DefectDet: A deep learning architecture for detection of defects with extreme aspect ratios in ultrasonic images
Authors:
- Duje MedakDMDuje Medak
- Luka PosilovićLPLuka Posilović
- Marko SubašićMSMarko Subašić
- Marko BudimirMBMarko Budimir
- Sven LončarićSLSven Lončarić
- 1 February 2022
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 473, 107-115
Abstract
No abstract availableKeywords
Funding Information
- European Commission
- European Regional Development Fund (KK.01.2.1.01.0151)
- Nvidia
This publication has 42 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- A support vector machine approach for classification of welding defects from ultrasonic signalsNondestructive Testing and Evaluation, 2014
- Parabola detection using matched filtering for ultrasound B-scansUltrasonics, 2011
- Automatic Defect Classification in Ultrasonic NDT Using Artificial IntelligenceJournal of Nondestructive Evaluation, 2010
- Automatic detection and classification of weld flaws in TOFD data using wavelet transform and support vector machinesInsight - Non-Destructive Testing and Condition Monitoring, 2010
- Nondestructive testing of corrosion in the aerospace industry2009
- Sampling phased array: a new technique for signal processing and ultrasonic imaging2007
- Classification of ultrasonic signalsInternational Journal of Materials and Product Technology, 2006
- The use of artificial neural network in the classification of pulse-echo and TOFD ultra-sonic signalsJournal of the Brazilian Society of Mechanical Sciences and Engineering, 2005
- An improved automated ultrasonic NDE system by wavelet and neuron networksUltrasonics, 2004