A novel defect detection technique based on automatic detection of potential background

Masoumeh Aminzadeh; Thomas Kurfess

doi:10.1117/12.2223289

1 April 2016 A novel defect detection technique based on automatic detection of potential background

Masoumeh Aminzadeh, Thomas Kurfess

Proceedings Volume 9805, Health Monitoring of Structural and Biological Systems 2016; 98051Q (2016) https://doi.org/10.1117/12.2223289
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2016, Las Vegas, Nevada, United States

Abstract

Automated defect detection from optical images is an efficient non-destructive evaluation technique for surface and structure health inspection. Background subtraction is a widely-used technique for automated defect detection. In background subtraction, an image of the part with no defect, called background image, is generated and subtracted from the defective part image; the resulted large differences are then considered as defects. In this paper, a new background generation technique is proposed that allows for efficient defect detection at a low-computational load. In this technique, a defect-free region is generated by approximately locating defects and removing them from the original image. The resulted defect-free region is now used to generate the background. The procedure and performance of the algorithm is illustrated by an example.

Citation Download Citation

Masoumeh Aminzadeh and Thomas Kurfess "A novel defect detection technique based on automatic detection of potential background", Proc. SPIE 9805, Health Monitoring of Structural and Biological Systems 2016, 98051Q (1 April 2016); https://doi.org/10.1117/12.2223289

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