Optim Lett
DOI 10.1007/s11590-016-1031-7
ORIGINAL PAPER
A DC optimization-based clustering technique for edge
detection
W. Khalaf
1
· A. Astorino
2
· P. D’Alessandro
3
·
M. Gaudioso
4
Received: 27 July 2015 / Accepted: 30 March 2016
© Springer-Verlag Berlin Heidelberg 2016
Abstract We introduce a method for edge detection which is based on clustering
the pixels representing any given digital image into two sets (the edge pixels and the
non-edge ones). The process is based on associating to each pixel an appropriate vector
representing the differences in brightness w.r.t. the surrounding pixels. Clustering is
driven by the norms of such vectors, thus it takes place in R, which allows us to use
a (simple) DC (Difference of Convex) optimization algorithm to get the clusters. A
novel thinning technique, based on calculation of the edge phase angles, refines the
classification obtained by the clustering algorithm. The results of some numerical
experiments are also provided.
Keywords Classification · Clustering · DC optimization · Edge detection
The work has been partially supported by Project PON 01_01180 “Neurostar”.
B M. Gaudioso
gaudioso@deis.unical.it; gaudioso@dimes.unical.it
W. Khalaf
walaakhalaf@yahoo.com; walaa@deis.unical.it
A. Astorino
astorino@icar.cnr.it
P. D’Alessandro
pietrodalessandro@gmail.com
1
Computer and Software Engineering Department, College of Engineering, AlMystansiriya
University, Baghdad, Iraq
2
Istituto di Calcolo e Reti ad Alte Prestazioni - C.N.R., 87036 Rende (CS), Italy
3
ICT Sud, 87036 Rende (CS), Italy
4
D.I.M.E.S., Università della Calabria, 87036 Rende (CS), Italy
123