Title :
Neuro-visually inspired figure-ground segregation
Author :
Ghosh, Kuntal ; Roy, Anirban
Author_Institution :
Machine Intell. Unit & Center for Soft, Indian Stat. Inst., Kolkata, India
Abstract :
An extra-classical receptive field (ECRF) based mid-level model of visual processing which we refer to as the neuro-visually inspired model of figure-ground segregation (NFGS) is proposed in this work. It is inspired by the non-linear interaction of the classical receptive field (CRF) and its non-classical extended surround, comprising of the non-linear mean increasing and decreasing sub-units. A simple digital kernel has been derived that performs efficient mid-level block representation.
Keywords :
computer vision; neurophysiology; visual perception; extra-classical receptive field based mid-level model; mid-level block representation; neurovisually inspired figure-ground segregation; nonlinear interaction; visual processing; Approximation methods; Brain modeling; Image segmentation; Information filters; Information processing; Laplace equations; extra-classical receptive field; figure-ground segregation; mid-level vision;
Conference_Titel :
Image Information Processing (ICIIP), 2011 International Conference on
Conference_Location :
Himachal Pradesh
Print_ISBN :
978-1-61284-859-4
DOI :
10.1109/ICIIP.2011.6108932
