Complex Ridgelets for the Extraction of Morphological Features on Engineering Surfaces

In this paper, a complex ridgelets transform, which provides approximate shift invariance analysis of line singularities, is proposed to extract morphological features with linear or directional/objective property, by taking a Dual Tree Complex Wavelet Transform (DT-CWT) on the projections of the Finite Radon Transform (FRAT). The Numerical experiments show the remarkable potential of this methodology to analyse engineering and bioengineering surfaces with liner scratches in comparison to wavelet-based methods developed in our pervious work.