Automatic detection of welding defects using the convolutional neural network

Roman Sizyakin; Viacheslav Voronin; Nikolay Gapon; Aleksandr Zelensky; Aleksandra Pižurica

doi:10.1117/12.2525643

21 June 2019 Automatic detection of welding defects using the convolutional neural network

Roman Sizyakin, Viacheslav Voronin, Nikolay Gapon, Aleksandr Zelensky, Aleksandra Pižurica

Proceedings Volume 11061, Automated Visual Inspection and Machine Vision III; 110610E (2019) https://doi.org/10.1117/12.2525643
Event: SPIE Optical Metrology, 2019, Munich, Germany

Abstract

Quality control of welded joints is an important step before commissioning of various types of metal structures. The main obstacles to the commissioning of such facilities are the areas where the welded joint deviates from acceptable defective standards. The defects of welded joints include non-welded, foreign inclusions, cracks, pores, etc. The article describes an approach to the detection of the main types of defects of welded joints using a combination of convolutional neural networks and support vector machine methods. Convolutional neural networks are used for primary classification. The support vector machine is used to accurately define defect boundaries. As a preprocessing in our work, we use the methods of morphological filtration. A series of experiments confirms the high efficiency of the proposed method in comparison with pure CNN method for detecting defects.

Citation Download Citation

Roman Sizyakin, Viacheslav Voronin, Nikolay Gapon, Aleksandr Zelensky, and Aleksandra Pižurica "Automatic detection of welding defects using the convolutional neural network", Proc. SPIE 11061, Automated Visual Inspection and Machine Vision III, 110610E (21 June 2019); https://doi.org/10.1117/12.2525643

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