Computer Vision Metrics: Survey, Taxonomy, and Analysis

Computer Vision Metrics: Survey, Taxonomy, and Analysis

by Scott Krig
Released June 2014
Publisher(s): Apress
ISBN: 9781430259299

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Computer Vision Metrics: Survey, Taxonomy, and Analysis provides a technical tour through computer vision, with a survey of nearly 100 types of local, regional, and global feature descriptors, blending history of the field with state-of-the-art analysis of contemporary methods, rather than just another how-to book with source code shortcuts and performance analysis. Observations are provided to develop intuition behind the methods and mathematics, interesting questions are raised for future research rather than providing all the answers, and a Vision Taxonomy is suggested to draw a conceptual map of the field. Extensive illustrations are included, with over 540 references to the literature in the comprehensive bibliography to dig deeper.

Computer Vision Metrics explores the key questions behind the design and mathematics of computer vision metrics and feature descriptors, providing a comprehensive survey and taxonomy of what methods are used, with analysis and observations about why the methods work. Several 3D depth sensing methods are surveyed including MVS, stereo, and structured light.

This work focuses on a slice through the field from the view of feature description metrics, or how to describe, compute, and design the macro-features and micro-features that make up larger objects in images. The focus is on the pixel-side of the vision pipeline, with a light introduction to the back-end training, classification, machine learning, and matching stages.

Computer Vision Metrics is written for engineers, scientists, and academic researchers in areas including video analytics, scene understanding, machine vision, face recognition, gesture recognition, pattern recognition, general object analysis, media processing, and computational photography.

What you'll learn

  • Current status, brief history, and future directions for computer vision metrics

  • Taxonomy of local binary, gradient & other spectra, shape features, and basis spaces

  • Overview of 2D image sensing, 3D depth sensing, and image preprocessing

  • Vision pipeline optimization methods for computer vision applications

  • Characterization of ten OpenCV detectors using synthetic feature alphabets

    • Who this book is for

    Engineers, scientists, and academic researchers in areas including media processing, computational photography, video analytics, scene understanding, machine vision, face recognition, gesture recognition, pattern recognition and general object analysis.

    Table of contents

    1. Title Page
    2. About ApressOpen
    3. Dedication
    4. Contents at a Glance
    5. Contents
    6. About the Author
    7. Acknowledgments
    8. Introduction
    9. CHAPTER 1: Image Capture and Representation
      1. Image Sensor Technology
      2. Cameras and Computational Imaging
      3. 3D Depth Processing
      4. 3D Representations: Voxels, Depth Maps, Meshes, and Point Clouds
      5. Summary
    10. CHAPTER 2: Image Pre-Processing
      1. Perspectives on Image Processing
      2. Problems to Solve During Image Pre-Processing
      3. The Taxonomy of Image Processing Methods
      4. Colorimetry
      5. Spatial Filtering
      6. Edge Detectors
      7. Transform Filtering, Fourier, and Others
      8. Morphology and Segmentation
      9. Thresholding
      10. Summary
    11. CHAPTER 3: Global and Regional Features
      1. Historical Survey of Features
      2. Texture Region Metrics
      3. Statistical Region Metrics
      4. Basis Space Metrics
      5. Summary
    12. CHAPTER 4: Local Feature Design Concepts, Classification, and Learning
      1. Local Features
      2. Local Feature Attributes
      3. Distance Functions
      4. Descriptor Representation
      5. Descriptor Density
      6. Descriptor Shape Topologies
      7. Local Binary Descriptor Point-Pair Patterns
      8. Descriptor Discrimination
      9. Search Strategies and Optimizations
      10. Computer Vision, Models, Organization
      11. Summary
    13. CHAPTER 5: Taxonomy of Feature Description Attributes
      1. General Robustness Taxonomy
      2. General Vision Metrics Taxonomy
      3. Feature Metric Evaluation
      4. Summary
    14. CHAPTER 6: Interest Point Detector and Feature Descriptor Survey
      1. Interest Point Tuning
      2. Interest Point Concepts
      3. Interest Point Method Survey
      4. Feature Descriptor Survey
      5. Spectra Descriptors
      6. Basis Space Descriptors
      7. Polygon Shape Descriptors
      8. 3D, 4D, Volumetric, and Multimodal Descriptors
      9. Summary
    15. CHAPTER 7: Ground Truth Data, Content, Metrics, and Analysis
      1. What Is Ground Truth Data?
      2. Previous Work on Ground Truth Data: Art vs. Science
      3. Key Questions For Constructing Ground Truth Data
      4. Defining the Goals and Expectations
      5. Robustness Criteria for Ground Truth Data
      6. Pairing Metrics with Ground Truth
      7. Synthetic Feature Alphabets
      8. Summary
    16. CHAPTER 8: Vision Pipelines and Optimizations
      1. Stages, Operations, and Resources
      2. Compute Resource Budgets
      3. The Vision Pipeline Examples
      4. Acceleration Alternatives
      5. Vision Algorithm Optimizations and Tuning
      6. Optimization Resources
      7. Summary
    17. APPENDIX A: Synthetic Feature Analysis
      1. Background Goals and Expectations
      2. Test Methodology and Results
      3. Summary of Synthetic Alphabet Ground Truth Images
      4. Test 1: Synthetic Interest Point Alphabet Detection
      5. Test 2: Synthetic Corner Point Alphabet Detection
      6. Test 3: Synthetic Alphabets Overlaid on Real Images
      7. Test 4: Rotational Invariance for Each Alphabet
      8. Analysis of Results and Non-Repeatability Anomalies
    18. APPENDIX B: Survey of Ground Truth Datasets
    19. APPENDIX C: Imaging and Computer Vision Resources
      1. Commercial Products
      2. Open Source
      3. Organizations, Institutions, and Standards
      4. Journals and Their Abbreviations
      5. Conferences and Their Abbreviations
      6. Online Resources
    20. APPENDIX D: Extended SDM Metrics
    21. Bibliography
    22. Index

    Product information

    • Title: Computer Vision Metrics: Survey, Taxonomy, and Analysis
    • Author(s): Scott Krig
    • Release date: June 2014
    • Publisher(s): Apress
    • ISBN: 9781430259299