (MFB)
- 2.1 Parameter Reduction
- 2.2 Invariance of Pooling by Child
- 3 Experimental Results
- 3.1 Pattern Extraction Experiments
- 3.2 Pooling Layer Training Experiments
- 4 Discussion
- 4.1 Bidirectional Recognition of Multiple Abstraction Features
- 4.2 Pooling Layer Training
- 4.3 Disadvantages of Bidirectional Recognition
- 4.4 Conclusion
- References
- Factorization Machines for Blog Feedback Prediction
- 1 Introduction
- 2 Factorization Machines
- 3 Experimental Evaluation
- 4 Conclusions and Outlook
- References
- Vertical and Horizontal Data Partitioning for Classifier Ensemble Learning
- 1 Introduction
- 2 Ensemble Classification
- 2.1 Generating the Base Experts
- 2.2 Predictions of Experts
- 2.3 Ensemble Pruning
- 2.4 Combination Strategy
- 3 Experimental Study
- 3.1 Experimental Setup
- 3.2 Experimental Results
- 4 Conclusions and Future Work
- References
- Segmentation of Subretinal Hyperreflective Material and Pigment Epithelial Detachment Using Kernel Graph Cut
- 1 Introduction
- 2 Materials and Methods
- 2.1 Graph Cut Based ILM and RPE Layer Segmentation
- 2.2 Classification of PED and SHRM
- 3 Results
- 3.1 Evaluation Metrics
- 3.2 Localization of PED and SHRM
- 4 Conclusion
- References
- Road Tracking Using Deep Reinforcement Learning for Self-driving Car Applications
- 1 Introduction
- 2 Modelling
- 2.1 Road Tracking
- 2.2 Actions Codes
- 2.3 Proposed DRL-RT
- 3 Results
- 3.1 Training and Testing Stages
- 3.2 Comparisons
- 4 Conclusion
- References
- New Heuristics for TCP Retransmission Timers
- 1 Introduction
- 2 Basic Performance Metrics for RTO Algorithms
- 3 The Algorithms
- 4 Results of Experiments
- 5 Conclusions and Final Remarks
- References
- Fault-Prone Software Classes Recognition via Artificial Neural Network with Granular Dataset Balancing
- 1 Introduction
- 2 State of the Art
- 3 Bug Prediction Dataset
- 4 Principal Component Analysis
- 5 Data Imbalance
- 6 Artificial Neural Network
- 7 Cross-Validation
- 8 Experiments
- 9 Performance Measures
- 10 Results
- 11 Conclusions
- References
- Segmentation of Scanned Documents Using Deep-Learning Approach
- 1 Introduction
- 2 Previous Works
- 3 Algorithm Description
- 4 Experiments
- 4.1 Benchmark Datasets
- 4.2 Experimental Setup
- 4.3 Results
- 4.4 Comparison with State-of-the-Art Methods
- 5 Summary
- References
- cGAAM - An Algorithm for Simultaneous Feature Selection and Clustering
- 1 Introduction
- 2 cGAAM
- 3 Methods
- 4 Results and Discussion
- 5 Conclusion
- References
- Online Adaptation of Language Models for Speech Recognition
- 1 Introduction
- 2 Background on Language Model Adaptation for Speech Recognition
- 3 Our Proposed Method
- 3.1 General Pipeline
- 3.2 Constructing Topic-Adapted Language Models
- 3.3 Topic Identification
- 4 Experiments
- 4.1 Dataset for Topic Identification
- 4.2 Training Dataset for Speech Recognition
- 4.3 Test Dataset for Speech Recognition
- 4.4 System Training
- 4.5 Experimental Results and Discussions
- 5 Conclusion
- References
- Pedestrian Detection in Severe Lighting Conditions: Comparative Study of Human Performance vs Thermal-Imaging-Based Automatic System
- 1 Introduction
- 2 Related Works
- 2.1 Driver's Reaction Time
- 2.2 Technical Solutions
- 3 Methods and Material
- 3.1 Characteristics of the Obtained Test Material
- 3.2 Study of Human Reaction
- 3.3 Automatic Recognition of Human Silhouette in Thermograms
- 4 Experimental Results
- 4.1 Human Performance
- 4.2 Performance of Automatic Recognition Using Thermograms
- 5 Discussion
- 6 Conclusion
- References
- Feature Extraction and Classification of Sensor Signals in Cars Based on a Modified Codebook Approach
- 1 Introduction
- 2 Related Work
- 3 Data
- 4 Feature Extraction
- 4.1 Handcrafted Feature Extraction
- 4.2 AFS Based on the Codebook Approach
- 5 Classifier
- 6 Results
- 7 Conclusion and Future Work
- References
- A Deep Learning Approach to Recognition of the Atmospheric Circulation Regimes
- 1 Introduction
- 2 Survey of the Field
- 2.1 Machine Learning in Meteorology
- 2.2 Atmospheric Circulation Classifications
- 3 Modeling
- 3.1 Data
- 3.2 Model Architecture
- 3.3 Model Training
- 4 Results and Discussion
- References
- Deep Learning for Object Tracking in 360 Degree Videos
- 1 Introduction
- 2 Proposed Object Trackers
- 2.1 Image Transformation
- 2.2 Object Detection
- 2.3 Kalman Filter
- 2.4 Lucas-Kanade
- 2.5 Combination of Kalman Filter and Lucas-Kanade
- 3 Results
- 4 Conclusion
- References
- Texture Features for the Detection of Playback Attacks: Towards a Robust Solution
- 1 Introduction
- 2 Databases, Protocols and Data-Related Problems
- 3 Basic Algorithm
- 4 Optimization
- 5 Conclusions
- References
- Image Smoothing Using p Penalty for 0p1 with Use of Alternating Minimization Algorithm
- 1 Introduction
- 2 Solutions
- 2.1 The Case p=0
- 2.2 The Case 0&p&1
- 2.3 The Case p=1, TV Filtering
- 3 Experimental Results
- 3.1 Determining Stopping Criterion for the Gauss-Seidel Method
- 3.2 Denoising Phantom Example
- 3.3 Real Life Examples
- 4 Conclusions and Remarks
- References
- Deep-Based Openset Classification Technique and Its Application in Novel Food Categories Recognition
- 1 Introduction
- 2 Background and Methods
- 2.1 Convolutional Neural Networks
- 2.2 Activation Vector Data Description Model
- 3 Empirical Evaluations
- 3.1 Datasets and Protocol
- 3.2 Results: Performance on Known Classes
- 3.3 Results: Novel Classes Detection
- 4 Conclusions
- References
- Singing Power Ratio Analysis in the Context of the Influence of Warm up on Singing Voice Quality
- 1 Introduction
- 2 Literature Review
- 3 Material for the Study
- 4 Research Background
- 5 The Analysis and the Results
- 6 Conclusion
- References
- Evaluation of a Feature Set with Word Embeddings to Improve Named Entity Recognition on Tweets
- 1 Introduction
- 2 Data and Features
- 2.1 Data
- 2.2 Feature Set
- 3 Tests and Evaluation
- 3.1 Implementation
- 3.2 Test and Results
- 4 Conclusions
- References
- Introducing Action Planning to the Anticipatory Classifier System ACS2
- 1 Introduction
- 2 Anticipatory Learning Classifier Systems (ACS2)
- 3 Action Planning
- 3.1 Goal-Generator
- 3.2 Bidirectional Search
- 4 Experiments
- 4.1 Environments
- 4.2 Results
- 5 Conclusions
- References
- Supervised Classification Box Algorithm Based on Graph Partitioning
- 1 Introduction
- 2 Supervised Classification as a G-cut Problem
- 3 Class Cover Problem by Colored Boxes
- 4 A Minimal Clique Cover Box Algorithm
- 5 Classification Rule Based on Box Algorithm
- 6 Relation of Box Algorithm to the Nearest Neighbor Rule and Tree Classifiers
- 6.1 Relation of Box Algorithm to the Nearest Neighbor Rule
- 6.2 Relation of Box Algorithm to Decision Trees
- 7 Experimental Results
- 7.1 Normal Attributes
- 7.2 Nominal Attributes
- 8 Conclusions
- References
- Algorithm of Multidimensional Analysis of Main Features of PCA with Blurry Observation of Facility Features Detection of Carcinoma Cells Multiple Myeloma
- 1 Introduction
- 2 A Mathematical Model of PCA Analysis with Fuzzy Observation of Object Features
- 3 Practical Examples of Using a Fuzzy PCA Model
- 4 Conclusion
- References
- A New Benchmark Collection for Driver Fatigue Research Based on Thermal, Depth Map and Visible Light Imagery
- 1 Introduction
- 2 Proposed Approach
- 2.1 Characteristics of the Obtained Test Material
- 2.2 Characteristics of the Benchmark
- 2.3 TensorFlow
- 3 Experimental Results
- 4 Summary
- References
- Image Contrast Enhancement Based on Laplacian-of-Gaussian Filter Combined with Morphological Reconstruction
- 1 Introduction
- 2 Related Works
- 3 Basic Notions
- 3.1 Laplacian-of-Gaussian-Based Contrast Enhancement
- 3.2 Morphological Processing
- 4 Proposed Approach
- 5 Tests
- 6 Conclusions
- References
- Lattice Auto-Associative Memories Induced Multivariate Morphology for Hyperspectral Image Spectral-Spatial Classification
- 1 Introduction
- 2 Multivariate Mathematical Morphology
- 3 Lattice Auto-Associative Memories (LAAM)
- 4 LAAM-Supervised Ordering
- 4.1 LAAM's h-Mapping
- 4.2 One-Side LAAM h-Supervised Ordering
- 4.3 Background/Foreground LAAM h-Supervised Pseudo-orderings
- 4.4 Beucher Morphological Gradient
- 4.5 Unsupervised Selection of Training Sets
- 5 Experimental Results with Hyperspectral Images
- 5.1 Methodology
- 5.2 Pavia University Data
- 6 Conclusions
- References
- Randomized Reference Classifier with Gaussian Distribution and Soft Confusion Matrix Applied to the Improving Weak Classifiers
- 1 Introduction
- 2 Proposed Method
- 2.1 Preliminaries
- 2.2 Soft Confusion Matrix
- 2.3 Randomized Reference Classifier
- 3 Experimental Setup
- 4 Results and Discussion
- 5 Conclusions
- References
- Hybrid Algorithm for the Detection and Recognition of Railway Signs
- 1 Introduction
- 2 Research Methodology, Initial Analysis, Implementations and Tests
- 2.1 Classic Image Processing Methods
- 2.2 Haar Algorithm
- 2.3 YOLO
- 3 Hybrid Concept
- 4 Concluding Remarks
- References
- Combination of Linear Classifiers Using Score Function - Analysis of Possible Combination Strategies
- 1 Introduction
- 2 Proposed Method
- 2.1 Linear Binary Classifiers
- 2.2 The Proposed Method
- 3 Experimental Setup
- 4 Results and Discussion
- 5 Conclusions
- References
- Multi Sampling Random Subspace Ensemble for Imbalanced Data Stream Classification
- 1 Introduction
- 2 Related Works
- 3 Multi Sampling Random Subspace Ensemble
- 4 Experiments
- 4.1 Data Streams
- 4.2 Evaluation
- 5 Results
- 5.1 Features Test
- 5.2 Imbalance Ratio Test
- 5.3 Ranking Tests
- 6 Conclusions
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.