Detecting salient contours using orientation energy distribution Conference Paper

abstract

• How does our visual system detect prominent contours? Our investigation begins with the observation that neurons in the visual cortex have receptive fields similar to oriented Gabor filters. Unlike plain gray-level intensity histograms which greatly vary across images, we found that Gabor orientation-response (or orientation-energy) histograms of natural images have a fairly uniform shape. Based on this observation, we derived a threshold criterion which only depends on the standard deviation of the orientation-energy distribution. Thus, the same principle could be uniformly applied to different natural images, either locally or globally. Comparison with thresholds chosen by humans showed that the criterion can accurately predict human performance. Further, the proposed criterion can be easily implemented in a neural network, which is currently under investigation.

name of conference

• Proceedings of the International Joint Conference on Neural Networks, 2003.

authors

• Choe, Yoonsuck

published proceedings

• PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4

author list (cited authors)

• Lee, H. C., & Choe, Y.

citation count

• 7

complete list of authors

• Lee, HC||Choe, Y

publication date

• January 2003

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• IEEE International Conference on Neural Networks - Conference Proceedings  Journal

keywords

• 7 Affordable And Clean Energy

Digital Object Identifier (DOI)

• 10.1109/ijcnn.2003.1223343

International Standard Book Number (ISBN) 10

• 0-7803-7898-9

start page

• 206

end page

• 211

volume

• 1

URL

• http%3A%2F%2Fdx.doi.org%2F10.1109%2Fijcnn.2003.1223343

user-defined tag

• 7 Affordable and Clean Energy