Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image Quality Parameters—An Experimental Study

• Main Authors: Castanedo, C.I (Author), Hena, B. (Author), Maldague, X. (Author), Wei, Z. (Author)
• Format: Article
• Language: English
• Published: MDPI 2023
• Subjects: article; Automated defect recognition; automated defect recognition (ADR); Automation; contrast to noise ratio; Contrast-to-noise ratio; deep learning; Deep learning; Defect recognition; Defects; digital X-ray radiography; Digital X-ray radiography; E-learning; experimental study; human; image quality; Image quality; Image quality parameters; Learning algorithms; Learning systems; Non destructive testing; Nondestructive examination; non-destructive testing; Performance; radiography; Radiography images; semantic segmentation; Semantic segmentation; Semantic Segmentation; Semantics; signal noise ratio; Signal to noise ratio; X ray radiography
• Online Access: View Fulltext in Publisher; View in Scopus
• ISBN: 14248220 (ISSN)
• DOI: 10.3390/s23094324

In response to the growing inspection demand exerted by process automation in component manufacturing, non-destructive testing (NDT) continues to explore automated approaches that utilize deep-learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep-learning models. This study investigated the influence of two image-quality parameters, namely signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), on the performance of a U-net deep-learning semantic segmentation model. Input images were acquired with varying combinations of exposure factors, such as kilovoltage, milli-ampere, and exposure time, which altered the resultant radiographic image quality. The data were sorted into five different datasets according to their measured SNR and CNR values. The deep-learning model was trained five distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection-over-union (IoU) metric of 0.9594 on test data of the same category but dropped to 0.5875 when tested on lower CNR test data. The result of this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters in order to enhance the performance of deep-learning segmentation models for NDT digital X-ray radiography applications. © 2023 by the authors.