Further processing options

Pattern Recognition: 7th Chinese Conference, CCPR 2016, Chengdu, China, November 5-7, 2016, Proceedings, Part II.

Bibliographic Details
Authors and Corporations: Tan, Tieniu., Li, Xuelong., Chen, Xilin., Zhou, Jie., Yang, Jian., Cheng, Hong.
Other Authors: Li, Xuelong. , Chen, Xilin. , Zhou, Jie. , Yang, Jian. , Cheng, Hong.
Type of Resource: E-Book
Language: English
published:
Singapore : Springer Singapore Pte. Limited, 2016.
©2016.
Series: Communications in Computer and Information Science Ser.
Subjects:
Source: Ebook Central
ISBN: 9789811030055
Table of Contents:
  • Intro
  • Preface
  • Organization
  • Contents
  • Part II
  • Contents
  • Part I
  • Image and Video Processing
  • Saliency Region Detection via Graph Model and Statistical Learning
  • 1 Introduction
  • 2 Algorithm
  • 2.1 Initial Saliency Map Generation
  • 2.2 Foreground Enhancement via Absorbing Markov Chain
  • 2.3 Saliency Map Construction by Bayes Estimation
  • 3 Experiments and Results
  • 3.1 Datasets and Metrics
  • 3.2 Experiment and Results
  • 4 Conclusion
  • References
  • An Efficient Gabor Feature-Based Multi-task Joint Support Vector Machines Framework for Hyperspectral Image Classification
  • 1 Introduction
  • 2 Related Work
  • 2.1 Gabor Functions and Wavelets
  • 2.2 Classical Support Vector Classification (C-SVC)
  • 3 Gabor Feature-Based Multi-task Joint Support Vector Machines for Hyperspectral Classification
  • 3.1 Gabor Features Extraction for Hyperspectral Image
  • 3.2 Combine Probabilistic Outputs of SVM for Gabor Features
  • 4 Experimental Results
  • 4.1 Indian Pines Data Set
  • 4.2 KSC Data Set
  • 5 Conclusion
  • References
  • Single Image Haze Removal Based on Priori Image Geometry and Edge-Preserving Filtering
  • Abstract
  • 1 Introduction
  • 2 Background
  • 2.1 Atmospheric Scatting Model
  • 2.2 Priori Image Geometry and Edge-Preserving Filtering
  • 3 The Proposed Algorithm
  • 3.1 The Algorithm Flowchart
  • 3.2 Atmospheric Light Estimation
  • 3.3 Initial Transmission Map Estimation
  • 3.4 Refined Transmission Map Estimation
  • 3.5 Scene Radiance Recovery
  • 4 Experimental Results
  • 4.1 Qualitative Comparison
  • 4.2 Quantitative Evaluation
  • 5 Conclusion and Future Work
  • Acknowledgements
  • References
  • Semantic Segmentation with Modified Deep Residual Networks
  • 1 Introduction
  • 2 Our Method
  • 2.1 Network Architecture
  • 2.2 SAR-Based Data Augmentation Method
  • 2.3 Online Hard Pixels Mining
  • 3 Experiments
  • 3.1 Dataset.
  • 3.2 Implementation Details
  • 3.3 Dilated Convolution
  • 3.4 LSTM and Multi-scale Prediction
  • 3.5 SAR-Based Data Augmentation Method
  • 3.6 Online Hard Pixels Mining
  • 3.7 Results of PASCAL VOC 2012 Dataset
  • 4 Conclusions
  • References
  • A Quantum-Inspired Fuzzy Clustering for Solid Oxide Fuel Cell Anode Optical Microscope Images Segmentation
  • Abstract
  • 1 Introduction
  • 2 Proposed Approach
  • 3 Experimental Results
  • 3.1 Experiments on Synthetic Images
  • 3.2 Results on SOFC Porous Electrodes Images
  • 4 Conclusions
  • Acknowledgments
  • References
  • Document Image Super-Resolution Reconstruction Based on Clustering Learning and Kernel Regression
  • 1 Introduction
  • 2 Super-Resolution Reconstruction Model
  • 3 Super-Resolution Reconstruction Implementation
  • 3.1 Training
  • 3.2 Super-Resolution Reconstruction
  • 4 Experiment Result and Analysis
  • 4.1 Reconstruction Experiment for Simulated Text Image
  • 4.2 Reconstruction Experiment for Actual Text Image
  • 5 Conclusion
  • References
  • Image Fusion and Super-Resolution with Convolutional Neural Network
  • Abstract
  • 1 Introduction
  • 2 The Basic Algorithm
  • 3 Wavelet Coefficients SR with Trained CNN
  • 4 Experiment and Analysis
  • 4.1 Multi-focus Image Fusion
  • 4.2 Medical and VL and NIR Image Fusion
  • 5 Conclusions
  • Acknowledgments
  • References
  • Robust Segmentation for Video Captions with Complex Backgrounds
  • Abstract
  • 1 Introduction
  • 2 Related Work
  • 3 Proposed Method
  • 3.1 Text Tracking
  • 3.2 Single-Frame Text Segmentation
  • 3.3 Multi-frame Integration
  • 4 Experimental Results
  • 4.1 Text Tracking
  • 4.2 Single-Frame Text Segmentation
  • 4.3 Multi-frame Integration
  • 5 Conclusion
  • References
  • Single Low-Light Image Enhancement Using Luminance Map
  • 1 Introduction
  • 2 The Proposed Algorithm
  • 2.1 Computing the Luminance Map.
  • 2.2 Estimating the Global Atmospheric Light
  • 2.3 Estimating the Transmittance
  • 2.4 Recovering the Inverted Scene Radiance
  • 3 Experiment Results
  • 3.1 Subjective Quality Comparison
  • 3.2 Objective Quality Comparison
  • 3.3 Running Speed Comparison
  • 4 Conclusion
  • References
  • Image Copy Detection Based on Convolutional Neural Networks
  • 1 Introduction
  • 2 Related Work
  • 2.1 Traditional Image Copy Detection
  • 2.2 Research Progress of CNN
  • 3 The Proposed Method
  • 3.1 Overview
  • 3.2 Network Architectures
  • 4 Learning
  • 5 Experiments
  • 5.1 Dataset
  • 5.2 Result
  • 6 Conclusions
  • References
  • Perceptual Loss with Fully Convolutional for Image Residual Denoising
  • 1 Introduction
  • 2 Related Work
  • 3 Method
  • 3.1 Encoder-Decoder Architectures
  • 3.2 Per-pixel Loss Functions
  • 3.3 Perceptual Loss Functions
  • 4 Experiments and Results
  • 4.1 Analysis on Model Details
  • 5 Conclusion and Outlook
  • References
  • Single Image Super Resolution Through Multi Extreme Learning Machine Regressor Fusion
  • 1 Introduction
  • 2 Related Work
  • 2.1 Single Image Super Resolution Using Gradient Profile Prior
  • 2.2 Extreme Learning Machine Regression
  • 3 Proposed Super Resolution Method
  • 3.1 Overview of Proposed Method
  • 3.2 Estimation of HR Gradient and High Frequency
  • 4 Experiments
  • 4.1 Settings
  • 4.2 Results
  • 4.3 Complexity
  • 5 Conclusion
  • References
  • Learning-Based Weighted Total Variation for Structure Preserving Texture Removal
  • 1 Introduction
  • 2 Related Work
  • 3 Model and Algorithm
  • 3.1 Learning-Based TV Model for Structure Extraction
  • 3.2 Model Computation
  • 3.3 Structural Contour Learning
  • 4 Experiment
  • 4.1 Parameter Setting
  • 4.2 Structure Extraction Comparison
  • 5 Conclusion
  • References
  • A Novel Texture Extraction Method for the Sedimentary Structures' Classification of Petroleum Imaging Logging.
  • Abstract
  • 1 Introduction
  • 2 Methods
  • 2.1 Local Binary Pattern Based Directional Texture Feature Model
  • 3 Experimental Results and Analysis
  • 3.1 Experimental Evaluation Scale
  • 3.2 Experimental Data Description
  • 4 Conclusion and Future Work
  • Acknowledgments
  • References
  • Rank Beauty
  • Abstract
  • 1 Introduction
  • 2 Rank Beauty
  • 2.1 Data and Crowdsourcing
  • 2.2 Learning to Rank
  • 3 Results
  • 3.1 Measuring Accuracy
  • 3.2 Facial Beauty Ranking
  • 4 Conclusion
  • Acknowledgments
  • References
  • Robust Optic Disc Detection Based on Multi-features and Two-Stage Decision Strategy
  • Abstract
  • 1 Introduction
  • 2 Method
  • 2.1 Finding Optic Disc Candidates
  • 2.2 Distinguish Really OD Region Based on HOG Feature
  • 3 Experiment Results
  • 3.1 Dataset
  • 3.2 The Robustness of the Proposed Methods
  • 4 Conclusion
  • References
  • Hierarchical Saliency Detection Under Foggy Weather Fusing Spectral Residual and Phase Spectrum
  • Abstract
  • 1 Introduction
  • 2 Transmission Estimation
  • 2.1 Atmospheric Imaging Model
  • 2.2 Transmission Estimation
  • 3 Hierarchical Saliency Detection
  • 3.1 Preliminary Spectral Residual Detection
  • 3.2 Detailed Phase Spectrum Detection
  • 3.3 Weighted Fusing and Region Localization
  • 4 Experiment
  • 5 Conclusion
  • References
  • Hierarchical Image Matching Method Based on Free-Form Linear Features
  • Abstract
  • 1 Introduction
  • 2 Research Methods
  • 2.1 Extraction of Free-Form Sub-pixel Linear Features
  • 2.2 Extraction of the Features for Matching
  • 2.3 Coarse Matching by Using Multiple Linear Features
  • 2.4 Accurate Matching Based on Multi-level Two-Dimensional ICP
  • 3 Experimental Results and Analysis
  • 4 Conclusions
  • References
  • Improved Saliency Optimization Based on Superpixel-Wised Objectness and Boundary Connectivity
  • 1 Introduction
  • 2 Backgrounds
  • 2.1 Objectness.
  • 2.2 Boundary Connectivity
  • 3 Saliency Measurement Based on Modified Objectness and Boundary Connectivity
  • 4 Improved Saliency Optimization
  • 5 Experiments
  • 5.1 Qualitative Evaluation
  • 5.2 Quantitative Evaluation
  • 5.3 Model Analysis
  • 5.4 Run Time
  • 6 Conclusion
  • References
  • A Dual-Based Adaptive Gradient Method for TV Image Denoising
  • 1 Introduction
  • 2 Dual Formulation
  • 3 Motivation and Adaptive Gradient Method
  • 3.1 Motivation
  • 3.2 Global Convergence
  • 4 Numerical Experiments
  • 5 Conclusion
  • References
  • Image Inpainting Based on Sparse Representation with Dictionary Pre-clustering
  • 1 Introduction
  • 2 Sparse Representation
  • 3 Inpainting Algorithm
  • 3.1 The Creation of Dictionary
  • 3.2 The Sparse Reconstruction of Image Patches
  • 3.3 Inpainting Order
  • 4 Experimental Results and Comparisons
  • 5 Conclusion
  • References
  • Efficient Image Retrieval via Feature Fusion and Adaptive Weighting
  • 1 Introduction
  • 2 Related Work
  • 3 Feature Fusion for Image Retrieval
  • 3.1 Overview of Image Features
  • 3.2 Feature Extraction and Processing
  • 3.3 Multiple Features Fusion and Complementation
  • 4 Adaptive Weights Allocation Algorithm
  • 5 Experiments
  • 5.1 Datasets and Evaluation
  • 5.2 Experimental Parameters Settings
  • 5.3 Experimental Results Analysis
  • 6 Summary and Outlook
  • References
  • The Effect of Quantization Setting for Image Denoising Methods: An Empirical Study
  • 1 Introduction
  • 2 Motivation
  • 3 Image Denoising Framework
  • 4 Experimental Results
  • 5 Conclusion
  • References
  • GPCA-SIFT: A New Local Feature Descriptor for Scene Image Classification
  • 1 Introduction
  • 2 PCA-SIFT
  • 3 GPCA-SIFT
  • 3.1 GPCA
  • 3.2 GPCA-SIFT
  • 4 Experiments
  • 4.1 Dataset Used
  • 4.2 Discussion
  • 4.3 Evaluation of GPCA-SIFT
  • 5 Conclusion
  • References
  • Speech and Language.
  • Low-Quality Character Recognition Based on Dictionary Learning and Sparse Representation.