Integrating Graphics and Vision for Object Recognition / Edition 1

by Mark R. Stevens, J. Ross Beveridge

Overview

Integrating Graphics and Vision for Object Recognition serves as a reference for electrical engineers and computer scientists researching computer vision or computer graphics.
Computer graphics and computer vision can be viewed as different sides of the same coin. In graphics, algorithms are given knowledge about the world in the form of models, cameras, lighting, etc., and infer (or render) an image of a scene. In vision, the process is the exact opposite: algorithms are presented with an image, and infer (or interpret) the configuration of the world. This work focuses on using computer graphics to interpret camera images: using iterative rendering to predict what should be visible by the camera and then testing and refining that hypothesis.
Features of the book include:

• Many illustrations to supplement the text;
• A novel approach to the integration of graphics and vision;
• Genetic algorithms for vision;
• Innovations in closed loop object recognition.
Integrating Graphics and Vision for Object Recognition will be of interest to research scientists and practitioners working in fields related to the topic. It may also be used as an advanced-level graduate text.

Product Details

ISBN-13:	9781441948601
Publisher:	Springer US
Publication date:	12/07/2010
Series:	The Springer International Series in Engineering and Computer Science , #589
Edition description:	Softcover reprint of hardcover 1st ed. 2001
Pages:	184
Product dimensions:	6.10(w) x 9.25(h) x 0.24(d)

Table of Contents

1. Introduction.- 2. Previous Work.- 3. Render: Predicting Scenes.- 4. Match: Comparing Images.- 5. Refine: Iterative Search.- 6. Evaluation.- 7. Conclusions.- Appendices.- A— Generating Scene Hypotheses.- 1. Object Detection and Pose Indexing.- 2. Detection based on Color Decision Trees.- 3. Pose Indexing.

Editorial Reviews

Characterizing computer graphics and computer vision as different sides of the same coin, Stevens (Worcester Polytechnic Institute) and Beveridge (Colorado State U.) focus on using computer graphics to interpret camera images, that is, using iterative rendering to predict what should be visible by the camera and then testing and refining that hypothesis. They offer research scientists and practitioners innovations in integrating graphics and vision and in closed loop object recognition, genetic algorithms for vision, and many monochrome illustrations to supplement the text. The work could also be used in an advanced graduate course. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Booknews