Pattern Recognition for Optical PSI Images of Surface Topography Using Wavelets

摘要

This paper proposes a novel philosophical approach using Wavelet and Radon Transform for addressing topographical features of surface from a PSI image. In this work, a combined technique using the Wavelet and Radon Transforms has been investigated and developed to achieve the forensic dissection of PSI image data. As a result, the isolated point-like features on a PSI image can be extracted using the wavelet transform with artifact free thresholding method, and the curve-like features on a PSI image can be identified using the Ridgelet Transform (Multi-Wavelet-Radon transform). Case studies are conducted using a series of femoral heads to demonstrate the application of using the new wavelet model in the assessment PSI images of these surfaces.