Artificial Neural Networks For Computer Vision - The Econometric Implications Of Learning While Maximizing

Zhou, Yi-Tong

ISBN 10: 0387976833 / ISBN 13: 9780387976839

Published by Springer, 1991

About this Item

This is a Brand-new US Edition. This Item may be shipped from US or any other country as we have multiple locations worldwide.

Seller Inventory # ABNR-82770

Bibliographic Details

• Title: Artificial Neural Networks For Computer Vision - The Econometric Implications Of Learning While Maximizing
• Publisher: Springer
• Publication Date: 1991
• Language: English
• ISBN 10: 0387976833
• ISBN 13: 9780387976839
• Binding: Soft cover
• Condition: New

About this title

Synopsis

This monograph is an outgrowth of the authors' recent research on the de­ velopment of algorithms for several low-level vision problems using artificial neural networks. Specific problems considered are static and motion stereo, computation of optical flow, and deblurring an image. From a mathematical point of view, these inverse problems are ill-posed according to Hadamard. Researchers in computer vision have taken the "regularization" approach to these problems, where one comes up with an appropriate energy or cost function and finds a minimum. Additional constraints such as smoothness, integrability of surfaces, and preservation of discontinuities are added to the cost function explicitly or implicitly. Depending on the nature of the inver­ sion to be performed and the constraints, the cost function could exhibit several minima. Optimization of such nonconvex functions can be quite involved. Although progress has been made in making techniques such as simulated annealing computationally more reasonable, it is our view that one can often find satisfactory solutions using deterministic optimization algorithms.