
Pattern Recognition Applications and Methods
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This book contains revised and extended versions of selected papers from the 5th International Conference on Pattern Recognition, ICPRAM 2016, held in Rome, Italy, in February 2016.
The 13 full papers were carefully reviewed and selected from 125 initial submissions and describe up-to-date applications of pattern recognition techniques to real-world problems, interdisciplinary research, experimental and/or theoretical studies yielding new insights that advance pattern recognition methods.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents
- Experimental Evaluation of Graph Classification with Hadamard Code Graph Kernels
- 1 Introduction
- 2 Graph Kernels
- 2.1 Framework of Representative Graph Kernels
- 2.2 Drawbacks of Existing Graph Kernels
- 3 Graph Kernels Based on the Hadamard Code
- 4 Experimental Evaluation
- 4.1 Experiments on Artificial Datasets
- 4.2 Experiments on Real-World Graphs
- 4.3 Effect of Assignment of Initial Labels
- 5 Conclusion
- References
- Document Clustering Games in Static and Dynamic Scenarios
- 1 Introduction
- 2 Game Theory
- 3 Dominant Set Clustering
- 4 Document Clustering Games
- 4.1 Document Representation
- 4.2 Data Preparation
- 4.3 Graph Construction
- 4.4 Clustering
- 4.5 Strategy Space Implementation
- 4.6 Clustering Games
- 5 Experimental Setup
- 5.1 Basic Experiments
- 5.2 Experiments with Feature Selection
- 5.3 Experiments with LSA
- 5.4 Comparison with State-of-the-Art Algorithms
- 5.5 Experiments with No Cluster Number
- 5.6 Experiments on Streaming Data
- 6 Conclusions
- References
- Criteria for Mixture-Model Clustering with Side-Information
- 1 Introduction
- 2 Clustering with Side-Information
- 2.1 Data Description
- 2.2 Mixture Model
- 3 Criteria
- 3.1 Criterion BIC
- 3.2 Criterion AIC
- 3.3 Criterion NEC
- 4 Results
- 4.1 Comparison of the Original and Adapted Versions of the Three Criteria
- 4.2 Influence of the Amount of Side-Information
- 4.3 Iris Data Set
- 4.4 Climatic Data
- 5 Conclusion
- References
- Near-Boolean Optimization: A Continuous Approach to Set Packing and Partitioning
- 1 Introduction
- 2 Set Partitioning: Full-Dimensional Case
- 3 Set Packing: Lower-Dimensional Case
- 4 Local Search
- 5 Near-Boolean Functions
- 5.1 Approximations
- 5.2 Equivalent Polynomials
- 5.3 MLE of Partition Functions
- 6 Near-Boolean Games
- 7 Conclusions
- References
- Approximate Inference in Related Multi-output Gaussian Process Regression
- 1 Introduction
- 2 Gaussian Process Regression
- 3 Multi-output Gaussian Process
- 3.1 Related Work
- 3.2 Multi-output Joint-Covariance Kernels
- 3.3 GP Regression Using Joint-Covariance
- 4 Approximating Inference
- 4.1 Variational Approximation on Multi-output GP
- 4.2 Distributed Inference on Multi-output GP
- 5 Experiments
- 5.1 Experiments on Theoretical Data
- 5.2 Experiments on Flight Test Data
- 6 Conclusions and Future Work
- References
- An Online Data Validation Algorithm for Electronic Nose
- 1 Introduction
- 1.1 Background
- 1.2 Motivation
- 1.3 Data Preparation
- 2 Data Analysis
- 3 Simulation
- 4 Experiment
- 5 Computational Complexity
- 6 Conclusion
- References
- Near-Duplicate Retrieval: A Benchmark Study of Modified SIFT Descriptors
- 1 Introduction
- 2 Near-Duplicate Images
- 3 Related Works
- 3.1 SIFT-128 D Descriptor
- 4 Region Compressed SIFT Descriptor
- 5 Evaluation
- 5.1 Benchmark Datasets
- 5.2 Evaluation Measures
- 6 Result and Analysis
- 6.1 UKbench Benchmark
- 6.2 Caltech-Buildings Benchmark
- 6.3 Combination of Image Affine Transformations
- 6.4 Combination of Blurring and Affine Transformation
- 7 Conclusion
- References
- Activity Recognition for Elderly Care by Evaluating Proximity to Objects and Human Skeleton Data
- 1 Introduction
- 2 Related Work
- 3 Activity Recognition Based on Proximity to Objects and Pose Information
- 3.1 Person Localisation
- 3.2 Pose Information
- 3.3 High-Level Reasoning Using Position and Pose Information
- 3.4 Analysis Method
- 3.5 Results and Discussion
- 4 System Enhancement with Skeleton-Based Activity Recognition
- 4.1 Actions
- 4.2 Sequence Duration and Frame Skipping
- 4.3 Feature Vectors
- 4.4 Results and Discussion
- 5 Conclusions and Future Work
- References
- Real-Time Swimmer Tracking on Sparse Camera Array
- 1 Introduction
- 2 Literature Review
- 3 The Site and the System Description
- 3.1 The Site
- 3.2 System
- 4 Planar Projection
- 4.1 Pre-computation and Post-computation
- 4.2 Error Analysis
- 4.3 Effect of Inaccurate Camera Placement to Traditional Calibration
- 5 Silhouette Tracking
- 6 Swimming Cycle Registration
- 7 Conclusions
- References
- Fundamentals of Nonparametric Bayesian Line Detection
- 1 Introduction
- 2 Bayesian Nonparametrics
- 3 Dirichlet Process
- 3.1 Dirichlet Mixture Model
- 3.2 Gibbs Sampling of Parameters
- 3.3 Gibbs Sampling of Clusters
- 4 Infinite Line Mixture Model
- 4.1 Bayesian Linear Regression Model
- 4.2 Conjugate Prior for the Bayesian Linear Regression Model
- 4.3 Implementation of Gibbs Sampling of Parameters
- 4.4 Implementation of Gibbs Sampling of Clusters
- 5 Results
- 5.1 Clustering Performance
- 5.2 Two Examples
- 6 Conclusions
- References
- Computing the Number of Bubbles and Tunnels of a 3-D Binary Object
- Abstract
- 1 Introduction
- 2 Problem Statement
- 3 Related Work
- 3.1 Pioneers Works
- 3.2 Recent Works
- 4 Definitions
- 5 The Proposal: Theoretical Part
- 5.1 Number of Bubbles of a 3-D Object
- 5.2 Number of Tunnels of a 3-D Object
- 6 The Proposal: Practical Part
- 6.1 Procedure to Compute the Number of Bubbles and Tunnels of a 3-D Object
- 6.2 Procedure to Compute the Number of Bubbles and Tunnels of a Set of 3-D Objects
- 7 Results and Discussion
- 7.1 First Experiment
- 7.2 Second Experiment
- 7.3 Third Experiment
- 7.4 Fourth Experiment
- 8 Conclusions and Directions for Further Research
- Acknowledgements
- References
- Raindrop Detection on a Windshield Based on Edge Ratio
- 1 Introduction
- 2 Raindrop Detection Method
- 2.1 Raindrop Detection in the Daytime
- 2.2 Raindrop Detection at Night
- 3 Experiments
- 4 Conclusion
- References
- Comparative Analysis of PRID Algorithms Based on Results Ambiguity Evaluation
- 1 Introduction
- 2 Methodology
- 2.1 Algorithm Description
- 2.2 Pre-processing Step
- 2.3 Post-processing Steps
- 3 Experiments and Results
- 4 Conclusion
- 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.