
Image Analysis and Processing - ICIAP 2017
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 138 papers presented were carefully reviewed and selected from 229 submissions. The papers cover both classic and the most recent trends in image processing, computer vision, and pattern recognition, addressing both theoretical and applicative aspects. They are organized in the following topical sections: video analysis and understanding; pattern recognition and machine learning; multiview geometry and 3D computer vision; image analysis, detection and recognition; multimedia; biomedical and assistive technology; information forensics and security; imaging for cultural heritage and archaeology; and imaging solutions for improving the quality of life.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents - Part II
- Contents - Part I
- Image Analysis, Detection and Recognition
- 3D Face Recognition in Continuous Spaces
- 1 Introduction
- 2 Detection of Characteristic Points in 3D Faces
- 3 Alignment of Two Faces
- 4 Functional Representation
- 5 Experimental Results
- 6 Discussion and Conclusions
- References
- Object Detection for Crime Scene Evidence Analysis Using Deep Learning
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Background of Faster-RCNN
- 3.2 VGG-16 Network
- 3.3 Object Detection
- 4 Experiments and Results
- 4.1 Datasets
- 4.2 Experimental Setup
- 4.3 Detection Accuracy
- 4.4 Detection Time
- 4.5 Experiments on the Karina Dataset
- 4.6 Discussion
- 5 Conclusion
- References
- Person Re-Identification Using Partial Least Squares Appearance Modelling
- 1 Introduction
- 2 Method
- 2.1 Partial Least Squares Foreground Appearance Modelling
- 2.2 Foreground Feature Extraction and Feature Weighting
- 2.3 Distance Metric Learning
- 3 Results and Discussion
- 4 Conclusions
- References
- Gender and Expression Analysis Based on Semantic Face Segmentation
- 1 Introduction
- 2 Related Works
- 3 The Face Segmentation Algorithm
- 3.1 Feature Extraction
- 3.2 Classification
- 4 The Proposed Gender and Expression Classification Algorithms
- 4.1 Gender Classification
- 4.2 Expression Classification
- 5 Experimental Setup
- 5.1 Gender and Expression Classification
- 6 Discussion of Results
- 6.1 Gender Recognition
- 6.2 Expression Recognition
- 7 Conclusions
- References
- Two More Strategies to Speed Up Connected Components Labeling Algorithms
- 1 Introduction
- 2 Previous Works
- 3 Pattern Analysis and Modeling of Decision Trees
- 4 Parallel Connected Components Labeling
- 5 Experimental Evaluation
- 5.1 Datasets
- 5.2 Frequencies Results
- 5.3 Parallel Results
- 6 Conclusions
- References
- Embedded Real-Time Visual Search with Visual Distance Estimation
- 1 Introduction
- 2 Related Work
- 3 Proposed Pipeline
- 3.1 Image Analyzer
- 3.2 Retrieval Stage
- 3.3 Multiple Results Loop
- 3.4 Distance Estimation
- 4 Experiments and Results
- 4.1 Distance Estimation Accuracy
- 4.2 Performances
- 5 Conclusions
- References
- Synchronization in the Symmetric Inverse Semigroup
- 1 Introduction
- 2 Synchronization
- 2.1 Matrix Formulation
- 3 Problem Formulation
- 4 Permutation Synchronization
- 5 Partial Permutation Synchronization
- 6 Experiments
- 7 Conclusion
- References
- A Fully Convolutional Network for Salient Object Detection
- 1 Introduction
- 2 Proposed Method
- 2.1 Training
- 3 Experiments
- 3.1 Datasets
- 3.2 Data Augmentation
- 3.3 Evaluation Measures
- 3.4 Results
- 4 Conclusions
- References
- A Lightweight Mamdani Fuzzy Controller for Noise Removal on Iris Images
- 1 Introduction
- 2 The Proposed Algorithm
- 2.1 Iris Detection and Decomposition
- 2.2 The SKE Values
- 2.3 The Fuzzy Rules
- 3 Preliminary Results
- 4 Conclusions
- References
- Analysis of the Discriminative Generalized Hough Transform for Pedestrian Detection
- 1 Introduction
- 2 Methods
- 2.1 Structured Edge Detection
- 2.2 Discriminative Generalized Hough Transform
- 2.3 Rejection of Proposals
- 3 Experimental Setup
- 3.1 Databases
- 3.2 Experimental Setup and System Parameters
- 3.3 Comparison to State-of-the-Art Approaches
- 3.4 Evaluation Metrics
- 4 Results
- 4.1 SCM Rejection
- 4.2 SCM Rejection: Error Analysis
- 4.3 SCM Rejection: Oracle Experiments
- 4.4 CNN Rejection: Detection Results
- 5 Discussion
- 6 Conclusions
- References
- Bubble Shape Identification and Calculation in Gas-Liquid Slug Flow Using Semi-automatic Image Segmentation
- 1 Introduction
- 2 Materials and Methods
- 2.1 Image Acquisition
- 2.2 Image Segmentation by Level Set Method
- 2.3 A Priori Shape Definition
- 2.4 Level Set Priori Shape Restrict - LSR
- 3 Proposed Scheme to Two-Phase Flow Image Segmentation
- 4 Experimental Results
- 4.1 Validation
- 4.2 Wire-Mesh Image Comparison and Grey Levels Images
- 4.3 Gas Bubbles Velocity
- 5 Conclusion
- References
- Deep Face Model Compression Using Entropy-Based Filter Selection
- 1 Introduction
- 2 Related Works
- 3 Entropy-Based Model Compression
- 3.1 Framework
- 3.2 Entropy-Based Prune Metric
- 3.3 Network Trimming
- 4 Experiments
- 4.1 VGG-16 Network
- 4.2 WebFace Network
- 4.3 Effectiveness Analysis
- 5 Conclusion
- References
- Deep Passenger State Monitoring Using Viewpoint Warping
- 1 Introduction
- 2 Method
- 2.1 Image Alignment Using Homography
- 2.2 Synthesising Viewpoint Changes
- 2.3 Passenger State Classification
- 3 Experiments and Results
- 3.1 Dataset
- 3.2 Evaluation
- 3.3 Results
- 4 Conclusions
- References
- Demographic Classification Using Skin RGB Albedo Image Analysis
- 1 Introduction
- 1.1 Skin Anatomy
- 1.2 Skin Visual Perception
- 1.3 Skin Related Demographics
- 2 Related Work
- 2.1 Skin Classification Based on Skin Aging and Light Exposure
- 2.2 Light-Skin Interaction Prediction: BSSRDF
- 2.3 State of the Art Skin Models
- 3 Proposed Albedo Based Descriptor
- 3.1 RGB Albedo Descriptor
- 4 Demographic Classification Results and Analysis
- 4.1 Gender, Skin Type and Age Clustering
- 4.2 Gender, Skin Type and Age Classification
- 5 Conclusion
- References
- Discriminative Dictionary Design for Action Classification in Still Images
- 1 Introduction
- 2 Related Works
- 2.1 Action Recognition from Still Images
- 2.2 Efficient Codebook Construction for Classification
- 3 Proposed Algorithm
- 3.1 Extraction of Local Features
- 3.2 Discriminative Dictionary Learning
- 3.3 Feature Encoding Using C"0362C
- 3.4 Classification
- 4 Experimental Details
- 4.1 Dataset
- 4.2 Experimental Setup
- 4.3 Performance Evaluation
- 5 Conclusion
- References
- Enhanced Bags of Visual Words Representation Using Spatial Information
- 1 Introduction
- 2 Traffic Signs Recognition
- 2.1 Enhanced BoVW Using Spatial Information
- 2.2 Similarity Measure
- 3 Experiment Results
- 3.1 Performance of the Proposed Method
- 3.2 Comparisons with Other State-of-the-Art Methods
- 4 Conclusions
- References
- Exploiting Spatial Context in Nonlinear Mapping of Hyperspectral Image Data
- 1 Introduction
- 2 Methods
- 2.1 Dimensionality Reduction
- 2.2 Exploiting Spatial Context in Dimensionality Reduction
- 3 Experimental Study
- 3.1 Classification of Hyperspectral Image Data
- 3.2 Clustering and Segmentation of Hyperspectral Image Data
- 3.3 Visualization of Hyperspectral Image Data
- 4 Conclusion
- References
- Exploiting Visual Saliency Algorithms for Object-Based Attention: A New Color and Scale-Based Approach
- 1 Introduction
- 2 State of the Art
- 3 Proposed Methods
- 3.1 Eye Tracking Data Acquisition
- 3.2 Proposed Saliency Map Generation Method
- 4 Experimental Results
- 5 Conclusion and Future Works
- References
- Face Recognition with Single Training Sample per Subject
- 1 Introduction
- 2 Background of Local Binary Patterns
- 3 Overview of Proposed Approach
- 3.1 Offline Phase
- 3.2 Online Phase
- 3.3 Optimization and Classification
- 3.4 Parameter Setting
- 4 Experimental Results
- 4.1 The Experiments Comparison: FR on FRGCv1, OR, CK+, FEI and GT Databases
- 4.2 Running Time Comparison
- 5 Conclusion
- References
- Food Recognition Using Fusion of Classifiers Based on CNNs
- 1 Introduction
- 2 Methodology
- 2.1 Training of CNN Models
- 2.2 Decision Templates for Classifiers Fusion
- 3 Experiments
- 3.1 Datasets
- 3.2 Experimental Setup
- 3.3 Data Preprocessing and Metrics
- 3.4 Experimental Results on Food-11
- 3.5 Experimental Results on Food-101
- 4 Conclusions
- References
- MR Brain Tissue Segmentation Based on Clustering Techniques and Neural Network
- 1 Introduction
- 2 Related Work
- 3 The Proposed Method
- 3.1 Training Phase
- 3.2 Testing Phase
- 4 Experimental Results
- 5 Conclusions
- References
- Multi-branch CNN for Multi-scale Age Estimation
- 1 Introduction
- 2 Related Works
- 3 Multi-branch CNN
- 4 Experimental Results
- 5 Conclusions
- References
- No-Reference Learning-Based and Human Visual-Based Image Quality Assessment Metric
- 1 Introduction
- 2 The LEVIQI Index
- 2.1 General Framework
- 2.2 Visual Sub-band Decomposition
- 2.3 Selected Features
- 3 Performance Evaluation
- 3.1 Experimental Setup
- 3.2 Experimental Results
- 4 Conclusion
- References
- Performance Evaluation of Multiscale Covariance Descriptor in Underwater Object Detection
- Abstract
- 1 Introduction
- 2 Autonomous Underwater Vehicle
- 3 Image Descriptors
- 3.1 Global Approach
- 3.2 Type of Descriptor
- 3.3 Multiscale Covariance Descriptor
- 3.4 Support Vector Machine
- 4 Experimental Result
- 4.1 Evaluation Metric
- 4.2 Maris Dataset
- 4.3 Result
- 5 Conclusion
- References
- Retinal Vessel Segmentation Through Denoising and Mathematical Morphology
- 1 Introduction
- 2 Dataset
- 3 Method
- 3.1 Denoising: Non-local Means Algorithm
- 3.2 Mathematical Morphology: Black Top-Hat
- 3.3 Image Thresholding
- 4 Experiments
- 5 Conclusions
- References
- Segmentation of Green Areas Using Bivariate Histograms Based in Hue-Saturation Type Color Spaces
- 1 Introduction
- 2 Theoretical Framework
- 2.1 Color Spaces
- 2.2 Morphological Filter
- 2.3 Watershed with Dynamics
- 3 Metodology
- 4 Results
- 5 Conclusion
- References
- Spatial Enhancement by Dehazing for Detection of Microcalcifications with Convolutional Nets
- 1 Introduction
- 2 Dataset
- 3 Spatial Enhancement by Dehazing
- 3.1 Image Dehazing
- 3.2 Dark Channel Prior
- 3.3 Spatial Enhancement of Microcalcifications
- 4 Convolutional Neural Networks
- 5 Experiments
- 6 Results
- 7 Conclusions
- References
- Towards Automatic Skin Tone Classification in Facial Images
- Abstract
- 1 Introduction
- 2 State of the Art
- 3 Proposed Solution
- 3.1 Region of Interest Selection
- 3.2 Color Descriptors
- 3.3 Pixel Based Classification
- 3.4 Patch Based Classification
- 4 Experimental Results and Discussions
- 5 Conclusions and Future Work
- References
- Towards Detecting High-Uptake Lesions from Lung CT Scans Using Deep Learning
- 1 Introduction
- 1.1 Contribution
- 1.2 Paper Structure
- 2 Related Literature
- 3 Detecting High-Uptake Lesions Using a CNN
- 4 Experimental Results
- 4.1 Experimental Setup
- 4.2 Analysis and Discussion
- 5 Conclusions and Outlook
- References
- Semi-automatic Training of a Vehicle Make and Model Recognition System
- 1 Introduction
- 2 Related Work
- 3 System Description
- 3.1 Detection: Vehicle Localization
- 3.2 Classification: Make and Model Recognition
- 4 Evaluation of Proposed System
- 4.1 Dataset
- 4.2 Evaluation Metrics
- 4.3 Vehicle Detection
- 4.4 Make and Model Classification
- 5 Conclusions
- References
- A Computer Vision System for Monitoring Ice-Cream Freezers
- 1 Introduction
- 2 Description of the Modules
- 2.1 Basket Edges Detection (BED) Module
- 2.2 Volume Estimation (VE) Module
- 2.3 Product Tracking (PT) Module
- 3 Experimental Results
- 4 Conclusions and Future Work
- References
- A Proposal of Objective Evaluation Measures Based on Eye-Contact and Face to Face Conversation for Videophone
- Abstract
- 1 Introduction
- 2 Human Behaviors in Conversation
- 2.1 Eye-Contact Conversation Ratio (ECCR)
- 2.2 Face to Face Conversation Ratio (FFCR)
- 3 Experimental System
- 3.1 Videophone System
- 3.2 Gaze Point Estimation
- 3.3 Signal Processing Flow
- 4 Experimental Results and Discussion
- 4.1 ECCR and FFCR in Higher Camera Position
- 4.2 ECCR and FFCR in Center Camera Position
- 5 Conclusion
- References
- Multimedia
- Wink Detection on the Eye Image as a Control Tool in Multimodal Interaction
- Abstract
- 1 Introduction
- 2 The Task Analysis and the Main Assumptions of the Project
- 3 Introduced Technical Solution
- 4 Influence of Infrared Radiation on the Eyeball
- 5 Algorithm of the Eye Winking Recognition
- 6 Analysis of Signals Generated from Eye Winks
- 7 The Prototype and Tests
- 8 Summary
- References
- Adaptive Low Cost Algorithm for Video Stabilization
- Abstract
- 1 Introduction
- 2 Prior Art
- 3 Proposed Filtering
- 4 Experimental Results
- 5 Conclusion and Future Work
- References
- Remote Biometric Verification for eLearning Applications: Where We Are
- 1 Introduction
- 2 eLearning Technologies
- 3 The Personal Verification Issue: The Biometric Perspective
- 4 Discussions
- References
- Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach
- 1 Introduction
- 2 Related Work
- 3 The M-VAD Names Dataset
- 4 Replacing the ``Someone'': An Approach to Video Description with Naming
- 4.1 Multi-Modal Network
- 4.2 Face Recognition
- 5 Experimental Evaluation
- 5.1 Experimental Results
- 6 Conclusion
- References
- Biomedical and Assistive Technology
- Bio-Inspired Feed-Forward System for Skin Lesion Analysis, Screening and Follow-Up
- Abstract
- 1 Introduction
- 2 Proposed Pipeline: System Description
- 2.1 Dermatoscope and SC-CNNs Pre-processing Block
- 2.2 The Hand-Crafted Image Features and SC-CNNs Hand-Crafted Blocks
- 2.3 The LV Network Clustering System
- 2.4 The Autonomous Diagnosis System
- 3 Experimental Results and Future Works
- References
- On the Estimation of Children's Poses
- 1 Introduction and Motivations
- 2 Related Work
- 3 Methods and Dataset
- 3.1 Dataset
- 4 Comparative Evaluation
- 5 Conclusion
- References
- Optical Coherence Tomography Denoising by Means of a Fourier Butterworth Filter-Based Approach
- 1 Introduction
- 2 Methodology
- 2.1 Fourier Butterworth Image Filtering
- 2.2 Post Processing
- 2.3 Automatic Validation Process
- 3 Results and Discussion
- 4 Conclusions
- References
- Smartphone Based Pupillometry: An Empirical Evaluation of Accuracy and Safety
- 1 Introduction
- 2 Related Work
- 3 Assessing Mobile Phones for Pupillometry
- 3.1 The Sober-Eye Approach to PLR Measurement
- 3.2 Experimental Set-Up and Results
- 3.3 The Dataset
- 3.4 Testing the Accuracy of the Pupil Radius Measurement
- 4 Light Hazard Evaluation
- 4.1 Measurements
- 4.2 Results
- 5 Conclusions
- References
- Pixel Classification Methods to Detect Skin Lesions on Dermoscopic Medical Images
- 1 Introduction
- 2 Related Work
- 3 Visual Features and Skin Image Processing
- 3.1 Hair Removing
- 3.2 Skin Lesion Detection
- 4 Experimental Setup and Results
- 5 Conclusions and Future Work
- References
- Feature Definition and Selection for Epiretinal Membrane Characterization in Optical Coherence Tomography Images
- 1 Introduction
- 2 Methodology
- 2.1 Identification of the Region of Interest
- 2.2 Feature Definition
- 2.3 Feature Selection and Classification
- 3 Results and Discussion
- 4 Conclusions
- References
- Fully-Automated CNN-Based Computer Aided Celiac Disease Diagnosis
- 1 Introduction
- 2 Proposed Pipeline
- 2.1 Discriminative Patch-Based Model
- 2.2 Probabilistic Patch-Based Model
- 2.3 Image-Wise Classification
- 2.4 Patient-Wise Classification
- 2.5 Image Representations
- 3 Experiments
- 3.1 Image Data Sets
- 3.2 Evaluation and Implementation Details
- 3.3 Results
- 3.4 Discussion and Conclusion
- References
- An Investigation of Deep Learning for Lesions Malignancy Classification in Breast DCE-MRI
- 1 Introduction
- 2 Materials and Methods
- 2.1 Dataset
- 2.2 Lesion Diagnosis in DCE-MRI
- 2.3 CNN for Lesion Diagnosis
- 2.4 Performance Evaluation
- 3 Experimental Results
- 4 Discussion and Conclusions
- References
- A Smartphone-Based System for Detecting Falls Using Anomaly Detection
- 1 Introduction
- 2 The Proposed Method
- 3 Experiments
- 3.1 Datasets
- 3.2 Results
- 4 Conclusion
- References
- CNN-Based Identification of Hyperspectral Bacterial Signatures for Digital Microbiology
- 1 Introduction
- 2 Proposed Method
- 3 Results and Discussion
- 4 Conclusion
- References
- Description of Breast Morphology Through Bag of Normals Representation
- 1 Introduction and Motivation
- 2 Materials and Methods
- 2.1 3D Breast Dataset
- 2.2 Shape Parametrization
- 3 Results
- 4 Conclusions
- References
- Measuring Refractive Properties of Human Vision by Showing 4D Light Fields
- 1 Introduction
- 2 Related Work
- 3 Refractive Properties of Human Vision
- 4 Estimating Refractive Properties from 4D Light Field
- 4.1 Observation of Light Field in Human Vision
- 4.2 Measuring Eyesight Characteristics from 4D Light Field
- 5 Experiments
- 5.1 Real Image Experiments
- 5.2 Accuracy Evaluation
- 6 Conclusion
- References
- Crossing the Road Without Traffic Lights: An Android-Based Safety Device
- 1 Introduction
- 2 Stationary Location-Specific Solution
- 3 Principles of Operation
- 3.1 Activity Estimation
- 3.2 Detecting Approaching Vehicles
- 3.3 Setting Detector Parameters
- 4 Examples and Evaluation
- 5 Real-Time Implementation
- 6 Discussion
- References
- Information Forensics and Security
- A Novel Statistical Detector for Contourlet Domain Image Watermarking Using 2D-GARCH Model
- 1 Introduction
- 2 Statistical Modeling of Contourlet Coefficients
- 2.1 Contourlet Transform
- 2.2 2D-GARCH Model
- 2.3 2D-GARCH Model for Contourlet Coefficients
- 3 Proposed Watermarking Scheme
- 3.1 Watermark Insertion
- 3.2 Watermark Detection
- 4 Experimental Results
- 5 Conclusion
- References
- H-264/RTSP Multicast Stream Integrity
- 1 Introduction
- 2 State of the Art
- 3 Operating Environment
- 3.1 H.264/AVC/SVC
- 3.2 RTSP/RTP in Short
- 3.3 Cryptographic Functions
- 4 Our Method
- 4.1 Setup Procedure
- 4.2 Sender Procedure
- 4.3 Receiver Procedure
- 4.4 Restart on Lost Packet
- 5 Implementation Details
- 5.1 Setup Procedure
- 5.2 Sender and Receiver Procedure
- 5.3 Implementation
- 6 Conclusions and Future Works
- References
- PRNU-Based Forgery Localization in a Blind Scenario
- 1 Introduction
- 2 Camera-Based Forgery Localization Framework
- 2.1 Residual-Based Image Clustering
- 2.2 Camera Fingerprint Estimation
- 2.3 Camera Assignment
- 2.4 PRNU-Based Forgery Localization
- 3 Experimental Results
- 3.1 Image Clustering and PRNU Estimation
- 3.2 Image to Cluster Assignment
- 3.3 Forgery Localization
- 4 Conclusion
- References
- Recognizing Context for Privacy Preserving of First Person Vision Image Sequences
- 1 Introduction
- 2 Proposed System
- 2.1 Scenario and Communication Protocol
- 3 Visual Context Recognition
- 3.1 Bag-of-Words and k-Nearest Neighbors Algorithm
- 3.2 AlexNet and SVM Algorithm
- 4 Experimental Settings and Results
- 4.1 Dataset
- 4.2 BoW Model
- 4.3 Beacon-Enhanced BoW Model
- 4.4 AlexNet Model
- 4.5 Discussion
- 5 Conclusions
- References
- GRAPHJ: A Forensics Tool for Handwriting Analysis
- 1 Introduction
- 2 GRAPHJ
- 2.1 Automated Search of Text Lines
- 2.2 Automated Detection of Words
- 2.3 Automated Search of Characters
- 2.4 Measures
- 3 Experimental Analysis
- 4 Conclusion
- References
- Identity Documents Classification as an Image Classification Problem
- 1 Introduction
- 2 Previous Works
- 3 A Plurality of Methods
- 3.1 Bag-of-Words
- 3.2 Fisher Vectors
- 3.3 VLAD
- 3.4 Convolutional Neural Networks
- 4 Experiments
- 4.1 Datasets
- 4.2 Results
- 5 Conclusion
- References
- Using LDP-TOP in Video-Based Spoofing Detection
- 1 Introduction
- 2 The Proposed Method
- 2.1 The Recaptured Artifacts
- 2.2 Processing Pipeline
- 3 Experimental Analysis
- 3.1 Parameter Selection
- 3.2 Comparisons with State-of-the-Art Approaches
- 3.3 Computational Complexity
- 4 Conclusions
- References
- A Classification Engine for Image Ballistics of Social Data
- 1 Introduction
- 2 A Dataset of Social Imagery
- 3 Dataset Analysis
- 3.1 Image Filename Alterations
- 3.2 Image Size Alterations
- 3.3 Meta-Data Alterations
- 3.4 Image JPEG Compression Alterations
- 4 Image Ballistics of Social Data
- 4.1 Implementing Image Ballistics: A Classification Engine
- 4.2 Classification Results
- 5 Conclusions and Future Works
- References
- Join Cryptography and Digital Watermarking for 3D Multiresolution Meshes Security
- 1 Introduction
- 2 Related Works
- 3 Techniques and Methods
- 3.1 Encrypting Logo: AES Algorithm
- 3.2 Wavelet Transform
- 3.3 Concolutional Error Correcting Code
- 4 Proposed Approach
- 4.1 Embedding
- 4.2 Extraction
- 5 Results
- 5.1 Encryption System Evaluation
- 5.2 Watermarking Algorithm Evaluation
- 6 Conclusion
- References
- Kinect-Based Gait Analysis for People Recognition Over Time
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 4 Datasets
- 5 Experimental Results
- 6 Conclusion
- References
- Imaging for Cultural Heritage and Archaeology
- ARCA (Automatic Recognition of Color for Archaeology): A Desktop Application for Munsell Estimation
- 1 Introduction
- 2 Material and Methods
- 2.1 Acquisition Phase
- 2.2 ARCA Desktop Application
- 2.3 Validation Phase
- 3 Results
- 3.1 Best Configuration
- 3.2 Best Order Statistic
- 3.3 Discretization
- 3.4 Color Tolerance
- 4 Conclusions
- References
- Two-Stage Recognition for Oracle Bone Inscriptions
- 1 Introduction
- 2 Related Work
- 3 Recognition Flow
- 4 Preprocessing
- 4.1 Noise Reduction Processing
- 4.2 Skeleton Extraction
- 4.3 Line Feature Extraction
- 5 Recognition
- 5.1 First-Stage Recognition Using Distance Calculation
- 5.2 Second Stage Recognition Using Checkpoints
- 6 Experimental Results
- 6.1 Recognition Results
- 6.2 Recognition Analysis
- 7 Conclusion
- References
- Imaging Solutions for Improving the Quality of Life
- Real Time Indoor 3D Pipeline for an Advanced Sensory Substitution Device
- Abstract
- 1 Introduction
- 2 State of the Art
- 3 3D Processing Algorithms
- 3.1 Pre-processing
- 3.2 Planar Segmentation
- 3.3 Labeling
- 4 Experimental Results
- 5 Conclusions
- Acknowledgement
- References
- Contactless Physiological Data Analysis for User Quality of Life Improving by Using a Humanoid Social Robot
- 1 Introduction
- 2 Physiological Parameters
- 3 Sensors
- 4 Methodology: Data Extraction and Analysis
- 4.1 Blink
- 4.2 Temperature Variation
- 4.3 Respiration
- 4.4 AUs
- 5 Results
- 5.1 Blinking
- 5.2 Thermal Data
- 5.3 Respiration
- 5.4 AUs
- 6 Discussion
- 7 Conclusion and Future Work
- References
- Exploiting Social Images to Understand Tourist Behaviour
- 1 Introduction
- 2 Proposed Method
- 2.1 Data Extraction and Exploration
- 2.2 Data Mining Techniques to Analyze Travel Preferences
- 3 Case Study
- 3.1 Analysis of Tourist Movements
- 4 Conclusion
- References
- Showing Different Images to Observers by Using Difference in Retinal Impulse Response
- 1 Introduction
- 2 Observation Model
- 2.1 Temporal Impulse Response of Human Retina
- 2.2 Observation Model from Impulse Response
- 2.3 Observation Model for Periodic Signals
- 3 Multiplex Image Representation from Impulse Response
- 4 Contrast Adjustment of Objective Images
- 4.1 Contrast Adjustment for a Whole Image
- 4.2 Pixel-Wise Contrast Adjustment
- 5 Experimental Results
- 5.1 Multiplex Image Representation
- 5.2 Comparison
- 6 Conclusion
- References
- A Framework for Activity Recognition Through Deep Learning and Abnormality Detection in Daily Activities
- 1 Introduction
- 2 Related Works
- 3 System Description
- 3.1 Human Tracking
- 3.2 Activity Recognition
- 3.3 Observing Abnormal Activities
- 4 Evaluation Results
- 5 Conclusion and Future Work
- References
- Combining Color Fractal with LBP Information for Flood Segmentation in UAV-Based Images
- Abstract
- 1 Introduction
- 2 Proposed Method
- 2.1 Color Fractal Dimension
- 2.2 Color Local Binary Patterns
- 2.3 Image Segmentation
- 3 Experimental Results
- 4 Conclusions
- Acknowledgements
- References
- Interconnected Neural Networks Based on Voting Scheme and Local Detectors for Retinal Image Analysis and Diagnosis
- Abstract
- 1 Introduction
- 2 Methodology and Algorithm
- 2.1 Learning Phase
- 2.2 Optic Disc and Macula Segmentation
- 2.3 Hemorrhages and Exudates Classification
- 2.4 Blood Vessels Segmentation
- 3 Experimental Results
- 4 Conclusion
- References
- A Unified Color and Contrast Age-Dependent Visual Content Adaptation
- 1 Introduction
- 2 Background
- 3 Age-Based Content Adaptation Method
- 3.1 White Balance
- 3.2 Contrast Sensitivity Function
- 4 Experimental Validation
- 5 Conclusion
- References
- Deep Appearance Features for Abnormal Behavior Detection in Video
- 1 Introduction
- 2 Related Work
- 3 Method
- 3.1 Feature Extraction
- 3.2 Learning Model
- 4 Experiments
- 4.1 Data Sets
- 4.2 Evaluation
- 4.3 Implementation Details
- 4.4 Results on the Avenue Data Set
- 4.5 Results on the UMN Data Set
- 5 Conclusion and Future Work
- 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.