Machine Learning and Image Interpretation / Edition 1

by Terry Caelli, Walter F. Bischof

Overview

In this groundbreaking new volume, computer researchers discuss the development of technologies and specific systems that can interpret data with respect to domain knowledge. Although the chapters each illuminate different aspects of image interpretation, all utilize a common approach - one that asserts such interpretation must involve perceptual learning in terms of automated knowledge acquisition and application, as well as feedback and consistency checks between encoding, feature extraction, and the known knowledge structures in a given application domain. The text is profusely illustrated with numerous figures and tables to reinforce the concepts discussed.

Product Details

ISBN-13:	9780306457616
Publisher:	Springer US
Publication date:	11/30/1997
Series:	Advances in Computer Vision and Machine Intelligence
Edition description:	1997
Pages:	423
Product dimensions:	6.14(w) x 9.21(h) x 0.04(d)

Table of Contents

1 An Overview and Perspective of Image Interpretation.- 2 Fuzzy Conditional Rule Generation for the Learning and Recognition of 3D Objects from 2D Images.- 3 Relational Evidence Theory and Interpreting Schematics.- 4 Cite—Scene Understanding and Object Recognition.- 5 See++: An Object Oriented Theory of Task Specific Vision.- 6 SOO-PIN: Picture Interpretation Networks.- 7 Invariance Signatures for Two-Dimensional Contours.- 8 ABC: Biologically Motivated Image Understanding.- References.- Author Index.

Editorial Reviews

Describes seven original technologies and specific systems that can interpret image data with respect to domain knowledge. They share the notion that processes that reflect how humans apply world knowledge to image data must involve perceptual learning in terms of automated knowledge acquisitions and application as well as feedback and consistency checks between encoding, feature extractions, and known knowledge structures in a given applications domain. Among the technologies are fuzzy conditional rule generation for learning and recognizing three-dimensional objects from two-dimensional images, the Cite system for understanding scenes and recognizing objects, See++, SOO-PIN for picture interpretation networks, and ABC for a biologically motivated understanding of images. Annotation c. by Book News, Inc., Portland, Or.

Booknews