Search

Abstract: In this paper, a novel geometric active contour model for color image is presented. It combines squared local contrast based alignment term about directional information of edge location as part of driving force, together with the improved geodesic active contour model containing Bays error based two-region segmentation information. And all these measures are integrated as a unified framework. Finally, an unconditionally stable and simple numerical scheme, including the narrow band and fast marching methods, is introduced for efficiently implementing this novel model. Experimental results on color image segmentation show that it can extract the contour of color images precisely and its performance is shown much better than the geodesic-aided C–V (GACV) method when directional information about edge location is supplied. [Copyright &y& Elsevier]