معیارهای بینایی کامپیوتری: مرور، طبقه‌بندی و تحلیل

Computer Vision Metrics provides an extensive survey and analysis of over 100 current and historical feature description and machine vision methods, with a detailed taxonomy for local, regional and global features. This book provides necessary background to develop intuition about why interest point detectors and feature descriptors actually work, how they are designed, with observations about tuning the methods for achieving robustness and invariance targets for specific applications. 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. Rather than providing ‘how-to’ source code examples and shortcuts, this book provides a counterpoint discussion to the many fine opencv community source code resources available for hands-on practitioners. What you’ll learn 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, and more), descriptor concepts (shape, sampling pattern, spectra, gradients, binary patterns, basis features), feature descriptor families. Local binary descriptors (LBP, LTP, FREAK, ORB, BRISK, BRIEF, CENSUS, and more). Gradient descriptors (SIFT, SIFT-PCA, SIFT-SIFER, SIFT-GLOH, Root SIFT, CensureE, STAR, HOG, PHOG, DAISY, O-DAISY, CARD, RFM, RIFF-CHOG, LGP, and more). Shape descriptors (Image moments, area, perimeter, centroid, D-NETS, chain codes, Fourier descriptors, wavelets, and more) texture descriptors, structural and statistical (Harallick, SDM, extended SDM, edge metrics, Laws metrics, RILBP, and more). 3D descriptors for depth-based, volumetric, and activity recognition spatio-temporal data sets (3D HOG, HON 4D, 3D SIFT, LBP-TOP, VLBP, and more). Basis space descriptors (Zernike moments, KL, SLANT, steerable filter basis sets, sparse coding, codebooks, descriptor vocabularies, and more), HAAR methods (SURF, USURF, MUSURF, GSURF, Viola Jones, and more), descriptor-based image reconstruction. Distance functions (Euclidean, SAD, SSD, correlation, Hellinger, Manhattan, Chebyshev, EMD, Wasserstein, Mahalanobis, Bray-Curtis, Canberra, L0, Hamming, Jaccard), coordinate spaces, robustness and invariance criteria. Image formation, includes CCD and CMOS sensors for 2D and 3D imaging, sensor processing topics, with a survey identifying over fourteen (14) 3D depth sensing methods, with emphasis on stereo, MVS, and structured light. Image pre-processing methods, examples are provided targeting specific feature descriptor families (point, line and area methods, basis space methods), colorimetry (CIE, HSV, RGB, CAM02, gamut mapping, and more). Ground truth data, some best-practices and examples are provided, with a survey of real and synthetic datasets. Vision pipeline optimizations, mapping algorithms to compute resources (CPU, GPU, DSP, and more), hypothetical high-level vision pipeline examples (face recognition, object recognition, image classification, augmented reality), optimization alternatives with consideration for performance and power to make effective use of SIMD, VLIW, kernels, threads, parallel languages, memory, and 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. Visual learning concepts, although not the focus of this book, a light introduction is provided to machine learning and statistical learning topics, such as convolutional networks, neural networks, classification and training, clustering and error minimization methods (SVM,’s, kernel machines, KNN, RANSAC, HMM, GMM, LM, and more). Ample references are provided to dig deeper. 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 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 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 About the Author Scott Krig is a pioneer in computer imaging, computer vision, and graphics visualization. He founded Krig Research in 1988 (krigresearch.com), providing the world’s first imaging and vision systems based on high-performance engineering workstations, super-computers, and dedicated imaging hardware, serving customers worldwide in 25 countries. Scott has provided imaging and vision solutions around the globe, and has worked closely with many industries, including aerospace, military, intelligence, law enforcement, government research, and academic organizations. More recently, Scott has worked for major corporations and startups serving commercial markets, solving problems in the areas of computer vision, imaging, graphics, visualization, robotics, process control, industrial automation, computer security, cryptography, and consumer applications of imaging and machine vision to PCs, laptops, mobile phones, and tablets. Most recently, Scott provided direction for Intel Corporation in the area of depth-sensing and computer vision methods for embedded systems and mobile platforms. Scott is the author of many patent applications worldwide in the areas of embedded systems, imaging, computer vision, DRM, and computer security, and studied at Stanford. Computers & Technology,Graphic Design,Programming,Graphics & Multimedia,Software,Reference,Web Graphics Computer Vision Metrics: Survey, Taxonomy, And Analysis provides a technical tour through computer vision, with a survey of over 70 local feature descriptors, blending history of the field with state-of-the-art analysis of contemporary methods, rather than just another 'how-to' book with lots of source code. 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 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. This work focuses on a slice through the field-Computer Vision Metrics-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. Nearly 100 types of global, regional and local features are surveyed. The focus is on the pixel-side of the vision pipeline, rather than the back-end training, classification, machine learning and matching stages. Computer Vision Metrics is not another 'how-to' book with shortcuts, source code examples, and performance analysis, but rather fills a gap in the literature to analyze a wide range of key feature descriptors such as SIFT, SURF, D-NETS, ORB, FREAK, basis spaces, polygon shape descriptors and many other methods, providing a counterpoint discussion intended to compliment the flourishing OpenCV community resources, which already provide ample tutorials and 'how-to' sample code