Model-Based Image Matching Using Location (ACM Distinguished Dissertation).

Baird, Henry S.

ISBN 10: 0262022206 / ISBN 13: 9780262022200

Published by Mit Pr, 1985

About this Item

Cambridge, MA: The MIT Press, 1985. Hardcover. 128 pp.- This work deals with the computer vision problem of recognizing and locating rigid shapes in the plane which have been subjected to unknown rotation, scaling, and noise. The recognition task includes both locating the overall pattern and identifying each of its features. Location is achieved by finding a geometric registration function that does a good job of superimposing the instance and the model. Identifying the features requires matching each model feature with the corresponding instance feature. A pruned tree-search algorithm is developed which makes effective use of the Soviet ellipsoid algorithm for feasibility of linear constraints. An interesting blend of theoretical analysis and practical implementation shows that the resulting algorithm has an expected runtime that is theoretically asymptotically quadratic in the number of feature points, but practically linear in n for patterns with fewer than 100 points. English text. Condition : as new. Condition : as new copy. ISBN 9780262022200. Keywords : , Pattern recognition.

Seller Inventory # 263330

Bibliographic Details

• Title: Model-Based Image Matching Using Location (ACM Distinguished Dissertation).
• Publisher: Mit Pr
• Publication Date: 1985
• Language: English
• ISBN 10: 0262022206
• ISBN 13: 9780262022200
• Binding: Hardcover
• Condition: as new

About this title

Synopsis

This work deals with the computer vision problem of recognizing and locating rigid shapes in the plane which have been subjected to unknown rotation, scaling, and noise. The recognition task includes both locating the overall pattern and identifying each of its features. Location is achieved by finding a geometric registration function that does a good job of superimposing the instance and the model. Identifying the features requires matching each model feature with the corresponding instance feature.

A pruned tree-search algorithm is developed which makes effective use of the Soviet ellipsoid algorithm for feasibility of linear constraints. An interesting blend of theoretical analysis and practical implementation shows that the resulting algorithm has an expected runtime that is theoretically asymptotically quadratic in the number of feature points, but practically linear in n for patterns with fewer than 100 points.

Contents: Introduction; Task Abstraction; Prior Approaches; A Linear Programming Approach; Geometry of Registrations and Ellipsoids; Worst-Case Number of Feasible Matchings; Random Patterns; Expected Cost of Feasibility Testing; Expected Size of Search Tree; Monte Carlo Trials; Conclusions.

Henry S. Baird received his doctorate from Princeton University. He is currently a technical staff member et AT & T Bell Laboratories. Model-Based Image Matching Using Location is a 1984 ACM Distinguished Dissertation.