Pattern Recognition and Image Analysis

Name: Pattern Recognition and Image Analysis | 5th Iberian Conference, IbPRIA 2011, Las Palmas de Gran Canaria, Spain, June 8-10, 2011. Proceedings
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

5th Iberian Conference, IbPRIA 2011, Las Palmas de Gran Canaria, Spain, June 8-10, 2011. Proceedings

Jordi Vitria Joao Miguel Sanches Mario Hernández(Editor)

Springer (Publisher)

Published on 18. June 2011

XXI, 754 pages

E-Book

PDF with digital watermarking

System requirements

978-3-642-21257-4 (ISBN)

€96.29incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Title
Preface
Organization
Table of Contents
Oral Sessions
Computer Vision
Deforming the Blurred Shape Model for Shape Description and Recognition
Introduction
Background
Blurred Shape Model
Image Distortion Model
Deformable Blurred Shape Model (DBSM)
DBSM Focus Representation
Deformation Process
Experiments
Datasets
Results and Analysis
Conclusions
References
A Shortest Path Approach for Vibrating Line Detection and Tracking
Introduction
Line Detection and Tracking
Line Detection Using a Shortest Path Approach
Design of the Weight Function.
Detecting Vibrating Lines in Different Positions.
Line Tracking
Validation of the Proposed Approach
Dataset
Line Detection Assessment
Tracking Assessment
Results
Conclusions
References
And-Or Graph Grammar for Architectural Floor Plan Representation, Learning and Recognition. A Semantic, Structural and Hierarchical Model
Introduction
Syntactic Model
Model Definition
Model Learning
Model Recognition
Components Extraction
Patch Level Extraction Approach for Windows Detection
Region Level Extraction Approach for Rooms Detection
Results
Conclusions
References
Linear Prediction Based Mixture Models for Event Detection in Video Sequences
Introduction
Linear Predictor Mixtures
Linear Predictors and Linear Prediction Error Filters
Mixture Model and Detection of Events
Parameter Estimation
Experiments and Discussion
Comparison to GMMs and HMMs on Synthetic Data
Car Tracking and Event Detection
Conclusion and Outlook
References
A Visual Saliency Map Based on Random Sub-window Means
Introduction
Literature Review
Our Method
Results
Experiments with the MSR Dataset
Experiments Using Eye Fixation Datasets
Discussion and Conclusion
References
There Is More Than OneWay to Get Out of a Car: Automatic Mode Finding for Action Recognition in the Wild
Introduction
Related Work
Action Modes
Automatic Grouping Using Random Sampling Consensus
Sub-category Selection
Experimental Setup
Results
Conclusion
References
The Fast and the Flexible: Extended Pseudo Two-Dimensional Warping for Face Recognition
Introduction
Image Warping
Pseudo Two-Dimensional Warping (P2DW)
Extended Pseudo-2D Warping
Results
Conclusion
References
On Importance of Interactions and Context in Human Action Recognition
Introduction
Human Action Recognition
Pose Estimation
Scene Model
Spatial Interaction
Local Interaction.
Global Interaction.
Classification
Experimental Results
Conclusions and Future Work
References
Detection Performance Evaluation of Boosted Random Ferns
Introduction
The Approach
Boosted Random Ferns
The Bootstrapping Phase
Experiments
Training Data
Bootstrapping Image Samples
Freestyle Motocross Dataset
Conclusions
References
Feature Selection for Gender Classification
Introduction
Information-Theoretic Feature Selection
Experimental Results
Conclusions
References
Image Processing and Analysis
Classification of Repetitive Patterns Using Symmetry Group Prototypes
Introduction
Proposed Method
Feature Computation and Symmetry Groups Classification
Adaptive NNC (ANNC)
Experiments
Conclusions
References
Distance Maps from Unthresholded Magnitudes
Introduction
Distance Maps from Untresholded Gradients
DMUM Algorithm
Results
Spatial Structure Analysis
Temporal Stability Results
Conclusions
References
Scratch Assay Analysis with Topology-Preserving Level Sets and Texture Measures
Introduction
Related Work
Entropy-Based Level Set Segmentation
Results
Conclusion
References
Level Set Segmentation with Shape and Appearance Models Using Affine Moment Descriptors
Introduction
Shape Alignment
Handling Shape Variability
Shape Model
Our Model
Numerical Algorithms
Liver Segmentation from 3D CT Images
Conclusion
References
Medical Applications
Automatic HyperParameter Estimation in fMRI
Introduction
Problem Formulation and Method
Optimization
Step One: b Estimation
Step Two: h Estimation
Step Three: d Estimation
Experimental Results
Synthetic Data
Real Data
Conclusions
References
Automatic Branching Detection in IVUS Sequences
Introduction
Method
Motion Artifacts Compensation
Automatic Branching Detection
Experimental Results
Discussion and Conclusion
References
A Region Segmentation Method for Colonoscopy Images Using a Model of Polyp Appearance
Introduction
Related Work
Our Proposed Methodology
A Model of Polyp Appearance
Algorithm
Results
Experimental Setup
Experimental Results
Conclusions and Future Work
References
Interactive Labeling of WCE Images
Introduction
Interactive Labeling
The Interactive Labeling System
Fast Density Estimation
Online Classifier
Results
Conclusions
References
Automatic and Semi-automatic Analysis of the Extension of Myocardial Infarction in an Experimental Murine Model
Introduction
Methodology
Semi-automatic Tissue Segmentation
Automatic Tissue Segmentation
Infarct Extension Evaluation
Results
Conclusion
References
Non-rigid Multi-modal Registration of Coronary Arteries Using SIFTflow
Introduction
Method
Registration Methods
Experimental Section
Material
Algorithms Setting
Results
Conclusion
References
Diffuse Liver Disease Classification from Ultrasound Surface Characterization, Clinical and Laboratorial Data
Introduction
Problem Formulation
Experimental Results
Conclusions
References
Classification of Ultrasound Medical Images Using Distance Based Feature Selection and Fuzzy-SVM
Introduction
Distance Based Criteria for Feature Selection
Feature Extraction from Ultrasound Medical Images
GLCM Based Statistical Texture Descriptors
GLRLM Based Statistical Texture Descriptors
Searching for Optimal Feature Subset Using GA
Multi-class Classification Using Fuzzy-SVM
Experimental Results
Conclusion
References
Ultrasound Plaque Enhanced Activity Index for Predicting Neurological Symptoms
Introduction
Methods
Ultrasound Profile of ``Active" Plaque
Enhanced Activity Index
Experimental Results
Conclusions
References
Pattern Recognition
On the Distribution of Dissimilarity Increments
Introduction
Dissimilarity Increments Distribution for 2D Gaussian Data
Empirical Estimation of DID
Clustering Using the Dissimilarity Increments Distribution
Graph-Based Dissimilarity Increments Distribution
Experimental Results and Discussion
Conclusions
References
Unsupervised Joint Feature Discretization and Selection
Introduction
Our Contribution
Background
Document Representation
Feature Discretization
Feature Selection Methods
Proposed Methods for Discretization and Selection
Unsupervised Feature Discretization - FD Step
Unsupervised Feature Selection - FS Step
Choice of the Number of Features
Experimental Evaluation
Sparse and Non-sparse Datasets
Bit Allocation and Discretization Results
Test Set Error Rate
Conclusions
References
Probabilistic Ranking of Product Features from Customer Reviews
Introduction
Related Work
Methodology
Extraction of Potential Features and Construction of a Basic Opinion Words List
Translation Model for Feature Ranking
Probability Density Estimation
Experiments
Conclusions and Future Work
References
Vocabulary Selection for Graph of Words Embedding
Introduction
Graph of Words Embedding
Motivation
Embedding Procedure
Vocabulary Construction
Experiments
Databases
Reference System: Graph Edit Distance
Results
Conclusions
References
Feature Selection in Regression Tasks Using Conditional Mutual Information
Introduction
Feature Selection for Regression
The Minimal-Relevant-Redundancy Criterion Function
Estimation of the Conditional Mutual Information for Regression Tasks
Experimental Validation
Methods
Dataset Description
Results and Discussion
Conclusions
References
Dual Layer Voting Method for Efficient Multi-label Classification
Introduction
Dual Layer Voting Method (DLVM)
Computational Complexity
Experimental Results
Conclusion
References
Passive-Aggressive for On-Line Learning in Statistical Machine Translation
Introduction
Related Work
The Passive-Aggressive Algorithm
Passive-Aggressive in SMT
Feature Vector Adaptation
Scaling Factor Adaptation
Heuristic Variations
Experiments
Experimental Setup
Experimental Results
Conclusions and Future Work
References
Feature Set Search Space for FuzzyBoost Learning
Introduction
The FuzzyBoost Algorithm
Fuzzy Weak Learners Optimization
The Search Space for the Feature Set
Experimental Results
Conclusions
References
Interactive Structured Output Prediction: Application to Chromosome Classification
Introduction
Non-interactive and Interactive Frameworks
Offline Framework
Offline Individual Chromosomes
Offline Karyotype Global
Offline Karyotype Unconstrained
Interactive Passive Framework
Interactive Passive Left-to-Right Karyotype Global
Interactive Passive Left-to-Right Karyotype Unconstrained
Interactive Active Framework
Experiments
Results
Discussion and Conclusions
References
On the Use of Diagonal and Class-Dependent Weighted Distances for the Probabilistic k-Nearest Neighbor
Introduction
Approach
MCMC Approximation
Maximum Likelihood Parameter Selection
Experiments
Conclusions
References
Explicit Length Modelling for Statistical Machine Translation
Introduction
Related Work
Log-Linear Modelling
Explicit Length Modelling
Standard Length Model
Specific Length Model
Estimation of Phrase-Length Models
Experimental Results
Conclusions and Future Work
References
Poster Sessions
Computer Vision
Age Regression from Soft Aligned Face Images Using Low Computational Resources
Introduction
Age Regression from Face Images
PCA+LDA Projection as the Age Metric Matrix
K-NN Regression
Experiments
Intra-database Tests
Cross-Database Tests
Conclusions
References
Human Activity Recognition from Accelerometer Data Using a Wearable Device
Introduction
Related Works
The Problem of Human Activity Recognition
Features Selection for Motion Data
Classification and Derivation of Importance Measurement
Validation and Discussions
Conclusions
References
Viola-Jones Based Detectors: How Much Affects the Training Set?
Introduction
Viola-Jones General Object Detection Framework
Datasets
Experiments
Classifiers
Results
Conclusions
References
Fast Classification in Incrementally Growing Spaces
Introduction
Fast Classification in PCA+SVM Settings
Experiments
Conclusions
References
Null Space Based Image Recognition Using Incremental Eigendecomposition
Introduction
Image Recognition through Discriminant Common Vectors
Incremental Null Space Characterization
Experiments and Discussion
Concluding Remarks and Further Work
References
Multi-sensor People Counting
Introduction
Computer Vision Methods
Range Laser Methods
Hybrid Methods
The Proposal
System Description
Visual Processing
Laser Scan Processing
Integration
Experiments and Results
Conclusions
References
Lossless Compression of Polar Iris Image Data
Introduction
Biometric Sample Compression
Experimental Study
Setting and Methods
Results
Conclusion and Future Work
References
Learning Features for Human Action Recognition Using Multilayer Architectures
Introduction
Related Works
Multilayer Models
Experiments and Results
Discussion and Conclusions
References
Human Recognition Based on Gait Poses
Introduction
Background
Gait Energy Image (GEI)
Phases and Key Poses within a Gait Cycle
Methodology
Fundamentals of the Proposed Method
Creating GEIs of Each Pose
Experiments and Results
Database Description and Preprocessing
Experimental Setup
Analysis of Results
Conclusion
References
On-Line Classification of Data Streams with Missing Values Based on Reinforcement Learning
Introduction
Reinforcement Learning
Formulating the Problem of Classification of Incomplete Data Using RL
Experiments and Results
Analysis of Results
Conclusions
References
Opponent Colors for Human Detection
Introduction
Opponent Colors Space
Human Detector
Experiments
Human Dataset
Training
Evaluation
Devised Experiments
Discussion
Conclusions
References
Automatic Detection of Facial Feature Points via HOGs and Geometric Prior Models
Introduction
Point Detection
Learning the Facial Point Models
Prior Distribution Model
Detection Algorithm
Experiments and Results
Discussion
References
Rectifying Non-euclidean Similarity Data through Tangent Space Reprojection
Introduction
Characterising Non-euclidean Data
Spherical Embedding
The Exponential and Log Map
The Algorithm
Experiments
Conclusion
References
Image Processing and Analysis
Gait Identification Using a Novel Gait Representation: Radon Transform of Mean Gait Energy Image
Introduction
Gait Identification System
Overview
Radon Transform
Zernike Moments
Experimental Results
Conclusions
References
New Algorithm for Segmentation of Images Represented as Hypergraph Hexagonal-Grid
Introduction
Related Work
Color Features and Hexagonal Structure of an Image
The Hexagonal Grid-Graph Structure
HyperGraph-Based Image Segmentation
Hypergraph Construction Algorithm
Segmentation Algorithm
Boundary Extraction of Visual Objects
Experiments
Conclusions
References
Statistical and Wavelet Based Texture Features for Fish Oocytes Classification
Introduction
Methods
Square ROI Extraction
Texture Feature Generation
Classification
Results and Discussion
Conclusion
References
Using Mathematical Morphology for Similarity Search of 3D Objects
Introduction
Brief Review of Mathematical Morphology
Method
Results
Discussion
References
Trajectory Analysis Using Switched Motion Fields: A Parametric Approach
Introduction
Switched Motion Field Model
Parametric Motion Fields
Model Estimation
Results
Conclusions
References
Semi-supervised Probabilistic Relaxation for Image Segmentation
Introduction
Probabilistic Relaxation Methodology
The Algorithm
Experimental Results
Results on 2D-Datasets and Two Classes
Results on Colour Image Segmentation
Conclusions
References
Poker Vision: Playing Cards and Chips Identification Based on Image Processing
Introduction
Playing Cards Identification
Find Cards
Cardsâ?? Extraction
Rank Extraction
Rank Identification
Suit Extraction and Identification
Chips Identification
Experimental Results
Conclusion and Future Work
References
Occlusion Management in Sequential Mean Field Monte Carlo Methods
Introduction
Theoretical Background
Previous Works
Occlusions and Mean Field
The Joint Likelihood
Experiments
Football Sequence
Indoor Surveillance Sequences
Conclusions
References
New Approach for Road Extraction from High Resolution Remotely Sensed Images Using the Quaternionic Wavelet
Introduction
Quaternionic Wavelet Transform
Our Approach for Network Road Extraction
Road Detection Algorithm
Control Point Selection
End points and junction points.
Frequency and Orientation Guided Joining Logic
Experimental Results
Conclusion
References
On the Influence of Spatial Information for Hyper-spectral Satellite Imaging Characterization
Introduction
Integration of Spatial Information in Imaging Characterization Methods
Basic Spatial Characterization
Feature Extraction Based on Gabor Filters
Hyper-spectral Data Set
Spectral/Spatial Classification Results
Classification Task
Segmentation Results
Conclusions
References
Natural Material Segmentation and Classification Using Polarisation
Introduction
Polarisation Image
Reflectance Distributions
Calculating Spherical Harmonic Features
Distribution of Information in the Feature Vector
Experiments
Skin Lesions
Region Segmentation
Conclusions
References
Reflection Component Separation Using Statistical Analysis and Polarisation
Introduction
Polarisation
Blind Source Separation
Iteration Process
Separation Results
Conclusion
References
Pattern Recognition
Characterizing Graphs Using Approximate von Neumann Entropy
Introduction
Graph Representation and the von Neumann Entropy
Riemann Zeta Function Derivative
Experiments
Conclusion
References
A Distance for Partially Labeled Trees
Introduction
Tree Comparison Methods
Proposed Tree Comparison Algorithm
Experiments and Results
Results
Conclusions
References
An Online Metric Learning Approach through Margin Maximization
Introduction
Maximizing the Margin on Distances
A Passive-Aggressive Approach to Distance Margin Maximization
Empirical Evaluation
Conclusions
References
Graph Matching on a Low-Cost and Parallel Architecture
Introduction
Graph Matching and Computer Architecture
Attributed Graphs and Graph Matching
Desktop Computer Architecture
Parallel Programming Model
A Parallel Solution for the Graph Matching problem
Parallel Update of the Probability Matrix
Parallel Normalisation Using Sinkhorn Method
Practical Evaluation
Conclusions and Future Work
A Probabilistic Framework to Obtain a Common Labelling between Attributed Graphs
Introduction
Graph Matching and Common Labelling of a Set of Graphs
A Probabilistic Framework to Obtain a CL
Common Labelling via Minimum Least Square Method (LSM)
Common Labelling via Probabilistic Iterative Algorithm
Evaluation of the Computational Cost
Evaluation
Conclusions and Further Work
References
Feature Selection with Complexity Measure in a Quadratic Programming Setting
Introduction
Quadratic Programming for Feature Selection
Feature Selection Based on Redundancy and Relevance
Capturing Relevance through Classifier Complexity
Experiments
Results
Conclusion
References
Automatic Estimation of the Number of Segmentation Groups Based on MI
Introduction
The Proposed Method
Noise Removing
Estimation of the Number of Segmentation Groups
Experiment and Discussion
Conclusion
References
Applications
Vitality Assessment of Boar Sperm Using N Concentric Squares Resized (NCSR) Texture Descriptor in Digital Images
Introduction
Image Dataset and Preprocessing
Image Acquisition
Segmentation
Texture Description of the Spermatozoa Heads
Texture Oriented Descriptors
Proposed Descriptors: N Concentric Squares (NCS)
Classification
Results
Best N Value for NCSR and NCSH
Errors and ROC Curves
Conclusions
References
Filled-in Document Identification Using Local Features and a Direct Voting Scheme
Introduction
Related Work
Approach
Feature Extraction and Classificacion
Experiments
Parameter Optimization
Conclusions
References
Combining Growcut and Temporal Correlation for IVUS Lumen Segmentation
Introduction
Method
Model-Based Temporal Analysis
Spatial Classification
In vivo Experiments
Discussion
References
Topographic EEG Brain Mapping before, during and after Obstructive Sleep Apnea Episodes
Methods
Dataset
Signal Processing
Power Calculation
Brain Mapping and Statistical Analysis
Results
Demographic, Respiratory and Polysomnographic Variables
EEG Analysis
Conclusion
References
Classifying Melodies Using Tree Grammars
Introduction
Melody Tree Representation
Stochastic k-Testable Tree Models
Grammars
Smoothing
Classification
Results
Conclusions
References
A Tree Classifier for Automatic Breast Tissue Classification Based on BIRADS Categories
Introduction
Methods and Materials
Feature Extraction
Classifiers, Data Training and Testing
Experimental Database
Results
Discussion and Conclusions
References
Diagnostic of Pathology on the Vertebral Column with Embedded Reject Option
Introduction
Pathologies of the Vertebral Column
Problem Statement and Standard Solutions
An Ordinal Data Approach for Detecting Reject Regions
The Data Replication Method for Detecting Reject Regions
Selecting the Misclassification Costs
Experiments
Conclusion
References
Language Identification for Interactive Handwriting Transcription of Multilingual Documents
Introduction
GIDOC Overview
Probabilistic Framework
Experiments
Conclusions
References
vManager, Developing a Complete CBVR System
Introduction to CBVR Systems
Methods
Scene Detection and Keyframe Selection
Feature Extraction
Representation and Similarity Measures
Practical Application and Results
Conclusions
References
On the Use of Dot Scoring for Speaker Diarization
Introduction
Speaker Diarization System
Dot Scoring
The Clustering Algorithm
Experimental Setup
Databases
Feature Extraction
Parameter Optimization
Performance Criteria
Results
Processing Time
Conclusions
References
A Bag-of-Paths Based Serialized Subgraph Matching for Symbol Spotting in Line Drawings
Introduction
Proposed Methodology
Bag-of-Paths
Construction of the LUT
Voting Scheme
Experimental Results
Shape Matching Experiments
Symbol Spotting Experiments
Conclusions and Future Work
References
Handwritten Word Spotting in Old Manuscript Images Using a Pseudo-structural Descriptor Organized in a Hash Structure
Introduction
Word Spotting Approach
Pre-processing Step
Feature Extraction
Matching Words
Experimental Results
Conclusions
References
Identification of Erythrocyte Types in Greyscale MGG Images for Computer-Assisted Diagnosis
Introduction
Description of the Used Pre-processing Method
Representation and Recognition of a Cell
Conditions and Results of the Experiment
Conclusions and Future Plans
References
Classification of High Dimensional and Imbalanced Hyperspectral Imagery Data
Introduction
Methodology
Preprocessing
Classification
Experiments and Results
Analysis of Results
Conclusions and Further Extensions
References
Active Learning for Dialogue Act Labelling
Introduction
The NGT Annotation Model
Active Learning
Sample Selection Criteria
Weighted Number of Hypothesis
Entropy
Experiments
Dihana Corpus
Experiment Strategy
Results
Conclusions and Future Work
References
Multi-class Probabilistic Atlas-Based Segmentation Method in Breast MRI
Introduction
Material
Methodology
Data Preprocessing
Construction of the Atlas
Segmentation
Results
Discussion and Conclusions
References
Impact of the Approaches Involved on Word-Graph Derivation from the ASR System
Introduction
ASR Decoding: Viterbi Algorithm
Approaches Involved Getting the Word-Graph
Forward Decoding
Backward Decoding: Getting the Word-Graph from the Lattice
Experimental Results
Concluding Remarks and Future Work
References
Visual Word Aggregation
Introduction
Clustering Aggregation
Visual Word Aggregation
Results
Conclusion
References
Character-Level Interaction in Multimodal Computer-Assisted Transcription of Text Images
Introduction
CATTI Overview
Multimodal CATTI (MM-CATTI) at the Character Level
Dynamic Language Modelling for Character-Level MM-CATTI
Off- and On-Line HTR System Overview
Experimental Framework
Assessment Measures
Corpus
Results
Conclusions
References
Simultaneous Lesion Segmentation and Bias Correction in Breast Ultrasound Images
Introduction
Methodology
Image Model
Expectation-Maximization (EM) Algorithm
Automatic Initialization Process
Experiments and Results
Ground Truth
Results
Conclusion
References
Music Score Binarization Based on Domain Knowledge
Introduction
Related Work
Robust Estimation of Staffline Thickness and Spacing in the Gray-Scale Domain
Content Aware Music Score Binarization
Using Other Reference Lengths to Guide the Binarization
Adaptive Content Aware Music Score Binarization
Experimental Evaluation
Conclusion
References
Identifying Potentially Cancerous Tissues in Chromoendoscopy Images
Introduction
Materials
Methods
Interest Point Detection
Feature Extraction
Classification
Experimental Setup
Parameter Setting
Data Normalization
Classification Results
Discussion
References
Myocardial Perfusion Analysis from Adenosine-Induced Stress MDCT
Introduction
Image Acquisition Protocol and Myocardium Segmentation
Threshold Based Method
Myocardium Radial Mean Attenuation
Segmental Attenuation Histogram
Conclusions and Future Work
References
Handwritten Digits Recognition Improved by Multiresolution Classifier Fusion
Introduction
Handwritten Digits Recognition Background
Multiresolution Classifier Fusion
Experimental Results
Conclusions
References
A Comparison of Spectrum Kernel Machines for Protein Subnuclear Localization
Introduction
The Spectrum Kernel
Kernel Classifiers
Minimum Distance Probability (MDP)
Results
Conclusions
References
Complex Wavelet Transform Variants in a Scale Invariant Classification of Celiac Disease
Introduction
Cwt Variants and Scale Invariant Features
Experimental Study
Discussion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Pattern Recognition and Image Analysis

Description

More details

Other editions

Additional editions

Content

System requirements