Computer Vision Metrics

1. Front Matter

   Pages i-xviii

   PDF

2. Image Capture and Representation

   • Scott Krig

   Pages 1-33

3. Image Pre-Processing

   • Scott Krig

   Pages 35-74

4. Global and Regional Features

   • Scott Krig

   Pages 75-114

5. Local Feature Design Concepts

   • Scott Krig

   Pages 115-166

6. Taxonomy of Feature Description Attributes

   • Scott Krig

   Pages 167-186

7. Interest Point Detector and Feature Descriptor Survey

   • Scott Krig

   Pages 187-246

8. Ground Truth Data, Content, Metrics, and Analysis

   • Scott Krig

   Pages 247-271

9. Vision Pipelines and Optimizations

   • Scott Krig

   Pages 273-317

10. Feature Learning Architecture Taxonomy and Neuroscience Background

    • Scott Krig

    Pages 319-374

11. Feature Learning and Deep Learning Architecture Survey

    • Scott Krig

    Pages 375-514

12. Back Matter

    Pages 515-637

    PDF

Based on the successful 2014 book published by Apress, this textbook edition is expanded to provide a comprehensive history and state-of-the-art survey for fundamental computer vision methods and deep learning. With over 800 essential references, as well as chapter-by-chapter learning assignments, both students and researchers can dig deeper into core computer vision topics and deep learning architectures. The survey covers everything from feature descriptors, regional and global feature metrics, feature learning architectures, deep learning, neuroscience of vision, neural networks, and detailed example architectures to illustrate computer vision hardware and software optimization methods. 



To complement the survey, the textbook includes useful analyses which provide insight into the goals of various methods, why they work, and how they may be optimized.



The text delivers an essential survey and a valuable taxonomy, thus providing a key learning tool for students, researchers and engineers, to supplement the many effective hands-on resources and open source projects, such as OpenCV and other imaging and deep learning tools.

• Computer vision
• Deep learning
• Feature learning
• Feature descriptors
• Image processing
• Computational imaging
• Neural networks
• 3D reconstruction
• Deep neural networks
• Computational neuroscience
• Convolutional neural networks
• DNN
• CNN
• Computer engineering
• Signal processing
• Image processing

• Krig Research, USA

  Scott Krig

Scott Krig is a pioneer in computer imaging, computer vision, and graphics visualization. He founded Krig Research in 1988, providing the world's first image 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, he provided direction for Intel Corporation in the area of depth-sensing andcomputer 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.   

Policies and ethics