Compressed sensing and defect-based dictionaries for characteristics extraction in mm-wave non-destructive testing
 
Compressed sensing and defect-based dictionaries for characteristics extraction in mm-wave non-destructive testing ■
 
Edison Cristofani, Mathias Becquaert, Gokarna Pandey, Marijke Vandewal, Nikos Deligiannis, Johan Stiens
 
Abstract ■

In ultra-wideband non-destructive testing of large multilayered polymers, data collection and reduction can be achieved by applying compressed sensing techniques. In this work, using effective modelling of possible defects, such as air gaps between layers, we construct defect dictionaries and use them as support data for a signal similarity-based classifier, which will automatically extract the main characteristics of the inspected defect.