Work

The role of non-CRF inhibition in contour detection

Year: 2003

Type: conference-paper

Abstract: We propose a biologically motivated computational step, called non-classical receptive field (non-CRF) inhibition,\nto improve the performance of contour detectors. Non-CRF inhibition is exhibited by 80% of the orientation\nselective neurons in the primary visual cortex of macaque monkeys and has been demonstrated to influence the\nvisual perception of man as well. We introduce an image processing operator, the bar cell operator, which consists\nof a Gabor energy operator augmented with non-CRF inhibition. This operator responds strongly to isolated lines,\nedges and contours, but exhibits a weaker or no response to edges that make part of texture. We evaluate the\ncontour detection performance of the proposed operator for images of natural scenes with associated ground truth\nedge maps. The bar cell operator consistently outperforms the Canny edge detector, mostly due to a reduced\nnumber of false positives.

Source: University of Groningen research database (University of Groningen / Centre for Information Technology)

Authors: Cosmin Grigorescu, Nicolai Petkov, Michel A. Westenberg

Institution: University of Groningen

Language: English

Topic: Image and Object Detection Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2156273688

FWCI:

Cites: 25

Cited by: 5

Related to: 10