The state-of-the art in computer vision: theory, applications, and programming

Whether you're a working engineer, developer, researcher, or student, this is your single authoritative source for today's key computer vision innovations. Gerard Medioni and Sing Bing Kang present advances in computer vision such as camera calibration, multi-view geometry, and face detection, and introduce important new topics such as vision for special effects and the tensor voting framework. They begin with the fundamentals, cover select applications in detail, and introduce two popular approaches to computer vision programming.

• Camera calibration using 3D objects, 2D planes, 1D lines, and self-calibration
• Extracting camera motion and scene structure from image sequences
• Robust regression for model fitting using M-estimators, RANSAC, and Hough transforms
• Image-based lighting for illuminating scenes and objects with real-world light images
• Content-based image retrieval, covering queries, representation, indexing, search, learning, and more
• Face detection, alignment, and recognition--with new solutions for key challenges
• Perceptual interfaces for integrating vision, speech, and haptic modalities
• Development with the Open Source Computer Vision Library (OpenCV)
• The new SAI framework and patterns for architecting computer vision applications

The popularity of topics in computer vision shifts periodically, precipitated by what actually works or shows great promise, changing interests in applications, and on occasion, fortuitous advancements in hardware technology. Some of these topics remain popular over the years, such as facial recognition and modeling from images, while others are relatively new, such as computer vision techniques for graphics and the application of level-set theory in computer vision. Many currently popular topics in computer vision tend to be multidisciplinary. The primary aim of this book is to provide a snapshot of topics that are currently popular in computer vision and enable the curious to get a quick grasp of such topics. Each chapter is a self-contained primer on a particular subject of current interest, and is suitable for use in an introductory short course. The chapters are written by leading researchers in their respective fields. This book is intended for researchers and technical practitioners in computer vision and other closely allied fields such as computer graphics and image processing. No advanced technical background knowledge is necessary in order to understand the contents of the book.