Variational Based Image Inpainting Methods by using
Cellular Neural Networks
Professor Alexandru Gacsadi
Electronics Department, University of Oradea
Str. Universitatii, No. 1, 410087, Oradea
Abstract: Image inpainting is an interpolation
problem where an image with missing or damaged parts is
restored. The most often used image inpainting
applications are for pictures or films known or damaged
partially. Discarding some unwanted parts, text or
objects from the whole image space, special effects can
be carried out using image restoration.
Complex mathematical models based on partial
differential equations (PDE) or variational computing
were proposed as techniques for restoring damaged or
partially known images. Those methods are computational
expensive and difficult to implement, even when a large
serial processing computing power is available.
The Cellular Neural Networks (CNN) based parallel
processing ensures computing-time reduction if the
processing algorithm can be implemented on a
continuous-time analogue CNN-UM (Cellular
Neural/Nonlinear Networks Universal Machine) or using
FPGA implemented emulated digital CNN-UM. Even if
variational computing methods are used, the design of
CNN templates ensuring the desired processing of the
gray-scale image remains an important step.
In the present paper, some variational based CNN methods
are presented and analyzed that can be used for the
reconstruction of damaged or partially known images.
Efficiency of these impanting methods can be enhanced by
combining them with nonlinear template that ensures the
growth of the local properties spreading area along with
Brief Biography of the Speaker:
Alexandru Gacsadi received the M.Sc. and the Ph.D.
degree in Electronic Engineering and Telecommunications,
both from the “Politechnica” University of Timisoara,
Romania, in 1986 and 2001, respectively. Since 1991 he
is with the University of Oradea, Romania, and currently
he is a professor at the Electronics Department of the
Electrical Engineering and Information Technology
Faculty responsible for teaching data acquisitions,
cellular neural networks applications and robotics.
His research interests are in the area of neural
networks, cellular neural networks and its applications,
image processing and analysis with applications in
medical imaging, processing and analysis of biomedical
data, smart transducers, and robotics.
He has published more than 70 papers in national and
international journals, conferences, workshops and
symposium proceedings, authored 3 books and 5
application guides. He conducted or acting as active
member for more than 15 research and development
projects, grants and contracts in his field of interest.
Professor Alexandru Gacsadi has been involved in setting
up national and international conferences as a reviewer
and/or member of organizing committee. He is a member of
the: IEEE Society (CAS), Society of Electronic Engineers
from Romania and Romanian Society for Industrial