Image Analysis and Processing - ICIAP 2015

Name: Image Analysis and Processing - ICIAP 2015 | 18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings, Part II
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings, Part II

Vittorio Murino Enrico Puppo(Editor)

Springer (Publisher)

Published on 20. August 2015

XXVI, 737 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-23234-8 (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 - Part II
Contents - Part I
Image Analysis
Learning Balanced Trees for Large Scale Image Classification
1 Introduction
2 Related Work
3 Learning a Balanced Tree for Image Classification
3.1 Overview of Label Tree
3.2 The Proposed Approach
4 Experiments
4.1 Datasets
4.2 Experimental Setting
4.3 Evaluation Measurement
4.4 Experimental Results
5 Conclusion
References
Analysis of Compact Features for RGB-D Visual Search
1 Introduction
2 Visual Search Architecture
2.1 Image Description
2.2 Binary Hashing
2.3 Matching
3 Experimental Evaluation
3.1 Datasets
3.2 Results
4 Conclusion and Future Work
References
Hierarchical Image Segmentation Relying on a Likelihood Ratio Test
1 Introduction
2 A Method Inspired by Likelyhood Ratio Test
2.1 Likelihood Ratio Test
2.2 Similarity Measure
2.3 The Proposed Method
3 Experimental Analysis
3.1 Compared Methods and Their Underlying Graphs
3.2 Databases
3.3 Quantitative Analysis
4 Conclusions and Further Works
References
Large Scale Specific Object Recognition by Using GIFTS Image Feature
1 Introduction
1.1 Related Work
2 GIFTS Image Local Feature and KD-Tree
2.1 GIFTS Image Feature
2.2 KD-Tree
3 Large Scale Book Image Query System
4 Experimental Results and Considerations
4.1 Comparison with ORB
5 Conclusions and Future Work
References
On Spatiochromatic Features in Natural Images Statistics
1 Introduction
2 Previous Studies on Spatial and Chromatic Natural Color Image Statistics
2.1 Chromatic Redundancy in Natural Images
2.2 Spatio-chromatic Redundancy in Natural Images
3 Relationship Between Second Order Stationarity and the Decorrelated Spatiochromatic Features of Natural Images
3.1 The Gray-Level Case
3.2 The Color Case
4 Validations on a Natural Image Database
4.1 c0(R,G,B) and Its Eigenvalues and Eigenvectors
4.2 The Exponential Decay of Spatiochromatic Covariance
5 Discussion and Perspectives
References
Real-Time Foreground Segmentation with Kinect Sensor
1 Introduction
2 Kinect
3 Previous Works
4 Foreground Segmentation
4.1 ToF Based Segmentation
4.2 Kinect Based Segmentation
5 Results
6 Conclusions
References
Hierarchical Image Representation Using Deep Network
1 Introduction
2 Related Work
3 Unsupervised Feature Extraction
3.1 Deep Network Architecture
3.2 Simulating K-Means in the Network
3.3 Hierarchical Bag-of-Words Representation
4 Performance Evaluation
5 Conclusion
References
Fast Image Classification with Reduced Multiclass Support Vector Machines
1 Introduction
2 Image Classification with Visual Descriptors
3 Reducing Multiclass Support Vector Machines
4 Experiments
5 Related Work on SVM Reduction
6 Conclusions and Future Work
References
A Gravitational Model for Plant Classification Using Adaxial Epidermis Texture
1 Introduction
2 A Gravitational System
3 Complexity Analysis
4 Proposed Feature Vector
5 Experiments and Results
6 Conclusion
References
Adaptive Background Modeling for Land and Water Composition Scenes
1 Introduction
2 Proposed Background Modeling Algorithm
2.1 Land and Water Area Separation
2.2 Background Learning Rate Calculation
2.3 Accounting for the Influence of Sunrise and Sunset
2.4 Background Updating
3 Experimental Results
3.1 Robustness to Changes in Luminance at Sunrise and Sunset
3.2 Robustness to Changes in Tidal Height
3.3 Quantitative Performance Evaluation on Real Data
4 Conclusions
References
Enhancing Signal Discontinuities with Shearlets: An Application to Corner Detection
1 Introduction
2 A Review of the Shearlet Transform
3 Detecting Discontinuities with Shearlets
4 Corner Detection with Shearlets
5 Experimental Results
6 Discussion
References
Improved Human Gait Recognition
1 Introduction
2 Related Works
3 Methodology
3.1 Motivations
3.2 Gait Energy Image
3.3 Feature Selection Mask
3.4 Canonical Discriminat Analysis
4 Experiments
5 Conclusions
References
Human Area Refinement for Human Detection
1 Introduction
2 Related Work
3 Proposed Method
3.1 Basic Ideas
3.2 Coarse Foot Position Estimation
4 Experiments
4.1 Evaluation of Projection Transformation
4.2 Evaluation of Refined B-Boxes
4.3 Evaluation of Tracking Performance
5 Conclusions
References
Skeletonization Algorithm Using Discrete Contour Map
1 Introduction
2 Preliminaries and Notations
3 Discrete Contour Map
4 Skeletonization Algorithm
5 Experimental Results
6 Related Work
7 Conclusion
References
Superpixel and Entropy-Based Multi-atlas Fusion Framework for the Segmentation of X-ray Images
1 Introduction
2 Proposed Model
2.1 Data Set and Multi-atlas Creation
2.2 Image Pre-processing
2.3 Proposed Multi-atlas Fusion Procedure
3 Experimental Results
4 Conclusion
References
Wavelet-Like Lifting-Based Transform for Decomposing Images in Accordance with the Inter-prediction Principles of Video Coding
1 Introduction
2 Proposed Principle of Image Analysis-Synthesis
3 Adaptive Prediction Mechanisms
4 Experimental Evaluation of the HASTD
5 Conclusion
References
Real-Time Age Estimation from Face Imagery Using Fisher Vectors
1 Introduction
2 Fast Face Detection and Alignment
2.1 Features and Image Pre-processing
2.2 Face Detection
2.3 Face Alignment
3 Face Representation
4 Large Scale Learning with SGD
5 Experimental Results
5.1 Timing
5.2 Accuracy
6 Conclusions
References
Bounded Non-Local Means for Fast and Effective Image Denoising
1 Introduction and Related Work
2 Weighting by a Bounding Function
2.1 Original NLM
2.2 Proposed Bounded NLM
3 Experimental Results
4 Concluding Remarks
References
i-Street: Detection, Identification, Augmentation of Street Plates in a Touristic Mobile Application
1 Introduction
2 i-Street Overview
3 Text in Scene Images
4 Plate Identification
5 Image Augmentation
6 Requirements and Criticalities
7 Lab Tests and Real Usage
8 Conclusions
References
Distortion Adaptive Descriptors: Extending Gradient-Based Descriptors to Wide Angle Images
1 Introduction
2 The Distorted Domain
2.1 Gradient Estimation of Distorted Images
3 Distortion Adaptive Descriptors
4 Experimental Settings
5 Results
6 Conclusion
References
Counting Turkish Coins with a Calibrated Camera
1 Introduction
2 The Proposed Coin Detection and Recognition Method
2.1 Bilateral Filtering
2.2 Circle Detection and Elimination
2.3 Diameter Computation and Coin Classification
3 Experimental Results
4 Conclusions
References
Design and Implementation of a Dynamic Adaptive Video Streaming System with a Buffer Aware Rate Selection Algorithm
1 Introduction
2 Background and Related Work
3 The Proposed Video Streaming System
3.1 Encoding Scheme
3.2 Dynamic Adaptive Video Streaming System
3.3 Throughput Estimation Mechanism
3.4 Buffer Aware Rate Selection Algorithm
4 Experimental Evaluation
5 Conclusion
References
Leveraging Mutual Information in Local Descriptions: From Local Binary Patterns to the Image
1 Introduction
2 Local Binary Pattern and Constraint Propagation
3 The Directed Constraint Graph
4 The Inversion Algorithm
5 Results and Discussions
6 Conclusions
References
Dominant LBP Considering Pattern Type for Facial Image Representation
1 Introduction
2 The Local Binary Pattern (LBP)
2.1 A Brief Overview of LBP
2.2 The Angular Difference LBP (AD-LBP)
3 Dominant LBP Considering Pattern Type (LBP)
3.1 Related Works and Motivation
3.2 The Learning Phase
3.3 Feature Extracting Phase
4 Experiments and Results
4.1 Experiments Setting
4.2 Experimental Results
5 Discussion and Conclusion
References
Improving High Resolution Satellite Images Retrieval Using Color Component Features
1 Introduction
2 Multiscale Opponent Color Descriptors
2.1 Opponent Cross-Correlation
2.2 Color Features
2.3 Feature Extraction
3 Bag of Visual Words Model
3.1 Features Extraction
4 Results and Discussions
5 Conclusion
References
The QCRI Recognition System for Handwritten Arabic
1 Introduction
2 Text Line Image Normalization
2.1 Baseline Estimation
2.2 Slant Correction
2.3 Size Normalization
2.4 Pen Size Normalization
3 Feature Extraction
4 Training Procedure
5 Experiments
5.1 Data Description
5.2 Results
6 Conclusion
References
Optimized Parallel Model of Covariance Based Person Detection
1 Introduction
2 Person Detection Based on Covariance Descriptor
2.1 Features Extraction
2.2 First and Second Order Tensors
2.3 Covariance Region
2.4 The Classifier
3 Parallelization Procedure
3.1 Kahn Process Networks
3.2 The Initial Parallel Model
The Communication Workload.
Computation Workload Analysis.
3.3 The Optimized Parallel Model
4 Conclusion
References
Face Recognition from Robust SIFT Matching
1 Introduction
2 Features Detection in Scale-Space
3 Proposed Method
4 Experimental Assessment
5 Conclusions
References
Optimized Intra Mode Decision for High Efficiency Video Coding
1 Introduction
2 HEVC Intra Prediction
3 Gradient Based Pre-processing
4 Optimization of Intra Mode Detection
4.1 Optimal Mode Selection
4.2 Mode Pre-selection
5 Fast Mode Decision
6 Complexity Analysis
7 Experimental Results
8 Conclusions
References
Towards Learning Free Naive Bayes Nearest Neighbor-Based Domain Adaptation
1 Introduction
2 Related Work
3 Problem Setting and Definitions
3.1 Domain Adaptation
3.2 Naive Bayes Nearest Neighbor
4 Learning Free NBNN-Based Domain Adaptation
5 Experiments
5.1 Datasets, Features and Setup
5.2 Results
5.3 Discussion
6 Conclusions
References
A Gravitational Model for Grayscale Texture Classification Applied to the pap-smear Database
1 Introduction
2 Gravitational Model
3 Signature for Grayscale Textures
4 Experiments
4.1 pap-smear Database
4.2 Methods and Classification
5 Results
6 Conclusion
References
Combining ARF and OR-PCA for Robust Background Subtraction of Noisy Videos
1 Introduction
2 Related Work
3 Proposed Approach
3.1 Real Time Acive Random Field (ARF) for Image Denoising
3.2 Background Subtraction
3.3 Color Transfer Method
4 Experimental Evaluations
4.1 Qualitative Results
4.2 Quantitative Results
5 Conclusion
References
Image Clarification Method Based on Structure-Texture Decomposition with Texture Refinement
1 Introduction
2 Imaging Model
3 Proposed Method
3.1 Structure-Texture Decomposition
3.2 Airlight Correction
3.3 Bad Weather Correction
3.4 Poor Lighting Correction
3.5 Texture Refinement
4 Evaluation
5 Conclusion
References
Detecting and Tracking the Tips of Fluorescently Labeled Mitochondria in U2OS Cells
1 Introduction
2 Materials and Methods
2.1 Image Acquisition
2.2 Training and Test Data
2.3 Detecting the Tips of Mitochondria Using a Random Forest Classifier
2.4 Tracking
2.5 Generation of Synthetic Image Data
3 Results
3.1 Performance of Tip Detection
3.2 Accuracy of Tracking
3.3 Quantification of Mitochondrial Motion in U2OS Cells
4 Discussion
References
Recognition of the Human Fatigue Based on the ICAAM Algorithm
1 Introduction
2 Behaviors That Demonstrate the Appearance of Fatigue
3 Image Processing in the Fatigue Detection
4 Assessment of the Fatigue Condition
5 Implementation and Tests of the System
6 Results and Analysis
7 Summary
References
Rich QR Code for Multimedia Management Applications
1 Introduction
2 Related Work
2.1 QR Code Features
2.2 Rich Graphical Codes
3 Rich QR Code with Two Stored Levels
3.1 Two Level QR (2LQR) Code Generation
3.2 Recognition Methods
4 Experimental Results
4.1 Generation of 2LQR Code
4.2 Message Extraction
5 Conclusion
References
Panel Tracking for the Extraction and the Classification of Speech Balloons
1 Introduction
2 Methodology
2.1 Pre-processing
2.2 Tracking
2.3 Extraction
2.4 Classification
3 Experimental Results
3.1 Experimental Setup
3.2 Panel Extraction
3.3 Speech Balloon Classification
3.4 Discussion
4 Conclusion and Future Work
References
Combining Hardwaremetry and Biometry for Human Authentication via Smartphones
1 Introduction
2 Related Works
3 Method
3.1 Sensor Recognition Module
3.2 Iris Recognition Module
3.3 Fusion Technique
4 Experimental Results
4.1 Data Set
4.2 Sensor n Recognition
4.3 Iris Recognition
4.4 Fusion
5 Conclusions
References
Multi-scale Opening - A New Morphological Operator
1 Introduction
2 Theory of Multi-Scale Opening of Conjoined Fuzzy Objects
2.1 Optimal Erosion Using Morpho-Connectivity
2.2 Constrained Dilation
2.3 Iterative Progression to Multi-Scale Opening
3 Experimental Results
4 Conclusion
References
Level-by-Level Adaptive Disparity Compensated Prediction in Wavelet Domain for Stereo Image Coding*
1 Introduction
2 Layer-Based Prediction Compensation Formulation
3 Proposed Scheme
3.1 Separable Level-by-Level Adaptive Disparity Compensation Scheme
Logo Recognition Using CNN Features
1 Introduction
2 Proposed Method
3 Selective Search
4 Query Expansion
5 Convolutional Neural Networks
5.1 CNN Features
5.2 Transformation Pursuit
6 Experimental Setup and Results
6.1 Selective Search Evaluation
6.2 Results
7 Results under Image Distortions
7.1 Selective Search Evaluation
7.2 Results
8 Conclusions
References
Person Re-identification Using Robust Brightness Transfer Functions Based on Multiple Detections
1 Introduction
2 Minimum Cumulative Brightness Transfer Function
3 Re-Identification with Min-MCBTF
3.1 Pedestrian Segmentation
3.2 Feature Extraction and Matching
4 Experiment
5 Conclusion
References
Analysis of HOG Suitability for Facial Traits Description in FER Problems
1 Introduction
2 Proposed Methodology
3 Experimental Setup
4 Experimental Results
4.1 Confusion Matrices for All the Datasets
4.2 Comparison with the State of the Art
4.3 Tests on Video Streams
5 Conclusions
References
Difference-Based Local Gradient Patterns for Image Representation
1 Introduction
2 Proposed Descriptors
2.1 A Brief Overview of Local Gradient Patterns(LGP)
2.2 AD-LGP Descriptor
2.3 RD-LGP Descriptor
2.4 ERD-LGP Descriptor
3 Experiments and Results
3.1 Face/Non-face Classification
3.2 Face Identification across Illumination
4 Conclusion and Future Work
References
Non-local Sigma Filter
1 Introduction
2 Calculation of Non-local Sigma Filter
3 Performance Comparison of Filtering Methods
Bold.
4 Conclusions and Future Work
References
A New Multi-resolution Affine Invariant Planar Contour Descriptor
1 Introduction
2 Affine Arc-Length Reparametrization
3 Fourier Descriptors of Affine Invariant Progressive Signature
3.1 Progressive Contour
3.2 Shape Signature
3.3 Fourier Descriptors
4 Experimental Results
5 Conclusion
References
Image Manipulation on Facebook for Forensics Evidence
1 Introduction
2 Motivation and Scenarios
3 Dataset
4 Social Network Image Analysis
4.1 Facebook Resizing Algorithm
4.2 Quantitative Measures
4.3 Quantization Tables
4.4 Metadata
5 Conclusions
References
Improved Performance in Facial Expression Recognition Using 32 Geometric Features
1 Introduction
2 Proposed Metodology
3 Experimental Setup
4 Experimental Results
4.1 Discussion on Confusion Tables
4.2 Comparison with State-of-the-Art Methods
4.3 Tests on Video Sequences
5 Conclusions and Future Works
References
A Selection Module for Large-Scale Face Recognition Systems
1 Introduction
2 Related Works
3 The fg-LS Selection Method
4 Experimental Analysis
4.1 Datasets
4.2 Feature Extraction
4.3 Tests on the fg-LS and Other Assessed Methods
5 Conclusions
References
A Classification-Selection Approach for Self Updating of Face Verification Systems Under Stringent Storage and Computational Requirements
1 Introduction
2 State of the Art of Self-Update
3 The Proposed Method
4 Experimental Result
4.1 Dataset
4.2 Experimental Protocol
4.3 Results
5 Conclusions
References
Super-Sparse Regression for Fast Age Estimation from Faces at Test Time
1 Introduction
2 Age Estimation from Faces
3 Super-Sparse Regression for Fast Age Estimation
4 Experiments
5 Conclusions and Future Work
References
Video Analysis
Automated Recognition of Social Behavior in Rats: The Role of Feature Quality
1 Introduction
2 Rodent Action Recognition
3 Rat Social Behavior Data Set
4 Feature Quality in Social Behavior Recognition
4.1 Eliminating Systematic Tracking Errors in RSBD
4.2 Extracting Features from the Data Set Versions
Feature Set Variants.
4.3 Experiment Setup
5 Results
5.1 Tracking Errors
5.2 Feature Set Variants
6 Discussion
6.1 Difference between Interactions
6.2 Unresolved Confusions
7 Conclusion
References
Scale and Occlusion Invariant Tracking-by-Detection
1 Introduction
1.1 Related Work
2 Scale and Occlusion Invariant Tracking-By-Detection
2.1 Scale Invariance
2.2 Occlusion and Out-of-View Handling
3 Experiments
3.1 Parameters
3.2 Scale Handling Test
3.3 Occlusion Handling Test
3.4 Final Test
4 Conclusion
References
Ensemble of Hankel Matrices for Face Emotion Recognition
1 Introduction
2 Related Work
3 Multi-Scale Face Appearance Representation
4 Ensemble of Hankel Matrices for Emotion-Dynamics
4.1 Hankel Matrix-Based Dynamics Representation
4.2 Emotion-Dynamics Representation
5 Emotion Classification
6 Experimental Results
6.1 Results
7 Conclusions and Future Work
References
A New Approach to Detect Use of Alcohol Through Iris Videos Using Computer Vision
1 Introduction
1.1 Anatomy of the Human Ocular System
2 Material and Methods
2.1 Pupillometer Construction
2.2 Construction of a Video Database
2.3 Characteristics Extraction
3 Results
3.1 Pattern Recognition
4 Discussion
5 Conclusion
References
Selection of Temporal Features for Event Detection in Smart Security
1 Introduction
2 Related Work
3 Preliminaries
3.1 Events
4 Temporal Event Learning
4.1 Temporal Feature Extraction
4.2 Neural Tree Learning
5 Experimental Results
6 Conclusions
References
Detection of Human Movements with Pressure Floor Sensors
1 Introduction
2 The COP MODEL
2.1 Data Model
2.2 People Detection and Tracking
3 Experimental Evaluation
3.1 Experimental Setup
3.2 Reference PIM Method
3.3 Quantitative Results
4 Conclusion and Future Works
References
Object Detection and Tracking from Fixed and Mobile Platforms
1 Introduction
2 HOG Features and the Matching Process
2.1 Gradient Contrast Normalization
3 Tracking as a Search Problem
3.1 Acceptance/Rejection Criteria
4 Object Detection by HOG Model Appearance Updating
4.1 Boot-Strap and First Model Selection
5 Experimental Results
5.1 Dataset and Performance Evaluation
5.2 Detailed Performance Analysis
6 Conclusions
References
Audiovisual Liveness Detection
1 Introduction
2 Text-dependent Bimodal Liveness Detection
2.1 Audio Segmentation
2.2 Visual Features
2.3 Audio-visual Features Extraction
2.4 Decision System
3 Experimental Results
4 Conclusion
References
Foreground Detection Robust Against Cast Shadows in Outdoor Daytime Environment
1 Introduction
2 Related Work
3 Proposed Method
3.1 The Concept of the Proposed Method
3.2 Solar Spectral Model
3.3 Color Change Model in Background
3.4 Extract d Foreground Region
3.5 The Overview of th he Proposed Method
4 Evaluations
4.1 Evaluation of r Color Change Model
4.2 Evaluation of Foreground Region Detection Performance
5 Conclusion
References
A Tool to Support the Creation of Datasets of Tampered Videos
1 Introduction
2 State of the Art
3 Proposed Method
3.1 Selection
3.2 Tracking
3.3 Transformation
3.4 Blending
4 Experiments
4.1 Dataset
4.2 Remarks
5 Conclusions
References
Cognition Helps Vision: Recognizing Biological Motion Using Invariant Dynamic Cues
1 Introduction
2 The Two-Thirds Power Law
3 From the Law to the Features
4 Representing Biological Motion
4.1 Centroid-Based Descriptor
4.2 Histogram-Based Descriptor
5 Experimental Analysis
5.1 Data Set
5.2 Proof of Concepts
5.3 Experiments on Classification
6 Final Discussion
References
Egocentric Object Tracking: An Odometry-Based Solution
1 Introduction and Related Work
2 Motivations
3 Proposed Method
4 Experimental Results
5 Conclusions
References
En Plein Air Visual Agents
1 Introduction
2 Learning Protocol
3 En Plein Air Assessment
4 Pioneer Visual Agents
5 Case Studies
6 Conclusions
References
Modalities Combination for Italian Sign Language Extraction and Recognition
1 Introduction
2 Related Works
3 Feature Representation
3.1 Frame-wise Feature Representation
3.2 Global Feature Representation
4 Action-Segment Spotting
5 Action Recognition Strategy
6 Experiments and Results
7 Conclusion and Perspectives
References
Abnormality Detection with Improved Histogram of Oriented Tracklets
1 Introduction
2 Improved HOT
2.1 Tracklet Extraction
2.2 Histogram of Tracklets Computation
3 Abnormality Detection
4 Experimental Evaluation
4.1 Crowd Datasets
4.2 Evaluating TDT Tracklet Extraction
4.3 Complete iHOT: TDT and Weighted Histogramming
5 Conclusion
References
Author Index
Blank Page

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Image Analysis and Processing - ICIAP 2015

Description

More details

Other editions

Additional editions

Content

System requirements