The Multiscale Medial Response of Grey-level Images

The Concordance-based Medial Axis Transform (CMAT) presented in this paper is a multiscale medial axis (MMA) algorithm that computes medial evidence from grey-level boundary measures. It differs from previous algorithms of this type in considering the symmetry of both boundary position and strength. The resultant MMA transform is not prone to the generation of spurious medial responses exhibited by previous algorithms, but accurately estimates the position of the medial axis across scale. In addition, the medial axis and object scale are more distinctly identified. Thus CMAT medialness responses are easier to interpret than responses from previously reported measures. This is illustrated using a test figure and a radiograph of a hand.