Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.12008/42719
How to cite
Title: | Unsupervised smooth contour detection |
Authors: | Grompone von Gioi, Rafael Randall, Gregory |
Type: | Artículo |
Keywords: | Contour detection, Unsupervised, Sub-pixel accuracy, a contrario, NFA, Mann-Whitney U test, Multiple hypothesis testing |
Descriptors: | Procesamiento de Señales |
Issue Date: | 2016 |
Abstract: | An unsupervised method for detecting smooth contours in digital images is proposed. Following the a contrario approach, the starting point is defining the conditions where contours should not be detected: soft gradient regions contaminated by noise. To achieve this, low frequencies are removed from the input image. Then, contours are validated as the frontiers separating two adjacent regions, one with significantly larger values than the other. Significance is evaluated using the Mann-Whitney U test to determine whether the samples were drawn from the same distribution or not. This test makes no assumption on the distributions. The resulting algorithm is similar to the classic Marr-Hildreth edge detector, with the addition of the statistical validation step. Combined with heuristics based on the Canny and Devernay methods, an efficient algorithm is derived producing sub-pixel contours. |
Publisher: | IPOL |
IN: | Image Processing On Line, 6, 2016, pp. 233–267 |
Citation: | Grompone von Gioi, R, Randall, G. "Unsupervised smooth contour detection". Image Processing On Line, 6, 2016, pp. 233–267. https://doi.org/10.5201/ipol.2016.175 |
ISSN: | 2105-1232 |
License: | Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0) |
Appears in Collections: | Publicaciones académicas y científicas - Instituto de Ingeniería Eléctrica |
This item is licensed under a Creative Commons License