You are previewing Graph-Based Methods in Computer Vision.
O'Reilly logo
Graph-Based Methods in Computer Vision

Book Description

Computer vision, the science and technology of machines that see, has been a rapidly developing research area since the mid-1970s. It focuses on the understanding of digital input images in many forms, including video and 3-D range data. Graph-Based Methods in Computer Vision: Developments and Applications presents a sampling of the research issues related to applying graph-based methods in computer vision. These methods have been under-utilized in the past, but use must now be increased because of their ability to naturally and effectively represent image models and data. This publication explores current activity and future applications of this fascinating and ground-breaking topic.

Table of Contents

  1. Cover
  2. Title Page
  3. Copyright Page
  4. Editorial Advisory Board and List of Reviewers
    1. Editorial Advisory Board
  5. Preface
  6. Acknowledgment
  7. Section 1: Graph-Based Methods for Image Matching
    1. Chapter 1: Graph Matching Techniques for Computer Vision
      1. ABSTRACT
      2. INTRODUCTION
      3. GRAPH MATCHING ALGORITHMS
      4. COMPUTER VISION APPLICATIONS USING GRAPH MATCHING
      5. CONCLUSION
      6. REFERENCES
    2. Chapter 2: Geometric-Edge Random Graph Model for Image Representation
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. GEOMETRIC-EDGE (GE) RANDOM GRAPH MODEL
      5. MODELING IMAGE USING G-E RANDOM GRAPH
      6. G-E RANDOM GRAPH MATCHING BASED ON RANDOM DOT PRODUCT GRAPH
      7. EXPERIMENT
      8. CONCLUSION
      9. ACKNOWLEDGEMENT
      10. REFERENCES
    3. Chapter 3: The Node-to-Node Graph Matching Algorithm Schema
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. MAIN FOCUS OF THE CHAPTER
      5. LIMITATIONS
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
      8. REFERENCES
  8. Section 2: Graph-Based Methods for Image Segmentation
    1. Chapter 4: Unsupervised and Supervised Image Segmentation Using Graph Partitioning
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. IMAGE INTO GRAPH CONVERSION
      4. 3. UNSUPERVISED IMAGE SEGMENTATION USING GRAPH PARTITIONING
      5. 4. SUPERVISED IMAGE SEGMENTATION BASED ON GRAPH PARTITIONING
      6. 5. CONCLUSION
      7. REFERENCES
      8. ENDNOTES
    2. Chapter 5: Motion Segmentation and Matting by Graph Cut
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. GRAPH CUTS NOTATION
      5. EXTRACTING THE LAYER DESCRIPTIONS
      6. MULTI-FRAME LAYER SEGMENTATION
      7. VIDEO MATTING AND SEGMENTATION REFINEMENT
      8. EXPERIMENTS
      9. FUTURE RESEARCH DIRECTIONS
      10. CONCLUSION
      11. REFERENCES
      12. ADDITIONAL READING
    3. Chapter 6: Hypergraph Based Visual Segmentation and Retrieval
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. BACKGROUND
      4. 3. UNSUPERVISED AND SEMI-SUPERVISED LEARNING WITH HYPERGRAPHS
      5. 4. HYPERGRAPH BASED VIDEO OBJECT SEGMENTATION
      6. 5. CONCLUSION
      7. REFERENCES
    4. Chapter 7: Recent Advances on Graph-Based Image Segmentation Techniques
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. SUPERVISED IMAGE SEGMENTATION METHODS
      5. UNSUPERVISED IMAGE SEGMENTATION METHODS
      6. OTHER CONCERNS AND FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
      8. REFERENCES
  9. Section 3: Graph-Based Methods for Image and Video Analysis
    1. Chapter 8: Graph Embedding Using Dissimilarities with Applications in Classification
      1. ABSTRACT
      2. INTRODUCTION
      3. RECENT DEVELOPMENTS IN GRAPH BASED PATTERN RECOGNITION
      4. EXPERIMENTAL EVALUATION
      5. REFERENCE SYSTEMS AND EXPERIMENTAL SETUP
      6. RESULTS AND DISCUSSION
      7. CONCLUSION
      8. REFERENCES
    2. Chapter 9: Generative Group Activity Analysis with Quaternion Descriptor
      1. ABSTRACT
      2. INTRODUCTION
      3. OVERVIEW OF THE PROPOSED FRAMEWORK
      4. QUATERNION DESCRIPTOR FOR ACTIVITY REPRESENTATION
      5. GENERATIVE ACTIVITY ANALYSIS
      6. EXPERIMENTS
      7. CONCLUSION
      8. REFERENCES
    3. Chapter 10: Shape Retrieval and Classification Based on Geodesic Paths in Skeleton Graphs
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. BACKGROUND
      4. 3. SKELETON GRAPHS
      5. 4. MATCHING THE SKELETON-GRAPHS
      6. 5. MATCHING EXPERIMENTS
      7. 6. IMPLEMENTATION AND COMPUTATIONAL COMPLEXITY
      8. 7. BAYESIAN CLASSIFICATION
      9. 8. CLASSIFICATION EXPERIMENTS
      10. 9. CONCLUSION
      11. REFERENCES
    4. Chapter 11: Discriminative Feature Selection in Image Classification and Retrieval
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. DISCRIMINATIVE FEATURES SELECTION
      5. PERFORMANCE EVALUATION
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
      8. REFERENCES
    5. Chapter 12: Normalized Projection and Graph Embedding via Angular Decomposition
      1. ABSTRACT
      2. INTRODUCTION
      3. ANGULAR DECOMPOSITION
      4. ALGORITHMS AND ANALYSIS
      5. EXPERIMENTS
      6. CONCLUSION AND FUTURE WORKS
      7. ACKNOWLEDGMENT
      8. REFERENCES
    6. Chapter 13: Region-Based Graph Learning towards Large Scale Image Annotation
      1. ABSTRACT
      2. INTRODUCTION
      3. REGION-AWARE AND SCALABLE MULTI-LABEL PROPAGATION FRAMEWORK
      4. EXPERIMENTS
      5. CONCLUSION
      6. REFERENCES
    7. Chapter 14: Copy Detection Using Graphical Model
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. OVERALL FRAMEWORK
      5. FORMULATION OF FRAME FUSION
      6. FRAME FUSION USING VITERBI-LIKE ALGORITHM
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. REFERENCES
  10. Section 4: Graph-Based Methods for Image Processing
    1. Chapter 15: Multi-Scale Exemplary Based Image Super-Resolution with Graph Generalization
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. RESOLUTION-INVARIANT IMAGE REPRESENTATION
      5. APPROXIMATE AND GENERALIZATION USING MULTI-TASK LEARNING
      6. MULTI-TASK LEARNING FOR MULTI-SCALE IMAGE RESIZING
      7. EXPERIMENTAL RESULTS
      8. CONCLUSION
      9. REFERENCES
      10. APPENDIX 1: RESOLUTION INVARIANCY IN NN MODEL
      11. APPENDIX 2: RESOLUTION INVARIANCY IN LLE MODEL
    2. Chapter 16: Graph Heat Kernel Based Image Smoothing
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. PRIOR WORK
      4. 3. A GRAPH SPECTRAL APPROACH TO ANISOTROPIC DIFFUSION
      5. 4. ANALYSIS OF THE ALGORITHM
      6. 5. EXPERIMENTS
      7. 6. CONCLUSION
      8. REFERENCES
  11. Compilation of References
  12. About the Contributors