Publication details

 

GPU Implementation of Linear Morphological Openings with Arbitrary Angle

Basic information
Original title:GPU Implementation of Linear Morphological Openings with Arbitrary Angle
Authors:Pavel Karas, Vincent Morard, Jan Bartovský, Thierry Grandpierre, Eva Dokládalová, Petr Matula, Petr Dokládal
Further information
Citation:KARAS, Pavel, Vincent MORARD, Jan BARTOVSKÝ, Thierry GRANDPIERRE, Eva DOKLÁDALOVÁ, Petr MATULA a Petr DOKLÁDAL. GPU Implementation of Linear Morphological Openings with Arbitrary Angle. Journal of Real-Time Image Processing, Neuveden: Springer-Verlag, 2012, Neuveden, online, s. 1-15. ISSN 1861-8200. doi:10.1007/s11554-012-0248-7.Export BibTeX
@article{964786,
author = {Karas, Pavel and Morard, Vincent and Bartovský, Jan and Grandpierre, Thierry and Dokládalová, Eva and Matula, Petr and Dokládal, Petr and Morard, Vincent and Bartovský, Jan and Grandpierre, Thierry and Dokládalová, Eva},
article_location = {Neuveden},
article_number = {online},
doi = {http://dx.doi.org/10.1007/s11554-012-0248-7},
keywords = {gpu; morphology; opening; closing; linear; real-time},
language = {eng},
issn = {1861-8200},
journal = {Journal of Real-Time Image Processing},
title = {GPU Implementation of Linear Morphological Openings with Arbitrary Angle},
url = {http://dx.doi.org/10.1007/s11554-012-0248-7},
volume = {Neuveden},
year = {2012}
}
Original language:English
Field:Informatics
WWW:link to a new windowhttp://dx.doi.org/10.1007/s11554-012-0248-7
Type:Article in Periodical
Keywords:gpu; morphology; opening; closing; linear; real-time

Linear morphological openings and closings are important non-linear operators from mathematical morphology. In practical applications, many different orientations of digital line segments must typically be considered. In this paper, we (1) review efficient sequential as well as parallel algorithms for the computation of linear openings and closings, (2) compare the performance of CPU implementations of four state-of-the-art algorithms, (3) describe GPU implementation of two recent efficient algorithms allowing arbitrary orientation of the line segments, (4) propose, as the main contribution, an efficient and optimized GPU implementation of linear openings, and (5) compare the performance of all implementations on real images from various applications. From our experimental results, it turned out that the proposed GPU implementation is suitable for applications with large, industrial images, running under severe timing constraints.

Related projects: