Share Email Print

Proceedings Paper

High-speed rail flaw pattern recognition and classification
Author(s): R. Mark Havira; Jinzhu Chen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A real time system for automated rail inspection and flaw classification at speeds up to 25 mph is described. To maintain a fast testing rate, a distributed multiple processor configuration is used for the high speed portion of the system. A graphics computer provides for real time visualization and playback analysis in a modified B-Scan format. A hierarchical approach is used to distribute the total pattern recognition task into a set of stages in which the recognition results at one stage provide input data of the next stage.

Paper Details

Date Published: 30 June 1995
PDF: 10 pages
Proc. SPIE 2458, Nondestructive Evaluation of Aging Railroads, (30 June 1995); doi: 10.1117/12.212690
Show Author Affiliations
R. Mark Havira, Pandrol Jackson Technologies, Inc. (United States)
Jinzhu Chen, Pandrol Jackson Technologies, Inc. (United States)

Published in SPIE Proceedings Vol. 2458:
Nondestructive Evaluation of Aging Railroads
Donald E. Gray; Daniel H. Stone, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?