Wendy Pan

Abstract

A simulated shape recognition system using feature extraction was built as an aid for designing robot vision systems. The simulation allows the user to study the effects of image resolution and feature selection on the performance of a vision system that tries to identify unknown 2-D objects. Performance issues that can be studied include identification accuracy and recognition speed as functions of resolution and the size and makeup of the feature set. Two approaches to feature selection were studied as was a nearest neighbor classification algorithm based on Mahalanobis distances. Using a pool of ten objects and twelve features, the system was tested by performing studies of hypothetical visual recognition tasks.

Library of Congress Subject Headings

Robot vision; Robot vision--Computer simulation; Optical pattern recognition; Computer vision

Publication Date

1989

Document Type

Thesis

Student Type

Graduate

Department, Program, or Center

Computer Science (GCCIS)

Advisor

Biles, John

Advisor/Committee Member

Salem, Edward

Advisor/Committee Member

Anderson, Peter

Comments

Note: imported from RIT’s Digital Media Library running on DSpace to RIT Scholar Works in December 2013.

Campus

RIT – Main Campus

Download

Share

COinS