Read more
This volume of original papers has been assembled to honor Azriel Rosenfeld, a dominant figure in the field of computer vision and image processing for over 30 years. Over this period he has made many fundamental and pioneering contributions to nearly every area in this field. Azriel Rosenfeld wrote the first textbook in the field in 1969 and was the founding editor of its first journal in 1972. The contributions in this book illustrate the change that have occurred in dealing with crucial research problems and the methodologies employed to solve them. The 22 papers specifically written for this text are by only a handful of researchers who have known and worked with Azriel over the years. These papers address five major themes: image segmentation, feature extraction, 3D shape estimation from 2D images, object recognition, and applications technologies.
List of contents
Preface/Introduction (Kevin Bowyer and Narendra Ahuja).
Section 1 -- Segmentation of Images into Regions.
Texture Segregation in Chromatic Element-Arrangement Patterns (Jacob Beck).
Multiresolution GMRF Models for Image Segmentation (Rama Chellappa Anthana Krishnamachari).
Feature Selection for Texture Segmentation (Michael Brady and Zhi-Yan Xie).
A Transform for Multiscale Image Segmentation (Narendra Ahuja).
Image Segmentation Using Clustering (Anil K. Jain and Patrick J. Flynn).
Boundary Encoding Revisited (Herbert Freeman).
Section 2 -- Feature Extraction.
Optimal Edge Detection in Images (Richard J. Qian and Thomas S. Huang).
Metamerism in Complete Sets of Image Operators (Jan J. Koenderink and A.J. van Doorn).
Structural Scales in Computational Vision (Steven W. Zucker).
Propagating Covariance in Computer Vision (Robert M. Haralick).
Section 3 -- 3-D Shape from 2-D images.
Improving the Vision of Magic Eyes: A Guide to Better Autostereograms (A. M. Bruckstein, R. Onn, and T. J. Richardson).
Shape Recovery from Stationary Surface Contours by Controlled Observer Motion (Liangyin Yu and Charles R. Dyer).
Section 4 -- Object Recognition.
Object Recognition Research: Matched Filtering becomes Bayesian Reasoning (Robert Hummel).
Finding and Describing Objects in Complex Images (Michael F. Kelly and Martin D. Levine).
Networks that Learn for Image Understanding (Tomaso Poggio and Kah-Kay Sung).
A Comparative Study of Three Paradigms for Object Recognition--Bayesian Statistics, Neural Networks, and Expert Systems (J. K. Aggarwal, J. Ghosh, D. Nair, and I. Taha).
Section 5 -- Computer Vision Technology in Applications.
Towards 3-D Model-Based Tracking of Humans in Action (D. M. Gavrila and L. S. Davis).
Descriptive and Prescriptive Languages for Mobility Tasks: Are They Different? (R. Bajcsy and H. -H. Nagel).
Computer Vision and Visual Information Retrieval (Ramesh Jain and Amarnath Gupta).
Object-Based and Image-Based Representations of Objects by their Interiors (Hanan Samet).
Section 6 -- Image Understanding in Human and Machine Intelligence.
Perceptual Intelligence (Alex Pentland).
Author Index.
About the author
Maggie Bowyer (they/them/theirs) is a poet, cat parent, and the author of various poetry collections including Ungodly (2022) and When I Bleed (2021). They are an essayist focusing on Endometriosis, chronic pain, and trauma. They have been featured in Bourgeon Magazine, Capsule Stories, Plainsongs Poetry Magazine, The Abbey Review, Troublemaker Firestarter, Wishbone Words, and more. They were the Editor-in-Chief of The Lariat Newspaper, a quarter-finalist in Brave New Voices 2016, and a Marilyn Miller Poet Laureate. You can find their work on Instagram and TikTok @maggie.writes.
