Detection And Characterization Of Flaws On Machined Metal Surfaces

Reza Safabakhsh; Rafael C. Gonzalez

doi:10.1117/12.947629

16 January 1989 Detection And Characterization Of Flaws On Machined Metal Surfaces

Reza Safabakhsh, Rafael C. Gonzalez

Proceedings Volume 0954, Optical Testing and Metrology II; (1989) https://doi.org/10.1117/12.947629
Event: SPIE International Symposium on Optical Engineering and Industrial Sensing for Advance Manufacturing Technologies, 1988, Dearborn, MI, United States

Abstract

This work studies detection and characterization of flaws on machined metal surfaces based on the flaw depth. Diffracted light resulting from the incidence of a laser beam on the metal surface is sensed by a solid-state detector and analyzed by a digital computer to determine the surface conditions. Statistical analysis and pattern recognition algorithms are used to find data features which strongly correlate with the flaw depth. Trainable classifiers use these features to detect surface flaws whose (maximum) depth exceeds a given threshold. The range of flaw depth and a rough depth estimate are also determined and problems arising due to detector characteristics or interaction of flaw parameters are discussed. Experimental results of near 100% correct detection and 50% to 85% correct range determinations are reported.

Citation Download Citation

Reza Safabakhsh and Rafael C. Gonzalez "Detection And Characterization Of Flaws On Machined Metal Surfaces", Proc. SPIE 0954, Optical Testing and Metrology II, (16 January 1989); https://doi.org/10.1117/12.947629

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available