Neural Networks for Vision and Image Processing

By Gail A. Carpenter

This interdisciplinary survey brings together recent models and experiments on how the brain sees and learns to recognize objects. It shows how to use these insights in technology and describes how neural networks provide a unifying computational framework for reaching these goals. Several chapters describe experiments in neurobiology and visual perception that clarify properties of biological vision and key conceptual issues that biological models need to address. Other chapters describe neural and computational models of biological vision that address such issues and clarify processes whereby biological vision derives its remarkable flexibility and power. Still other chapters use biologically derived models or heuristics to suggest neural network solutions to challenging technological problems in computer vision. Topics range from analyses of motion, depth, color and form to new concepts about learning, attention, pattern recognition, and hardware implementation.

• Format: Paperback
• Language: English
• ISBN: 0262531089
• ISBN13: 9780262531085
• Release Date: January 1992
• Publisher: Mit Pr
• Length: 488 Pages
• Weight: 2.20 lbs.
• Dimensions: 10.3" x 1.3" x 7.0"

Customer Reviews

Hard to find academic papers on vision and neural nets

This is a unique if somewhat older book on the subject of applying neural networks to applications in the fields of image processing and computer vision to solve very specific problems. It is just a collection of papers, so there is no tutorial included on the basics of neural networks themselves. Thus you should already be familiar with the topic including the construction of neural networks via Matlab or whatever toolkit with which you feel comfortable, and you should also already be aware of the limitations and capabilities of neural networks. Since this is a compiled work, the various papers vary tremendously in quality. Personally, I thought "Perception: A Biological Perspective", the paper on "Figure-Ground Separation of Connected Scenic Figures", and "A New Approach to Shape From Shading" were the best papers with the clearest explanations and best figures. However, your mileage may vary depending on your particular interests. Some papers go as far as giving algorithmic steps, and others are little more than a pure text explanation. Quite a few papers might be interesting to the student of neuroscience more than the computer scientist as theories are presented more as models of biological vision than algorithms that can be coded. An example of this would be "Neural Circuits for Visual Attention in the Primate Brain". Parts of this book are online for your examination, so since most of the used copies are going for such high prices, you might want to look at the several online chapters before purchasing. Just put the book's title in quotations and do a Google search. It should be the third link on the returned list of addresses.

Vision it is!

I'm gonna be short, if you're looking for some very complete literature in the field, you just found it. Although it's not very recent, it covers all the topics you may need for research. The same ideas that cotinue evolving.