Computer Vision Metrics

Survey, Taxonomy, and Analysis

By Scott Krig

Computer Vision Metrics Cover Image

Computer Vision
Metrics
provides an extensive survey and analysis of current and historical
feature description and machine vision methods, with a detailed taxonomy for
local, regional and global features. The survey is broader than it is deep,
with over 540 references provided to dig deeper. The taxonomy includes search
methods, spectra components, descriptor representation, shape, distance
functions, accuracy, efficiency, robustness and invariance attributes, and more.
This book provides necessary background to develop intuition about why interest
point detectors and feature descriptors actually work, how they are designed,
and observations about tuning the methods for achieving robustness and invariance
targets for specific applications. This is not another ‘how-to’ book with
source code examples and shortcuts, but rather provides a counterpoint to the
many fine opencv community source code resources currently available for
hands-on practitioners.


Full Description

  • ISBN13: 978-1-4302-5929-9
  • 508 Pages
  • User Level: Beginner to Advanced
  • Publication Date: June 1, 2014
  • Available eBook Formats: EPUB, MOBI, PDF
  • Print Book Price: $39.99
  • eBook Price: $0.00
Buy eBook Buy Print Book Add to Wishlist

Related Titles

Full Description

Computer Vision Metrics provides an extensive survey and analysis of current and historical feature description and machine vision methods, with a detailed taxonomy for local, regional and global features. The survey is broader than it is deep, with over 540 references provided to dig deeper. The taxonomy includes search methods, spectra components, descriptor representation, shape, distance functions, accuracy, efficiency, robustness and invariance attributes, and more. This book provides necessary background to develop intuition about why interest point detectors and feature descriptors actually work, how they are designed, and observations about tuning the methods for achieving robustness and invariance targets for specific applications. This is not another ‘how-to’ book with source code examples and shortcuts, but rather provides a counterpoint to the many fine opencv community source code resources currently available for hands-on practitioners.


What you’ll learn

Here is a sampling of topics covered:

  • Interest point & descriptor concepts (interest points, corners, ridges, blobs, contours, edges, maxima), interest point tuning and culling, interest point methods (Laplacian, LOG, Moravic, Harris, Harris-Stephens, Shi-Tomasi, Hessian, Difference of Gaussians, Salient Regions, MSER, SUSAN, FAST, FASTER, AGHAST, Local Curvature, Morphological Regions, more), descriptor concepts (shape, sampling pattern, spectra, gradients, binary patterns, basis features).
  • Local binary descriptors (LBP, LBP-TOP, LTP, FREAK, ORB, BRISK, BRIEF, CENSUS, more).
  • Gradient descriptors (SIFT, SIFT-PAC, SIFT-SIFER, SIFT-GLOH, Root SIFT, CensureE,, STAR, HOG, PHOG, DAISY, O-DAISY, CARD, RFM, RIFF-CHOG, LGP, more).
  • Shape descriptors (Image Moments, area, perimeter, centroid, D-NETS, Chain Codes, Fourier, Wavelets, more) texture descriptors, structural and statistical (Harallick, SDM, extended SDM, edge metrics, Laws Metrics, LBP, more).
  • 3D descriptors (3D HOG, HON 4D, 3D SIFT, more).
  • Basis space descriptors (Zernike Moments, several other transforms, Steerable Filter Basis Sets, Fourier Descriptors, Sparse Coding, Codebooks, Descriptor Vocabularies, more), HAAR methods (SURF, USURF, MUSURF, GSURF, Viola Jones, more), descriptor-based image reconstruction.
  • Image formation, includes CCD and CMOS sensors for 2D and 3D imaging, along with sensor processing topics, with a survey identifying over fourteen (14) 3D depth sensing methods, with emphasis on stereo, MVS, and structured light.
  • Image-processing methods targeted at specific feature descriptor methods (point, line and area methods, basis space methods), colorimetry (CIE, HSV, RGB, CAM02, gamut mapping, more).
  • Distance functions (Euclidean, Cartesian, SAD, SSD, Correlation, Hellinger, Manhattan, Chebyshev, EMD, Wasserstein, Mahalanobis, Bray-Curtis, Canberra, L0, Hamming, Jaccard), coordinate spaces, robustness and invariance criteria, light introduction to machine learning, classification and training (SVM,’s kernel machines, KNN, convolutional networks, neural networks, more).
  • Ground truth data, real and synthetic datasets, survey of datasets.
  • Vision pipeline optimizations, types of compute resources (CPU, GPU, DSP, more), hypothetical optimized vision pipeline examples (face recognition, object recognition, image classification, augmented reality), optimization alternatives for effective use of SIMD, VLIW, kernels, threads, parallel languages, memory, more.
  • Synthetic interest point alphabet analysis against 10 common OpenCV detectors to develop intuition about how different classes of detectors actually work (SIFT, SURF, BRISK, FAST, HARRIS, GFFT, MSER, ORB, STAR, SIMPLEBLOB). Source code provided online.

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

Table of Contents

Chapter 1. Image Capture and Representation

Chapter 2. Image Pre-Processing

Chapter 3. Global and Regional Features

Chapter 4. Local Feature Design Concepts, Classification, and Learning

Chapter 5. Taxonomy Of Feature Description Attributes

Chapter 6. Interest Point Detector and Feature Descriptor Survey

Chapter 7. Ground Truth Data, Data, Metrics, and Analysis

Chapter 8. Vision Pipelines and Optimizations

Appendix A. Synthetic Feature Analysis

Appendix B. Survey of Ground Truth Datasets

Appendix C. Imaging and Computer Vision Resources

Appendix D. Extended SDM Metrics


Source Code/Downloads

Downloads are available to accompany this book.

Your operating system can likely extract zipped downloads automatically, but you may require software such as WinZip for PC, or StuffIt on a Mac.

Errata

Please Login to submit errata.

No errata are currently published