Robot Vision (MIT Electrical Engineering and Computer Science) [Hardcover]

Berthold K.P. Horn (Author)

Book Description

Publication Date: March 13, 1986 | ISBN-10: 0262081598 | ISBN-13: 978-0262081597 | Edition: MIT Press ed

This book presents a coherent approach to the fast moving field of machine vision, using a consistent notation based on a detailed understanding of the image formation process. It covers even the most recent research and will provide a useful and current reference for professionals working in the fields of machine vision, image processing, and pattern recognition.An outgrowth of the author's course at MIT, Robot Vision presents a solid framework for understanding existing work and planning future research. Its coverage includes a great deal of material that important to engineers applying machine vision methods in the real world. The chapters on binary image processing, for example, help explain and suggest how to improve the many commercial devices now available. And the material on photometric stereo and the extended Gaussian image points the way to what may be the next thrust in commercialization of the results in this area. The many exercises complement and extend the material in the text, and an extensive bibliography will serve as a useful guide to current research.Contents: Image Formation and Image Sensing. Binary Images: Geometrical Properties; Topological Properties. Regions and Image Segmentation. Image Processing: Continuous Images; Discrete Images. Edges and Edge Finding. Lightness and Color. Reflectance Map: Photometric Stereo Reflectance Map; Shape from Shading. Motion Field and Optical Flow. Photogrammetry and Stereo. Pattern Classification. Polyhedral Objects. Extended Gaussian Images. Passive Navigation and Structure from Motion. Picking Parts out of a Bin.Berthold Klaus Paul Horn is Associate Professor, Department of Electrical Engineering and Computer Science, MIT. Robot Vision is included in the MIT Electrical Engineering and Computer Science Series.

Editorial Reviews

Review

" Robot Vision is an impressive book....an excellent introduction to the field and the first book to thoroughly cover the mathematics of computer vision." Charles Thorpe , American Scientist

"A very good book indeed, probably the best currently available on robot vision and related topics....a valuable reference workfor researchers in this field." T.M. Husband , Times Higher Education Supplement

About the Author

Berthold K. P. Horn is Professor in the department of Electrical Engineering and Computer Science and a member of the Artificial Intelligence Lab at the Massachusetts Institute of Technology.

Product Details

• Hardcover: 480 pages
• Publisher: The MIT Press; MIT Press ed edition (March 13, 1986)
• Language: English
• ISBN-10: 0262081598
• ISBN-13: 978-0262081597
• Product Dimensions: 9.2 x 6.2 x 1.2 inches
• Shipping Weight: 1.8 pounds (View shipping rates and policies)
• Average Customer Review: 5.0 out of 5 stars  See all reviews (6 customer reviews)
• Amazon Best Sellers Rank: #143,510 in Books (See Top 100 in Books)
  • #14 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Theory of Computing
  • #35 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Robotics

More About the Author

Discover books, learn about writers, read author blogs, and more.

Customer Reviews

Most Helpful Customer Reviews

17 of 17 people found the following review helpful:

5.0 out of 5 stars The Classic of Computer Vision, June 11, 2000

By A Customer

This review is from: Robot Vision (MIT Electrical Engineering and Computer Science) (Hardcover)

When I first picked up Robot Vision, I was a bit concerned at the age of the book: the field of computer/machine/robot vision progresses at a fantastic pace, and it would seem a given that such a book would be so out of date as to be useless.

However, while this book might not reflect the latest research, especially the tight interweaving of computer graphics and computer vision as exists now or in areas such as active vision, it is a rich presentation of the core ideas of machine vision. In particular, it provides a mathematically rigorous presentation, focusing on core notions of geometric optics and calibration, as well as classic approaches to segmentation, edge detection, signal filtering, and the like.

I would strongly suggest this book as a text that every serious computer vision, robotics, or computer graphics researcher should own; of course, it isn't the _only_ book you should own, and the bibliography certainly won't let you in on the latest trends in vision. Nonetheless, I think the book is so well written that it will remain useful for many years to come.

5 of 5 people found the following review helpful:

5.0 out of 5 stars A great old book on the fundamentals of computer vision, January 30, 2007

By 

calvinnme - See all my reviews
(HALL OF FAME REVIEWER)    (VINE VOICE)    (TOP 50 REVIEWER)   

This review is from: Robot Vision (MIT Electrical Engineering and Computer Science) (Hardcover)

This book does a good job of introducing the readers to the basics of computer vision - it really has nothing to do with robots outside of the last chapter, other than if you build one and need to give it vision capabilities, you need to know the information in this book. Physics equations via calculus and ODE are used to describe how light intereacts with solid objects and also with image sensors, the latter tieing in to the subject of robot vision. Therefore, the reader should have a good knowledge of first-year university physics as well as multi-variable calculus. As a reference for the geometrical and physical mathematics of light interacting with surfaces and the camera, it is particularly excellent.

Horn does a great job of deriving and providing the equations you need, and brings it all together with excellent narrative and very good illustrations. The book goes all the way from the basics of image formation, to simple matrix operations such as edge detection, to some more advanced topics such as shape from shading. The final chapter, on picking parts out of a bin, uses the ideas developed in previous chapters to come up with the basic design of a robot hand-eye system that is capable of picking up specific parts from a parts bin. It really is a very good unifying capstone to the entire book. The only drawback I can see in the book is that it pretty much stays in the domain of continuous mathematics. There is not much in the way of explicit algorithm steps - the author expects the reader to be able to do that based on his explanation and equations, and given the high quality of the text this is really not too rash of an assumption.

Because of its age it doesn't have some of the more modern techniques and algorithms, but if I had to choose between this older book and that more recently published waste of trees, "Computer Vision: A Modern Approach", give me this book every time. You get a firm foundation in the basics, plus a good understanding of some more advanced topics too.

7 of 10 people found the following review helpful:

5.0 out of 5 stars Good introduction to Computer and Robot Vision, December 3, 2003

By 

Thomas Wikman "Texas Swede" (Texas) - See all my reviews
(VINE VOICE)   

This review is from: Robot Vision (MIT Electrical Engineering and Computer Science) (Hardcover)

I have to admit that I read this book many years ago. This is not a book that should be read as a way to keep oneself updated on the latest research in the field. It should be seen as a comprehensive, but systematic introduction to basic machine vision techniques. As such, it is a great book, maybe a classic. Its focus is on such topics as Binary Image Processing, Optics, Image formation, Transforms, Filtering, Stereo vision, Optical flow, Noise reduction, etc. It is well organized, and it covers the fundamentals of many useful techniques.