Title: Custom Dilated Edge Detection Filters
Authors: Bogdan, Victor
Bonchis, Cosmin
Orhei, Ciprian
Citation: WSCG 2020: full papers proceedings: 28th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 161-168.
Issue Date: 2020
Publisher: Václav Skala - UNION Agency
Document type: conferenceObject
konferenční příspěvek
URI: http://wscg.zcu.cz/WSCG2020/2020-CSRN-3001.pdf
ISBN: 978-80-86943-35-0
ISSN: 2464–4617 (print)
2464–4625 (CD-ROM)
Keywords: dilatační filtry;operátor detekce hran;detekce hrany;Cannyho algoritmus
Keywords in different language: dilated filters;edge detection operator;edge detection;Canny algorithm
Abstract in different language: Edge detection is a basic and fundamental function in image processing. Inspired by the new dilated convolution techniques which have impressive results in machine learning, we discuss here the idea of dilating the standard filters which are used to compute the gradient of an image. We compare the result of the proposed dilated filters with original filters and extend or custom variants of them. We also present the impact of dilatation on a complex edge detection algorithm, like Canny.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG 2020: Full Papers Proceedings

Files in This Item:
File Description SizeFormat 
G83.pdfPlný text7,99 MBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/38463

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.