Abstract
The results of Chapters 3–5 show that the best possible rates of convergence in various image and edge estimation problems are attained by estimators that are complicated from the computational viewpoint. On the other hand, there are many data processing algorithms in image analysis which deal with some simple partial procedures and do apply in practice. We study here two popular and important classes of such procedures: linewise processing and linear estimates. The questions are: whether they ensure the minimax rate of convergence and, if not, what is the best possible rate within these classes?
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag New York, Inc.
About this chapter
Cite this chapter
Korostelev, A.P., Tsybakov, A.B. (1993). Image Reconstruction Under Restrictions on Estimates. In: Minimax Theory of Image Reconstruction. Lecture Notes in Statistics, vol 82. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-2712-0_6
Download citation
DOI: https://doi.org/10.1007/978-1-4612-2712-0_6
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-94028-1
Online ISBN: 978-1-4612-2712-0
eBook Packages: Springer Book Archive