Your browser doesn't support javascript.
loading
Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image Quality Parameters-An Experimental Study.
Hena, Bata; Wei, Ziang; Castanedo, Clemente Ibarra; Maldague, Xavier.
Afiliación
  • Hena B; Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada.
  • Wei Z; Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la Médecine, Université Laval, Quebec City, QC G1V 0A6, Canada.
  • Castanedo CI; Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada.
  • Maldague X; Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la Médecine, Université Laval, Quebec City, QC G1V 0A6, Canada.
Sensors (Basel) ; 23(9)2023 Apr 27.
Article en En | MEDLINE | ID: mdl-37177528
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.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Suiza

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Suiza