Figures of merit for quality assessment of binary edge maps
Armando J. Pinho, Luı́s B. Almeida · 2002
We present a novel quality evaluation method for binary edge maps. This method is composed of two different steps: (1) the partition of the edge map into three subsets of active edge elements and (2) the computation of figures of merit, covering five types of distortions, which are errors due to: displacement, smearing, false responses, missing elements, and lack of connectivity.