Flaw Detection from Ultrasonic Images using YOLO and SSD

Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space industry. Due to a vast amount of time needed for a human expert to perform inspection it is practical for a computer to take over that task. Some...

Full description

Saved in:
Bibliographic Details
Published in:2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) pp. 163 - 168
Main Authors: Posilovic, Luka, Medak, Duje, Subasic, Marko, Petkovic, Tomislav, Budimir, Marko, Loncaric, Sven
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2019
Subjects:
Acoustics
automated flaw detection
Computer architecture
convolutional neural networks
Discrete wavelet transforms
image analysis
image processing
Inspection
non-destructive testing
Probes
Testing
Training
ultrasonic imaging
ISSN:1849-2266
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space industry. Due to a vast amount of time needed for a human expert to perform inspection it is practical for a computer to take over that task. Some attempts have been made to produce algorithms for automatic UT scan inspection mainly using older, non-flexible analysis methods. In this paper, two deep learning based methods for flaw detection are presented, YOLO and SSD convolutional neural networks. The methods' performance was tested on a dataset that was acquired by scanning metal blocks containing different types of defects. YOLO achieved average precision (AP) of 89.7% while SSD achieved AP of 84.5 %.
ISSN:1849-2266
DOI:10.1109/ISPA.2019.8868929