Robustness analysis of transferable cellular automata rules optimized for edge detection

Edge detection is an important component in many computer vision tasks since edges convey information about the objects in an image. This paper presents a comparative analysis of the proposed edge detector with respect to one of the state-of-the-art methods, the Canny edge detector. Our edge detecti...

Full description

Saved in:
Bibliographic Details
Published inProcedia computer science Vol. 176; pp. 713 - 722
Main Authors Dumitru, Delia, Andreica, Anca, Dioşan, Laura, Bálint, Zoltán
Format Journal Article
LanguageEnglish
Published Elsevier B.V 2020
Subjects
separated by semicolons
Type your keywords here
Type your keywords here
separated by semicolons
Online AccessGet full text

Cover

More Information
Summary:Edge detection is an important component in many computer vision tasks since edges convey information about the objects in an image. This paper presents a comparative analysis of the proposed edge detector with respect to one of the state-of-the-art methods, the Canny edge detector. Our edge detection model involves the supervised optimization of a cellular automaton rule with particle swarm optimization. Using this scheme we obtain transferable rules that can be applied on multiple images with similar properties. We test the two methods on clean and noisy images and the proposed method outperforms Canny on average on our data set containing a variety of edges.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2020.09.044