Title :
Figure-ground separation by a dynamical system
Author :
Zhang, J. ; Gao, J. ; Liu, J.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Wisconsin Univ., Milwaukee, WI, USA
fDate :
1/1/1999 12:00:00 AM
Abstract :
This correspondence describes a novel nonlinear scheme for figure-ground separation where a nonlinear differential equation is defined at each pixel site and coupled with those at neighboring sites. The steady state solution enhances salient image structures and suppresses background noise. Experimental results on synthetic and real-world images demonstrate the efficacy of this scheme
Keywords :
feature extraction; image enhancement; interference suppression; nonlinear dynamical systems; background noise suppression; dynamical system; figure-ground separation; image analysis; image enhancement; nonlinear differential equation; nonlinear scheme; pixel site; real-world images; salient image structures; steady state solution; synthetic images; Background noise; Computer vision; Couplings; Differential equations; Feature extraction; Humans; Image edge detection; Image segmentation; Machine vision; Steady-state;
Journal_Title :
Image Processing, IEEE Transactions on
