Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Name: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications | 21st Iberoamerican Congress, CIARP 2016, Lima, Peru, November 8-11, 2016, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

21st Iberoamerican Congress, CIARP 2016, Lima, Peru, November 8-11, 2016, Proceedings

César Beltrán-Castañón Ingela Nyström Fazel Famili(Editor)

Springer (Publisher)

Published on 14. February 2017

XVIII, 541 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-52277-7 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Preface
Organization
Contents
Direction-Based Segmentation of Retinal Blood Vessels
Abstract
1 Introduction
2 Building the Direction Map DMG
3 The Segmentation Method
4 Experimental Results and Concluding Remarks
References
Identifying Aedes aegypti Mosquitoes by Sensors and One-Class Classifiers
1 Introduction
2 Optical Sensor and Insect Data
2.1 Data Collection
2.2 Feature Extraction
3 One-Class Classification
4 Experimental Evaluation
5 Conclusion
References
Partial Matching of Finger Vein Patterns Based on Point Sets Alignment and Directional Information
Abstract
1 Introduction
2 The Proposed Approach
3 Experiments and Results
4 Conclusion
References
Highly Transparent and Secure Scheme for Concealing Text Within Audio
1 Introduction
2 Proposed Audio Steganography Model
2.1 Embedding Module
2.2 Recovering Module
3 Experimental Results and Discussion
3.1 Transparency
3.2 Security
4 Conclusion
References
Spatio-Colour Asplünd's Metric and Logarithmic Image Processing for Colour Images (LIPC)
1 Introduction
2 Prerequisites
2.1 LIPC Model
2.2 Marginal Asplünd's Metric for Colour and Multivariate Images
3 Asplünd's Metric Defined in the Logarithmic Image Processing Colour (LIPC) Framework
4 Examples
5 Conclusion and Perspectives
References
Two Compound Random Field Texture Models
1 Introduction
2 Compound Random Field Texture Models
2.1 Region Switching Model
2.2 Local Markov Models
3 Experiments
4 Conclusion
References
An Automatic Tortoise Specimen Recognition
1 Introduction
2 Discriminative Tortoise Features
3 Automatic Detection of Tortoise Features
3.1 Plastron Localization
3.2 Central Seam Junctions Localization
4 Tortoise Classification
5 Experimental Results
5.1 Feature Discriminability Validation
5.2 Classification of Automatically Measured Features
6 Conclusion
References
Autonomous Scanning of Structural Elements in Buildings
Abstract
1 Introduction: Key Points and Contributions
2 A Brief Overview of the Method
3 Structural Elements Recognition
3.1 Finding the Region of Interest
3.2 Structural Elements Classification
4 NBS
5 Test and Experimental Comparison
6 Conclusions
Acknowledgements
References
Parallel Integer Motion Estimation for High Efficiency Video Coding (HEVC) Using OpenCL
1 Introduction
2 Parallel Integer Motion Estimation
2.1 Distortion Measure Calculations
2.2 Distortion Measure Accumulations
2.3 Estimating Minima of Rate-Distortion
2.4 GPU and CPU Communication
3 Experimental Evaluation
3.1 Experimental Setup and Encoder Configuration
3.2 Experimental Results
4 Conclusions
References
Automatic Fruit and Vegetable Recognition Based on CENTRIST and Color Representation
1 Introduction
2 Background
2.1 CENTRIST
2.2 Color CENTRIST
3 Methodology
3.1 Preprocessing
3.2 Feature Extraction
3.3 Feature Reduction and Classification
4 Experimental Results
5 Conclusions
References
Scale Sensitivity of Textural Features
1 Introduction
2 Textural Features
2.1 2DCAR Illumination Invariant Features
2.2 Local Binary Patterns
2.3 Gabor Features
2.4 Histogram Based Features
3 Experiments
4 Conclusion
References
Noise-Added Texture Analysis
1 Introduction
2 Regionalized Variables in an Image
3 Measuring Dissimilarity of Regionalized Variables
4 Experiments
5 Conclusion
References
Breast Density Classification with Convolutional Neural Networks
1 Introduction
1.1 Breast Density
1.2 American College of Radiology: BIRADS Categories
1.3 Radiologist Agreement and Performance Evaluation
2 The Breast Density Dataset
3 Methods
3.1 HT-L3 Visual Features with Random Filters
3.2 Deep Learning Trained with the Image.net and Fine-Tuned with the Breast Density Dataset
4 Results
5 Conclusions
References
Community Feature Selection for Anomaly Detection in Attributed Graphs
1 Introduction
2 Related Work
3 Basic Concepts
4 Improving Anomaly Detection Using Community Features
5 Experimental Results
6 Conclusions
References
Lung Nodule Classification Based on Deep Convolutional Neural Networks
1 Introduction
2 Background
2.1 Lung Nodule Classification
2.2 Deep Learning
3 Proposed Method
3.1 Preprocessing and Data Augmentation
3.2 Architecture
3.3 Learning
3.4 Adjacent Rejection
4 Experimental Results
4.1 Dataset
4.2 Results
5 Conclusions
References
A Hierarchical K-Nearest Neighbor Approach for Volume of Tissue Activated Estimation
1 Introduction
2 Materials and Methods
3 Experimental Set-Up
4 Results and Discussion
5 Conclusions
References
Discriminative Capacity and Phonetic Information of Bottleneck Features in Speech
1 Introduction
2 Bottleneck Features
3 Discriminative Capacity of the BN Features
4 Phonetic Information Conveyed by the BN Features
5 Experimental Setup
5.1 Data Corpus
5.2 The DNN Toolkit
5.3 Experiments
6 Results
7 Conclusions
References
Boosting SpLSA for Text Classification
1 Introduction
2 Related Work
3 Supervised pLSA and Our Extensions
3.1 Variables and Assumptions
3.2 Supervised pLSA (spLSA)
3.3 Model Fitting
3.4 Label Inference on New Documents
3.5 A First Extension: SpLSA Regularization
3.6 A Second Extension: Modeling Label Uncertainty
4 Experiments
4.1 Data Sets
4.2 Results
5 Conclusions
References
A Compact Representation of Multiscale Dissimilarity Data by Prototype Selection
1 Introduction
2 Proposed Method
3 Experimental Analysis
4 Conclusions
References
A Kernel-Based Approach for DBS Parameter Estimation
1 Introduction
2 Materials and Methods
3 Experimental Set-Up
4 Results and Discussion
5 Conclusions
References
Consensual Iris Segmentation Fusion
1 Introduction
2 Iris Consensual Segmentation Fusion by Segmentation Ensemble via Kernels
3 Experimental Design
3.1 Results and Discussion
4 Conclusions
References
Depth Estimation with Light Field and Photometric Stereo Data Using Energy Minimization
1 Introduction
2 Acquisition Setup
3 Combination of Light Fields and Photometric Stereo
3.1 Light Field Depth Estimation
3.2 Surface Normals from Photometric Stereo
3.3 Energy Minimization
4 Experimental Results
5 Summary and Outlook
References
Distributed and Parallel Algorithm for Computing Betweenness Centrality
1 Introduction
2 Background
3 Our Proposal
3.1 Modification for Sparse Networks
3.2 Analysis
4 Experiments
5 Conclusions and Future Work
References
A New Parallel Training Algorithm for Optimum-Path Forest-Based Learning
1 Introduction
2 Supervised Classification Based on Optimum-Path Forest
2.1 Training
2.2 Testing
3 Parallel-Driven Optimum-Path Forest Training
4 Experiments and Results
5 Conclusions and Future Work
References
Face Composite Sketch Recognition by BoVW-Based Discriminative Representations
1 Introduction
2 Proposal: BoVW-Based Discriminative Representation
3 Experimental Analysis
4 Conclusions
References
Efficient Sparse Approximation of Support Vector Machines Solving a Kernel Lasso
1 Introduction
2 Problem Statement and Related Work
3 Sparse SVM Approximations via Kernelized Lasso
4 Experimental Results
5 Conclusions
References
Metric Learning in the Dissimilarity Space to Improve Low-Resolution Face Recognition
1 Introduction
2 Related Work
3 Proposed Approach: Dissimilarity Space and Metric Learning for LRFR
3.1 Dissimilarity Space
3.2 Metric Learning Approach
4 Experimental Evaluation
4.1 Experiments and Discussion on SCFace Database
4.2 Experiments and Discussion on LFW Database
5 Conclusions
References
Video Temporal Segmentation Based on Color Histograms and Cross-Correlation
1 Introduction
2 Background
3 Methodology
3.1 Histogram-Based Dissimilarity
3.2 Block-Based Cross-Correlation
3.3 Fusion
3.4 Adaptive Thresholding
4 Experimental Results
5 Conclusions and Future Work
References
Automatic Classification of Herbal Substances Enhanced with an Entropy Criterion
1 Introduction
2 Data Preprocessing
3 Discovery of Classes
4 Entropy-Based Template Selection
5 SVM Classification
6 Experimental Results and Discussion
7 Conclusions and Future Work
References
Extended LBP Operator to Characterize Event-Address Representation Connectivity
1 Introduction
2 Features Generation
2.1 Dynamic Vision Sensor Data
2.2 Events Orientation
2.3 Events Connectivity
3 Grouping Features as Histograms
4 Discussions and Conclusions
References
Definition and Composition of Motor Primitives Using Latent Force Models and Hidden Markov Models
1 Introduction
2 Materials and Methods
2.1 Latent Force Models
2.2 Hidden Markov Models
2.3 HMM and LFM
2.4 Learning the Model
3 Experimental Results
3.1 Synthetic Data
3.2 Real Data
4 Conclusions
References
Similarity Measure for Cell Membrane Fusion Proteins Identification
1 Introduction
2 Background
3 Proposed System
3.1 Development of a Similarity Measure
3.2 Classification
4 Data Description and Experimental Results
4.1 Data Pre-processing
5 Conclusions and Future Work
References
Abnormal Behavior Detection in Crowded Scenes Based on Optical Flow Connected Components
1 Introduction
2 Proposed Method
2.1 OFCCs Computation
2.2 Normal Behavior Model
2.3 Abnormality Detection
3 Results and Comparisons
4 Conclusions
References
Identifying Colombian Bird Species from Audio Recordings
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 Feature Extraction and Audio Representation
2.3 Automatic Identification of Bird Species
2.4 Visualization of Bird Species
3 Experiments and Results
3.1 Classification Experiments
3.2 Visualization Experiments
4 Conclusion and Future Work
References
GMM Background Modeling Using Divergence-Based Weight Updating
1 Introduction
2 Methods
3 Experimental Set-Up
4 Results and Discussion
5 Conclusions
References
Bayesian Optimization for Fitting 3D Morphable Models of Brain Structures
1 Introduction
2 Materials and Methods
2.1 Database
2.2 3D Brain Model
2.3 Bayesian Optimization with Gaussian Process Priors
2.4 Morphable Model Fitting Using Bayesian Optimization
3 Results and Discussions
3.1 Training Results for 3D-MM
3.2 Fitting Results Using Bayesian Optimization
4 Conclusions and Future Works
References
Star: A Contextual Description of Superpixels for Remote Sensing Image Classification
1 Introduction
2 Star Descriptor
2.1 Segmentation into Superpixels
2.2 Graph Modeling
2.3 Vertex Descriptors
2.4 Edge Descriptors
2.5 Final Descriptor Composition
3 Experimental Protocol
4 Results
5 Conclusion
References
A Similarity Indicator for Differentiating Kinematic Performance Between Qualified Tennis Players
1 Introduction
2 Kernel Based Multi-channel Data Representation
3 Performance Comparison Expanded to RKHS Representation
4 Experimental Setup and Results
4.1 Database
4.2 Baseline Kinematic Analysis
4.3 Kernel-Based Performance Analysis
5 Discussion and Concluding Remarks
References
Subsampling the Concurrent AdaBoost Algorithm: An Efficient Approach for Large Datasets
1 Introduction
2 Adaptive Boosting and Some Parallel Variants
3 Subsampling the Concurrent AdaBoost Algorithm
4 Experimentation
5 Conclusions
References
Deep Learning Features for Wireless Capsule Endoscopy Analysis
1 Introduction
2 Frame-Based Motility Events
3 Feature Learning Using Convolution Neural Networks
3.1 Our Network Architecture
3.2 CNN Training
4 Experimental Results
4.1 Quantitative Results
4.2 Qualitative Results
5 Conclusions
References
Interactive Data Visualization Using Dimensionality Reduction and Similarity-Based Representations
1 Introduction
2 Data Visualization via Dimensionality Reduction
3 Interactive Data Visualization Scheme
3.1 Mixture
3.2 Interaction Model
3.3 Similarity-Based Visualization
4 Experimental Setup
5 Results and Discussion
6 Conclusions and Future Work
References
Multi-labeler Classification Using Kernel Representations and Mixture of Classifiers
1 Introduction
2 Related Works and Background
3 Proposed Multi-labeler Classification Approach
3.1 Modified Supervised Kernel
3.2 Multi-labeler Approach
3.3 Estimation of Weighting Factors
4 Results and Discussion
5 Conclusions and Future Work
References
Detection of Follicles in Ultrasound Videos of Bovine Ovaries
1 Introduction
2 Dataset
3 Signal Processing for Follicle Detection
3.1 Follicle-Like Regions Detection in Each Frame
3.2 Temporal Coherence by Multiple Tracking
3.3 Identification of the Ovarian Region
3.4 Follicle Identification and Measurement
4 Experiments and Results
5 Concluding Remarks
References
Decision Level Fusion for Audio-Visual Speech Recognition in Noisy Conditions
1 Introduction
2 Proposed Approach
3 Audio-Visual Databases
4 Experimental Results
5 Conclusions
References
Improving Nearest Neighbor Based Multi-target Prediction Through Metric Learning
1 Introduction
2 General Notation and State of the Art
3 Distance Metric Learning for Multi-target Prediction (DMLMTP)
4 Experiments
5 Concluding Remarks and Further Work
References
An Approximate Support Vector Machines Solver with Budget Control
1 Introduction
2 Proposal
2.1 Sparsity Constraints
3 Experiments
3.1 Experimental Setup
3.2 Discussion
4 Conclusion
References
Multi-biometric Template Protection on Smartphones: An Approach Based on Binarized Statistical Features and Bloom Filters
1 Introduction
2 Proposed Multi-biometric Approach
2.1 Face and Periocular Segmentation
2.2 Generalized Feature Extraction and Binarization
2.3 Biometric Template Protection: Bloom Filters
3 Experimental Setup and Results
3.1 Real-Time Evaluation of the Proposed System
4 Conclusion
References
Computing Arithmetic Operations on Sequences of Handwritten Digits
1 Introduction
2 Previous Work
3 Handwritten Arithmetics with Deep Learning
3.1 Problem Description
3.2 Deep Learning Architecture
4 Experiments and Results
4.1 Dataset and Sequences
4.2 Training
4.3 Testing
5 Conclusions and Future Work
References
Automatic Classification of Non-informative Frames in Colonoscopy Videos Using Texture Analysis
1 Introduction
2 Automatic Classification of Non-Infomative Frames
2.1 Frequency Domain Transform
2.2 Texture Analysis
2.3 Classification Using Support Vector Machines
3 Experimental Evaluation
3.1 Evaluation Conditions
3.2 Results and Discussion
4 Final Remarks
References
Efficient Training Over Long Short-Term Memory Networks for Wind Speed Forecasting
1 Introduction
2 Long Short-Term Memory
3 An Efficient Training for LSTM
4 Experiments and Results
5 Conclusions and Future Work
References
Classifying Estimated Stereo Correspondences Based on Delaunay Triangulation
1 Introduction
2 Corresponding Points Classification
2.1 Fundamentals
2.2 Classification Based on Delaunay Triangulation
3 Experimental Evaluation
4 Conclusions
References
Data Fusion from Multiple Stations for Estimation of PM2.5 in Specific Geographical Location
Abstract
1 Introduction
2 Materials and Methods
2.1 Database
2.2 Theoretical Background
3 Results and Discussion
4 Conclusions
Acknowledgments
References
Multivariate Functional Network Connectivity for Disorders of Consciousness
1 Introduction
2 Materials and Methods
2.1 Participants and Data Acquisitions
2.2 fMRI Preprocessing
2.3 Community Detection
2.4 Multivariate FNC Method
2.5 Group Analysis
3 Results
4 Conclusions
References
Non-parametric Source Reconstruction via Kernel Temporal Enhancement for EEG Data
1 Introduction
2 Materials and Methods
2.1 Inverse Problem
2.2 LORETA
2.3 Kernel Temporal Enhancement
2.4 Reconstruction Error Metrics
2.5 Experimental Setup
3 Results
4 Discussion and Conclusions
References
Tsallis Entropy Extraction for Mammographic Region Classification
1 Introduction
2 Related Works
3 Methodology
3.1 Gray-Level Co-occurrence Matrix (GLCM)
3.2 Multilevel Decomposition
3.3 Weighted Haralick Features
3.4 Tsallis Entropy
3.5 Classification
4 Database Acquisition
4.1 ROI Extraction
5 Experiments
5.1 Experiment I: Fixed Direction and q [0.1, 1.9]
5.2 Experiment II: Two Refined Ranges: [1.31, 1.39] and [1.41, 1.49]
6 Conclusions and Future Works
References
Edge Detection Robust to Intensity Inhomogeneity: A 7T MRI Case Study
1 Introduction
2 Related Works
2.1 Parameter Selection
2.2 Edge Refining
3 Proposed Methodology
4 Experiments
5 Conclusion
References
Fine-Tuning Based Deep Convolutional Networks for Lepidopterous Genus Recognition
1 Introduction
2 Related Work
3 Proposed Approach
4 Experimental Results
5 Conclusions
References
Selection of Statistically Representative Subset from a Large Data Set
Abstract
1 Introduction
1.1 Related Works
1.2 Problem Setting
2 Testing Complex Hypotheses
2.1 Testing Hypothesis in Hard and Soft Modes
2.2 Null-Hypothesis and Artificial Contrary Hypothesis
3 Method
3.1 Steps of Algorithm
3.2 Evaluation of Results
4 Experiments
4.1 Selecting Companies of Mobile Communication (Russia)
4.2 Selecting Modes of Movements in Intercity Autobus Communication (Peru)
5 Conclusions
References
Non-local Exposure Fusion
1 Introduction and Previous Works
2 Non-local Exposure Fusion
2.1 Classical Exposure Fusion
2.2 Non-local Fusion
2.3 Computing Pixel Similarity
2.4 Algorithm Details
3 Experiments
4 Conclusions
References
Analysis of the Geometry and Electric Properties of Brain Tissue in Simulation Models for Deep Brain Stimulation
1 Introduction
2 Materials and Methods
2.1 Simulation Models for DBS and Geometries
2.2 Brain Conductivity Through Diffusion Magnetic Resonance Imaging (dMRI)
3 Experimental Results
3.1 Anisotropy Level of Brain Structures for Each Patient
3.2 Simulations of DBS Models
3.3 Discussion
4 Conclusions and Future Work
References
Spatial Resolution Enhancement in Ultrasound Images from Multiple Annotators Knowledge
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 Spatial Resolution Enhancement Based on Gaussian Processes Regression with Multiple Annotators
2.3 Procedure
3 Results and Discussions
4 Conclusion
References
How Deep Can We Rely on Emotion Recognition
1 Introduction
2 Related Work
3 Proposed Emotion Recognition Model
4 Experimental Design
5 Results and Discussion
6 Conclusion
References
Sparse Linear Models Applied to Power Quality Disturbance Classification
1 Introduction
2 Materials and Methods
2.1 Power Quality (PQ) Disturbances
2.2 Overcomplete Representation
2.3 Sparse Linear Models for Grouped Variable Selection
2.4 Procedure
3 Results and Discussions
4 Conclusions
References
Trading off Distance Metrics vs Accuracy in Incremental Learning Algorithms
1 Introduction
2 Incremental Hypersphere Classifier (IHC) Algorithm
3 Experimental Results
4 Conclusions and Future Work
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Description

More details

Other editions

Additional editions

Content

System requirements