B. Montrucchio F. Lamberti A. Sanna P. Montuschi
Dipartimento di Automatica e Informatica
Politecnico di Torino
c.so Duca degli Abruzzi 24, I-10129 Torino Italy
Many image processing tasks depend on contrast measures, which can be
to compare and improve contrast enhancement algorithms. Contrast
definitions are not always suitable for all situations. In particular an isotropic
local contrast measure, that produces a flat response to sinusoidal gratings, can
be difficult to obtain. In this paper we review the main existing contrast measures,
and propose a new approach, denoted as Circular Mask Metric (CMM). It is based
on band-pass filters and circular mask based local contrast computations.
This approach has been applied on different test images and with three contrast
enhancement methods, in order to show its potentialities for contrast
enhancement algorithm testing and improving.