Image and Graphics

Name: Image and Graphics | 9th International Conference, ICIG 2017, Shanghai, China, September 13-15, 2017, Revised Selected Papers, Part I
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

9th International Conference, ICIG 2017, Shanghai, China, September 13-15, 2017, Revised Selected Papers, Part I

Yao Zhao Xiangwei Kong David Taubman(Editor)

Springer (Publisher)

Published on 29. December 2017

XXX, 705 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-71607-7 (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 - Part I
Contents - Part II
Contents - Part III
S2DLDP with its Application to Palmprint Recognition
Abstract
1 Introduction
2 Palmprint Feature Extraction Based S2DLDP
2.1 Two-Dimensional Discriminant Locality Preserving Projections (2DDLPP)
2.2 Sparse Two-Dimensional Local Discriminant Projections (S2DLDP)
3 The Experimental Results and Analysis
3.1 The Non-zero Number Test Result
3.2 The Image Size Test Result
3.3 The Comparative Test Result with LDA, LPP and DLPP
4 Conclusions
Acknowledgments
References
A Hierarchical Voting Scheme for Robust Geometric Model Fitting
1 Introduction
2 A Hierarchical Voting Scheme for Model Fitting
2.1 The Consensus Voting of the Hierarchical Voting Scheme
2.2 The Preference Voting of the Hierarchical Voting Scheme
2.3 The Complete Method
3 Experiments
3.1 Line Fitting and Outlier Removal
3.2 Homography Based Segmentation
3.3 Two-View Based Motion Segmentation
4 Conclusion
References
Multi-kernel Hashing with Semantic Correlation Maximization for Cross-Modal Retrieval
1 Introduction
2 Proposed Algorithm
2.1 Learning Hash Functions
2.2 Learning Projection Matrices
2.3 Optimizing the Weights of Multiple Kernels
3 Experiments
3.1 Datasets
3.2 Experimental Setup
3.3 Experimental Results
3.4 Parameters Sensitivity Study
4 Conclusions
References
Preprocessing and Segmentation Algorithm for Multiple Overlapped Fiber Image
Abstract
1 Introduction
2 Fiber Image Preprocessing
2.1 Target Fiber Protrusion Method by Visual Significance Theory
2.2 Contour Extraction of Target Fiber Image
3 Concave Points Matching and Fiber Segmentation Algorithm
3.1 Extraction Method of Fiber Contour Concave Points
3.2 Concave Points Matching Method
3.3 Fiber Image Segmentation Method Based on Concave Points Matching
4 Experimental Results
4.1 The Basic Morphology of Overlapped Fiber Images
4.2 Discussion of Matching and Segmentation Results
4.3 Matching Error and Resolvent
5 Conclusions and Perspectives
Acknowledgments
References
Action Graph Decomposition Based on Sparse Coding
Abstract
1 Introduction
1.1 Sparse Coding for Visual Computing
2 Action Graph from Dense Trajectories
2.1 Grouping Dense Trajectories
2.2 Action Graphs
2.3 Action Graph Representation with Sparse Coding
2.3.1 Laplacian Matrix of Action Graphs
2.3.2 Sparse Coding for Action Graphs
2.3.3 Distance Between Action Graphs
2.4 Experimental Results
3 Summary
Acknowledgement
References
An Unsupervised Change Detection Approach for Remote Sensing Image Using Visual Attention Mechanism
Abstract
1 Introduction
2 Methodology
2.1 An Overview of the Approach
2.2 Key Steps of the Approach
3 Experimental Results and Analysis
3.1 Experimental Datasets
3.2 Change Detection Results and Analysis
4 Conclusions
References
An Efficient and Robust Visual Tracking via Color-Based Context Prior Model
Abstract
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Dense Spatio-Temporal Context Prior Model
3.2 The Proposed Saliency Prior Model
3.3 Lookup-Table Update Scheme
3.4 Scale Update Scheme
4 Experimental Results and Analysis
4.1 Experimental Setup
4.2 Evaluation Metrics
4.3 Quantitative Comparisons
4.4 Qualitative Comparisons
5 Conclusion
Acknowledgements
References
Non-local L0 Gradient Minimization Filter and Its Applications for Depth Image Upsampling
1 Introduction
2 Non-local L0 Gradient Minimization
3 Depth Image Upsampling
4 Conclusion
References
Salient Object Detection via Google Image Retrieval
1 Introduction
2 Our Proposed Approach
2.1 Google Image Search
2.2 Matching
2.3 Superpixel Segmentation and Fusion
2.4 Saliency Estimation
3 Experimental Results
3.1 Experimental Setup
3.2 Comparison of Approaches
4 Conclusion
References
Abnormal Gait Detection in Surveillance Videos with FFT-Based Analysis on Walking Rhythm
Abstract
1 Introduction
2 The Proposed Method
2.1 Gait Silhouette Extraction
2.2 Aspect Ratio
2.3 Statistic over FFT Regarding Periodicity
3 Experiments
3.1 Data Collection
3.2 Performance Evaluation
4 Conclusions
Acknowledgments
References
Uncooperative Gait Recognition Using Joint Bayesian
1 Introduction
2 Gait Recognition
2.1 Gait Verification Using Joint Bayesian
2.2 Gait Identification Using Joint Bayesian
3 Experiments
3.1 Experiments Settings
3.2 Experimental Results on OULP
3.3 Experimental Results on CASIA-B
4 Conclusion
References
Pedestrian Detection via Structure-Sensitive Deep Representation Learning
1 Introduction
2 Proposed Method
2.1 Candidate Region Extraction
2.2 Structure-Sensitive RoI Pooling
2.3 Multi-task Loss with Classification and Localization
2.4 Pre-training with Triplet Loss
3 Experiments
3.1 Experimental Results
3.2 Results with Different IoU Thresholds
3.3 Detection Speed Analysis
4 Conclusion
References
Two-Stage Saliency Fusion for Object Segmentation
Abstract
1 Introduction
2 Proposed Saliency Fusion for Object Segmentation
2.1 Fusion Based on Average and Min-Max Statistics
2.2 Fusion Based on Fourier Transform of AF Map and MMF Map
2.3 Object Segmentation
3 Experimental Results
3.1 Experimental Setting
3.2 Quantitative Comparison
3.3 Qualitative Comparison
3.4 Computation Cost
3.5 Discussion
4 Conclusion
Acknowledgements
References
Recognition of Offline Handwritten Mathematical Symbols Using Convolutional Neural Networks
Abstract
1 Introduction
2 A Brief Introduction of BN, GAP and Very Small Convolutional Kernels
2.1 Batch Normalization
2.2 Global Average Pooling
2.3 1 × 1 and 3 × 3 Convolutional Kernels
3 Datasets
3.1 CROHME Offline Data Generation
3.2 Data Enrichment
4 Network Configurations
5 Experiments
5.1 Experiments in CROHME Dataset
5.2 Experiments in HASYv2 Dataset
6 Conclusion
References
4D ISIP: 4D Implicit Surface Interest Point Detection
1 Introduction
2 Related Work
3 Method
3.1 Acquisition of 3D Human Motion Dataset
3.2 3D Spatial Temporal Interest Points
3.3 4D Implicit Surface Interested Points
4 Experiments
4.1 3D Human Action Reconstruction
4.2 4D-ISIP Detection
4.3 Comparison with 3D STIP
5 Conclusions
References
Integrative Embedded Car Detection System with DPM
Abstract
1 Introduction
2 Algorithm and Implementation of Detection System
2.1 DPM Algorithm Overview
2.2 System Architecture
2.3 Feature Pyramid and Optimization
2.4 Convolution of Feature Matrix
2.5 Communication
3 Experiments and Evaluation
3.1 Assessment Architecture
3.2 Results
4 Conclusion
Acknowledgements
References
Online Fast Deep Learning Tracker Based on Deep Sparse Neural Networks
Abstract
1 Introduction
2 Deep Sparse Neural Network for Tracking
2.1 Sparse Auto-Encoders with ReLU
2.2 Online Tracking Network
3 Proposed Tracking Algorithm
3.1 Initialization of the Tracking Network
3.2 Local Confidence Maps
3.3 Online Adaptive Model Update
3.4 Overall Process of Proposed Algorithm
4 Experiments
4.1 Qualitative Comparison
4.2 Quantitative Comparison
4.3 Tracking Speed Comparison
5 Conclusions
Acknowledgments
References
Affine-Gradient Based Local Binary Pattern Descriptor for Texture Classification
1 Introduction
2 Affine-Gradient Based Local Pattern Descriptor
2.1 Overview of LBP Method
2.2 Affine-Gradient Based Descriptors
2.3 Rotation Invariance
2.4 Feature Selection
2.5 Classification Method
3 Experiments
3.1 Outex12
3.2 Outex10
3.3 KTH-TIPS2 Dataset
4 Conclusion
References
Deep Convolutional Neural Network for Facial Expression Recognition
Abstract
1 Introduction
2 Related Works
3 Proposed Approach
3.1 Convolutional Neural Networks
3.2 Transfer Face Net to Exp Net
3.3 Modified Softmax Loss Function (Softmax-MSE)
3.4 Double Activation Layer
4 Experiments
4.1 Preprocessing on SFEW 2.0 New and FER2013
4.2 Experiments and Results on SFEW2.0 and FER2013
5 Conclusions and Future Works
Acknowledgment
References
A New Framework for Removing Impulse Noise in an Image
Abstract
1 Introduction
2 Impulse Noise Model
3 A New Denoising Framework
3.1 Description of the Denoising Framework
3.2 Details of the Denoising Framework
4 Experiment and Results
5 Some Discussion
6 Conclusion
Acknowledgment
References
Joint Classification Loss and Histogram Loss for Sketch-Based Image Retrieval
1 Introduction
2 Related Work
3 Methodology
3.1 Network Architecture
3.2 Classification Loss
3.3 Histogram Loss
3.4 Optimization
4 Experiment
4.1 Dataset
4.2 Experimental Settings
4.3 Evaluation
4.4 Results
4.5 Running Cost
5 Conclusion and Future Work
References
Correlation Based Identity Filter: An Efficient Framework for Person Search
1 Introduction
2 Related Work
3 Approach
3.1 Cropping Original Patches and Dense Sampling
3.2 Learning Identity Filter
3.3 Search the Query Person
4 Experiment
4.1 Dataset and Evaluation Protocols
4.2 Implementation Details
4.3 Results
5 Conclusion
References
An Online Approach for Gesture Recognition Toward Real-World Applications
1 Introduction
2 Approach
2.1 Gesture Recognition Network
2.2 Target Localization
2.3 Optical Flow Improvement
2.4 Integration
3 Experiments
3.1 Datasets
3.2 Evaluation on Online Method
3.3 Evaluation on Target Localization and Optical Flow Improvement
3.4 Evaluation on Overall Integrated Approach
4 Conclusion
References
A Novel Pavement Crack Detection Approach Using Pre-selection Based on Transfer Learning
Abstract
1 Introduction
2 Proposed Method
2.1 Preprocessing
2.2 T-DCNN Pre-selection
2.3 Crack Detection
3 Experiment
3.1 Dataset and Metrics
3.2 Fine-Tuning ImageNet-Based Model
3.3 Experimental Results
4 Conclusion
References
Learning Local Instance Constraint for Multi-label Classification
Abstract
1 Introduction
2 Our Method
2.1 Basic Structure of Convolutional Neural Network
2.2 Dilated Convolutional Neural Network
2.3 Multi-task Loss
3 Experimental Results
3.1 Datasets and Baseline
3.2 Parameters Configuration
3.3 Multi-label Classification Results
4 Conclusions
References
Disparity Refinement Using Merged Super-Pixels for Stereo Matching
Abstract
1 Introduction
2 Obtaining Raw Cost Aggregation and Initial Disparities
2.1 Obtaining Cost and Disparity in Pixel Domain
2.2 Over-Segment Based on Color-Depth
2.3 Cross-Checking Test
3 Robust Super-Pixels Merging
3.1 Voting the Information of Super-Pixel
3.2 Supporting Neighbors Selection
3.3 Merging Super-Pixels to Stable Region
4 The Principle of Unreliable Region Optimization
5 Depth Hypotheses Generation
5.1 The Constraint on Smoothness of Region
5.2 Enhancement with Iteration
6 Experimental Results
7 Conclusion
References
Deep Scale Feature for Visual Tracking
1 Introduction
2 Related Work
3 Proposed Method
3.1 Deep Network Output When Tracking
3.2 Deep Feature Mask
3.3 Deep Scale Feature
3.4 Locator Construction
3.5 Tracking Algorithm
4 Experiment
4.1 Experiment Setup
4.2 Experiment Result
5 Conclusion
References
TCCF: Tracking Based on Convolutional Neural Network and Correlation Filters
1 Introduction
2 Related Work
3 Tracking Based on CNN and Correlation Filters
3.1 Feature Selection
3.2 Correlation Filters
4 Experiments
5 Conclusion
References
PPEDNet: Pyramid Pooling Encoder-Decoder Network for Real-Time Semantic Segmentation
1 Introduction
2 Related Work
3 Network Architecture
3.1 Encoder Network
3.2 Decoder Network
4 Experiments
4.1 Decoder Variant
4.2 Comparison
5 Conclusion
References
A New Kinect Approach to Judge Unhealthy Sitting Posture Based on Neck Angle and Torso Angle
Abstract
1 Introduction
2 Our New Approach for Unhealthy Sitting Posture Detection
2.1 Sitting Posture Modeling and Feature Extraction
2.2 Key Joints Acquisition and Angles Calculation
2.3 Algorithm and Implementation
3 Experiment and Results
4 Conclusions
Acknowledgments
References
Using Stacked Auto-encoder to Get Feature with Continuity and Distinguishability in Multi-object Tracking
1 Introduction
2 Conditional Random Field Model
3 Approach
3.1 Auto-encoder Structure
3.2 New Loss Function
3.3 Online Learning
4 New Feature in Network Flow
5 Experiment
5.1 Continuity and Distinguishability
5.2 Tracking Perfomance
6 Conclusion
References
Vehicle Detection Based on Superpixel and Improved HOG in Aerial Images
Abstract
1 Introduction
2 Model Based on Superpixel Segmentation and Improved HOG
2.1 Region Extraction Based on SLIC and Contour Shrinking
2.2 Feature Extraction
2.3 Computational Procedure of the Proposed Model
3 Experiments and Results
3.1 Parameter Analyze
3.2 Performance Analyze
4 Conclusions
Acknowledgment
References
Scalable Object Detection Using Deep but Lightweight CNN with Features Fusion
Abstract
1 Introduction
2 Related Work
2.1 Traditional Machine Learning
2.2 Current Deep Learning
3 The Proposed Scalable Object Detection Method
3.1 The Overall Framework
3.2 The Features Fusion Structure
3.3 Multi-scale Structure
3.4 Training Details
4 Experiments and Evaluation
4.1 Datasets
4.2 VOC2007 and VOC2012 Results
4.3 KITTI Results
5 Conclusion
Acknowledgements
References
Object Tracking with Blocked Color Histogram
Abstract
1 Introduction
2 Proposed Approach
2.1 Mean Shift with Blocked Color Histogram
2.2 Speed up with Double-Layer Structure
3 Evaluation
3.1 Model Analysis
3.2 Results of VOT2015 and VOT2016 Benchmark
4 Conclusion
Acknowledgment
References
Deep Networks for Single Image Super-Resolution with Multi-context Fusion
1 Introduction
2 Related Work
2.1 Convolutional Neural Network for Image Super-Resolution
2.2 Residue Learning
3 Proposed Method
3.1 Network Architecture
3.2 Loss Function
4 Experiments
4.1 Implementation Details
4.2 Comparisons with the State-of-the-arts
4.3 Execution Time
5 Conclusions
References
Chinese Handwriting Generation by Neural Network Based Style Transformation
1 Introduction
2 Handwriting Generation Method
2.1 Sample Points Matching
2.2 Matching Distance Between Characters
3 Style Transformation Learning
3.1 Sample Point Context Feature Extraction
3.2 Single Points Regression
3.3 Multi-point Regression
4 Experiments
4.1 Deformation Effect of Different Learning Models
4.2 Generating Characters of Different Writing Styles
5 Conclusion
References
Text Detection Based on Affine Transformation
Abstract
1 Introduction
2 Text Detection
3 External Bounding Box Estimation
3.1 Quadruple Extreme Points
3.2 Triple Extreme Points
3.3 Twin Extreme Points
4 Affine Transformation
4.1 Affine Parameter Estimation
4.2 Affine Correction
5 Experimental Results
6 Conclusion
References
Visual Servoing of Mobile Robots with Input Saturation at Kinematic Level
1 Introduction
2 System Model Development
2.1 System Modeling in 3D Space
2.2 Vision-Based System Model
3 Saturated Velocity Control Design
4 Simulation Results
5 Conclusion
References
Fabric Defect Detection Algorithm Based on Multi-channel Feature Extraction and Joint Low-Rank Decomposition
1 Introduction
2 McDerf Feature Extraction
2.1 Multi-channel Derf Feature Extraction
2.2 Feature Matrices Construction
3 Joint Low-Rank Decomposition
4 Experimental Results and Analysis
5 Conclusion
References
Robust 3D Indoor Map Building via RGB-D SLAM with Adaptive IMU Fusion on Robot
Abstract
1 Introduction
2 Related Work
3 Calibration Between Camera and IMU System
3.1 System Setup
3.2 System Calibration
4 Adaptively Combining IMU and Visual Pose to Enhance Tracking Robustness
5 Robot Movement Pattern Design
6 Experiments
7 Conclusion
Acknowledgement
References
The Research of Multi-angle Face Detection Based on Multi-feature Fusion
Abstract
1 Introduction
2 Method of Multi-angle Face Detection
2.1 Preprocessing
2.2 Feature Extraction
2.3 Classifier Building
3 Simulation Experiment and Result Analysis
3.1 Simulation Experiment
3.2 Result Analysis
4 Conclusion
References
Attention-Sharing Correlation Learning for Cross-Media Retrieval
1 Introduction
2 Related Work
2.1 Cross-Media Retrieval
2.2 Attention Mechanism
3 Attention-Sharing Correlation Learning
3.1 Local Feature Extraction
3.2 Attention-Sharing Learning
3.3 Common Representation Generation
4 Experiments
4.1 Details of the Deep Architecture
4.2 Dataset Introduction
4.3 Compared Methods and Input Settings
4.4 Evaluation Metrics
4.5 Experimental Results
5 Conclusion
References
A Method for Extracting Eye Movement and Response Characteristics to Distinguish Depressed People
1 Introduction
2 Experiment
2.1 Materials and Participants
2.2 Model
2.3 Procedure
3 Reaction Characteristics Extraction
3.1 Extraction Algorithm
3.2 Significance Test
3.3 SVM
4 Result
5 Discussion
References
Long-Distance/Environment Face Image Enhancement Method for Recognition
Abstract
1 Introduction
2 Related Work
3 Proposed G-Log Method
3.1 G-Log Analysis
3.2 Parameter Selection
4 Experimental Results and Analysis
5 Conclusion
References
A Method on Recognizing Transmission Line Structure Based on Multi-level Perception
Abstract
1 Introduction
2 Acquisition of Contour Segments of Transmission Line
3 Acquisition of Contour Segments of Transmission Line
3.1 Splitting Based on Key Points
3.2 Merging Based on Gestalt Theory
4 Perception of Significant Characteristics of Transmission Line
4.1 Perception of Parallel Structure and Symmetrical Crossing Structure
4.2 Perception of Connecting Structure and Attachment Structure
5 The Recognition of Transmission Line Structure
5.1 The Recognition of Insulator
5.2 The Recognition of Insulator
6 Experiment Result
7 Conclusions
References
Saliency Detection Based on Background and Foreground Modeling
1 Introduction
2 Saliency Detection Algorithm
2.1 Saliency Detection via Background Information
2.2 Saliency Detection via Optimal Contour Closure
2.3 Integration and Refinement Operation
3 Experiments
4 Conclusions
References
Scale Estimation and Refinement in Monocular Visual-Inertial SLAM System
Abstract
1 Introduction
2 Preliminaries
2.1 Camera Model
2.2 Inertial Sensor Model and IMU Kinematics Model
2.3 IMU Pre-integration
3 Scale Estimation and Refinement with a Weighted Item
3.1 Scale Estimation
3.2 Weighting Method for Scale Estimation Refinement
3.3 Termination Criterion
3.4 Scale Benchmark
4 Experimental Results
4.1 Scale Estimation Results
4.2 The Performance of Weighted Method for Scale Estimation Refinement
4.3 The Effect of Termination Criterion
5 Conclusions
Acknowledgment
References
Crop Disease Image Recognition Based on Transfer Learning
1 Introduction
2 Image Acquisition and Features Extraction
2.1 Image Acquisition and Equipment
2.2 Image Segmentation
2.3 Feature Extraction
3 Disease Image Recognition Based on Transfer Learning
4 Experimental Results and Discussion
4.1 Data Sets Description
4.2 Experimental Results and Analysis
5 Conclusions
References
Multi-orientation Scene Text Detection Leveraging Background Suppression
1 Introduction
2 Related Work
3 Proposed Method
3.1 Global Background Suppression
3.2 Local Background Suppression
3.3 Text Lines Formation
4 Experiments and Discussions
4.1 Datasets
4.2 Experimental Results and Discussions
5 Conclusions
References
Sparse Time-Varying Graphs for Slide Transition Detection in Lecture Videos
1 Introduction
2 Related Work
3 Problem Settings
4 Sparse Time-Varying Graphs
4.1 Graph Modeling
4.2 Global Optimization
5 Results and Discussion
6 Conclusion
References
Heterogeneous Multi-group Adaptation for Event Recognition in Consumer Videos
1 Introduction
2 Related Work
3 Event Recognition Based on Heterogeneous Multi-group Adaptation
3.1 Transfer Model
3.2 Detailed Solution
3.3 Optimization Algorithm
4 Experiment
4.1 Datasets and Features
4.2 Experimental Setup
4.3 Results
5 Conclusion and Future Work
References
Margin-Aware Binarized Weight Networks for Image Classification
1 Introduction
2 Binarized Weight Networks
3 Experiments
3.1 MNIST
3.2 CIFAR-10
3.3 Compression Rates
4 Conclusion
References
Multi-template Matching Algorithm Based on Adaptive Fusion
Abstract
1 Introduction
2 Proposed Method
2.1 Template Matching Based on Multiple References
2.2 Adaptive Analytic Hierarchy Process Based on Entropy Weight Method
2.3 Fusion Method Based on Overlap Region and Local Search
3 Simulation Experiments and Results Analysis
3.1 Complicated Background Interference
3.2 Different Scale and Sight Interference
4 Conclusions
References
Combining Object-Based Attention and Attributes for Image Captioning
1 Introduction
2 Related Work
3 Model Description
3.1 Problem Formulation
3.2 Object Attention Layer
3.3 LSTM Structures
3.4 Probability Output Layer
4 Experiments
4.1 Dataset
4.2 Experimental Settings
4.3 Performance Comparison
4.4 Case Study and Visualization
5 Conclusion
References
Intrinsic Image Decomposition: A Comprehensive Review
1 Introduction
2 Intrinsic Image Dataset
2.1 MIT Intrinsic Image Dataset
2.2 Intrinsic Image in the Wild (IIW) Dataset
2.3 MPI Sintel Dataset
3 Existing Algorithm
3.1 Image Sequence and Multiple Views
3.2 Priors and Constraints Based on Reflectance
3.3 Priors and Constraints Based on Shape and Illumination
4 Experiments and Result
4.1 Experiments on MIT Dataset
4.2 Experiments on IIW Dataset
5 Conclusions
References
Multi-instance Multi-label Learning for Image Categorization Based on Integrated Contextual Information
Abstract
1 Introduction
2 Construction of Contextual Information
2.1 MIMLL Formulation
2.2 Latent Probability Distribution of Instances
2.3 Spatial Context Among Adjacent Instances
2.4 Correlations Between Instances and Labels
3 Multi-instance Conditional Random Fields Algorithm
3.1 Algorithm Framework
3.2 Formulation of Mi-CRFs
4 Experiments and Analysis
5 Conclusion
References
Book Page Identification Using Convolutional Neural Networks Trained by Task-Unrelated Dataset
Abstract
1 Introduction
2 The Proposed Method
2.1 Book Page Segmentation
2.2 Image Correction
2.3 Feature Extraction
2.4 Feature Compression
2.5 Feature Matching
3 Experiments
3.1 Overall Performance
3.2 Effectiveness of the Proposed Pipeline
3.3 Performance of Different Feature Code Compression
3.4 Computation Time
4 Conclusions
Acknowledgements
References
No Reference Assessment of Image Visibility for Dehazing
1 Introduction
2 The Proposed Approach
2.1 Multi-scale Contrast Feature
2.2 Dark Channel Feature
2.3 The Proposed Visibility Indicator
3 Experiments and Analysis
4 Conclusion
References
Multi-focus Image Fusion Using Dictionary Learning and Low-Rank Representation
1 Introduction
2 Related Work
3 The Proposed Image Fusion Method
3.1 Dictionary Learning
3.2 Proposed Fusion Method
3.3 Summary of the Proposed Fusion Method
4 Experiment
4.1 Experimental Settings
4.2 Image Fusion Results
5 Conclusions
References
Key-Region Representation Learning for Anomaly Detection
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Key-Region Selection Module
3.2 Representation Learning Module
3.3 Normal/Abnormal Classifier
4 Experiment Validation
4.1 Parameter Setting
4.2 Experiment Result
5 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Image and Graphics

Description

More details

Other editions

Additional editions

Content

System requirements