Visual enhancement of incised text

摘要

This paper describes ongoing research into the application of pattern recognition to incised documents, for which grooves and other structural surface markings are significant, rather than surface coloration. We deduce incised stroke information by imaging the document under a carefully selected set of lighting conditions that cause shadows to be cast, and observing the position and motion of shadow areas. The removal of wood grain noise, image registration, and the detection of image features using phase congruency techniques form the basis of our work. We also briefly describe our approach to interpolating broken strokes and recovering 3D surface structure.