Minimax Theory Of Image Reconstruction

There exists a large variety of image reconstruction methods proposed by different authors (see e. g. Pratt (1978), Rosenfeld and Kak (1982), Marr (1982)). Selection of an appropriate method for a specific problem in image analysis has been always considered as an art. How to find the image reconstruction method which is optimal in some sense? In this book we give an answer to this question using the asymptotic minimax approach in the spirit of Ibragimov and Khasminskii (1980a,b, 1981, 1982), Bretagnolle and Huber (1979), Stone (1980, 1982). We assume that the image belongs to a certain functional class and we find the image estimators that achieve the best order of accuracy for the worst images in the class. This concept of optimality is rather rough since only the order of accuracy is optimized. However, it is useful for comparing various image reconstruction methods. For example, we show that some popular methods such as simple linewise processing and linear estimation are not optimal for images with sharp edges. Note that discontinuity of images is an important specific feature appearing in most practical situations where one has to distinguish between the "image domain" and the "background" . The approach of this book is based on generalization of nonparametric regression and nonparametric change-point techniques. We discuss these two basic problems in Chapter 1. Chapter 2 is devoted to minimax lower bounds for arbitrary estimators in general statistical models.

The first text to bridge the gap between image processing andjump regression analysis Recent statistical tools developed to estimate jump curves andsurfaces have broad applications, specifically in the area of imageprocessing. Often, significant differences in technicalterminologies make communication between the disciplines of imageprocessing and jump regression analysis difficult. Ineasy-to-understand language, Image Processing and JumpRegression Analysis builds a bridge between the worlds ofcomputer graphics and statistics by addressing both the connectionsand the differences between these two disciplines. The authorprovides a systematic analysis of the methodology behindnonparametric jump regression analysis by outlining procedures thatare easy to use, simple to compute, and have proven statisticaltheory behind them. Key topics include: Conventional smoothing procedures Estimation of jump regression curves Estimation of jump location curves of regression surfaces Jump-preserving surface reconstruction based on localsmoothing Edge detection in image processing Edge-preserving image restoration With mathematical proofs kept to a minimum, this book isuniquely accessible to a broad readership. It may be used as aprimary text in nonparametric regression analysis and imageprocessing as well as a reference guide for academicians andindustry professionals focused on image processing or curve/surfaceestimation.

Presents state-of-the-art sparse and multiscale image and signal processing with applications in astronomy, biology, MRI, media, and forensics.

Techniques and principles of minimax theory play a key role in many areas of research, including game theory, optimization, and computational complexity. In general, a minimax problem can be formulated as min max f(x, y) (1) ",EX !lEY where f(x, y) is a function defined on the product of X and Y spaces. There are two basic issues regarding minimax problems: The first issue concerns the establishment of sufficient and necessary conditions for equality minmaxf(x,y) = maxminf(x,y). (2) "'EX !lEY !lEY "'EX The classical minimax theorem of von Neumann is a result of this type. Duality theory in linear and convex quadratic programming interprets minimax theory in a different way. The second issue concerns the establishment of sufficient and necessary conditions for values of the variables x and y that achieve the global minimax function value f(x*, y*) = minmaxf(x, y). (3) "'EX !lEY There are two developments in minimax theory that we would like to mention.

No detailed description available for "Probability Theory and Mathematical Statistics".

Shanti S. Gupta has made pioneering contributions to ranking and selection theory; in particular, to subset selection theory. His list of publications and the numerous citations his publications have received over the last forty years will amply testify to this fact. Besides ranking and selection, his interests include order statistics and reliability theory. The first editor's association with Shanti Gupta goes back to 1965 when he came to Purdue to do his Ph.D. He has the good fortune of being a student, a colleague and a long-standing collaborator of Shanti Gupta. The second editor's association with Shanti Gupta began in 1978 when he started his research in the area of order statistics. During the past twenty years, he has collaborated with Shanti Gupta on several publications. We both feel that our lives have been enriched by our association with him. He has indeed been a friend, philosopher and guide to us.