ICGST/GVIP Journal VOLUME={10}, ISSUE = {VI}, Decdember2010
ISSN: 1687-398X Print, 1687-3998 Online & 1687-4005 CD-ROM
Guest editors:
Pr. D. Mammass , Ibn Zohr University ( Morocco )
mammass@univ-ibnzohr.ac.ma
Pr. F. Nouboud, UQTR ( Canada )
nouboud@uqtr.ca
Pr. A. El Moataz, University of Caen ( France )
Abder.Elmoataz@greyc.ensicaen.fr
| @ARTICLE |
{P1151052911, |
| AUTHOR
= |
{Edouard
Auvinet and Franck Multon and Alain St-Arnaud and Jacqueline Rousseau
and Jean Meunier}, |
| TITLE
= |
{Fall
detection using body volume recontruction and vertical repartition
analysis}, |
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{With the life expectancy
increase, more and more elderly people risk to fall at home. In order
to help them living safely at home by reducing the eventuality of
unrescued fall, autonomous systems are developped. In this paper, we
propose a new method to detect falls at home, based on a multiple
cameras network for reconstructing the 3D shape of people. Fall events
are detected by analyzing the volume distribution along the vertical
axis, and an alarm is triggered when the major part of this
distribution is abnormaly near the floor which implies that a person
has fallen on the floor. This method is evaluated regarding the number
of cameras (from 3 to 8) with 22 fall scenarios. Results show 96% of
correct detections with 3 cameras and above 99% with 4 cameras and more},
|
NOTE=
|
{Fall detection, multiple cameras, 3D reconstruction, occlusion},
|
| PAGES= |
{1--5} } |
| @ARTICLE |
{P1151052912, |
| AUTHOR
= |
{Y. Benezeth and P.M. Jodoin and B. Emile
and H. Laurent and C. Rosenberger}, |
| TITLE
= |
{Human detection with a multi-sensors
stereovision system},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{In this paper, we
propose a human detection process using Far-Infrared (FIR) and daylight
cameras mounted on a stereovision setup. Although daylight or FIR
cameras have long been used to detect pedestrians, they nonetheless
suffer from known limitations. In this paper, we present how both can
collaborate inside a stereovision setup to reduce the false positive rate inherent to their individual use. Our detection method is based on
two distinctive steps. First, human positions are detected in both FIR
and daylight images using a cascade of boosted classifiers. Then, both
results are fused based on the geometric information of the sterovision
system. In this paper, we present how human positions are localized in
images, and how the decisions taken by each camera are fused together.
In order to gauge performances, a quantitative evaluation based on an
annotated dataset is presented},
|
NOTE=
|
{People
detection, Stereovision, Farinfrared},
|
| PAGES= |
{7--12} } |
| @ARTICLE |
{P1151052913, |
| AUTHOR
= |
{Ali
Idarrou and Driss Mammass and Chantal Soulé Dupuy and Nathalie
Valles-Parlangeau}, |
| TITLE
= |
{A generic Approach to the
Classification of Multimedia Documents: a Structures Comparison},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{Traditional systems of
digital documents process, exploit only the textual part of these
documents. This paper presents a generic method of structural
clustering of the multi-structured multimedia documents. The main
originality of this approach is its ability to take into account other
modality notably the image that is one of the basic components of
multimedia documents. The
method we propose provides a general framework for the classification
of multi-structured multimedia documents. In our clustering process,
the comparison of structures is based on a graph matching representing
these structures. We evaluate our approach on a corpus of multimedia
documents extracts from the INEX 2007 corpus. These experimental
results show the feasibility and interest of our approach}, |
NOTE=
|
{multimedia documents, image, classification, clustering,
similarity, graph matching},
|
| PAGES= |
{13--18} } |
| @ARTICLE |
{P1151052914, |
| AUTHOR
= |
{Khaled Loukhaoukha and Jean-Yves Chouinard
and Mohamed Haj Taieb}, |
| TITLE
= |
{Optimal image watermarking algorithm
based on singular value decomposition and lifting wavelet transform via
multi-objective
genetic algorithm optimization},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{In this paper, a new
optimal watermarking scheme based on singular value decomposition (SVD)
and lifting wavelet transform (LWT) using multi-objective genetic
algorithm optimization (MOGAO) is presented. The singular values of the
watermark is
embedded in a detail subband of host image. To achieve the highest
possible robustness without losing watermark transparency, multiple
scaling factors (MSF) are used instead of single scaling factor (SSF).
Determining the optimal values of the MSFs is a difficult problem.
However, to find this values a multi-objective genetic algorithm
optimization is used. Experimental results show a much improved
performance in term of transparency and robustness of the proposed
method compared to others methods}, |
NOTE=
|
{Digital watermarking, multi-objective optimization, genetic
algorithm, singular value decom-position, lifting wavelet transform},
|
| PAGES= |
{19--27} } |
| @ARTICLE |
{P1151052915, |
| AUTHOR
= |
{Marcin Grzegorzek and Marina Trierscheid and Dimitri Papoutsis and Dietrich Paulus}, |
| TITLE
= |
{3D Teeth Segmentation from Dentition Surfaces},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{In this paper, we present a multi-stage approach for
teeth segmentation from 3D dentition surfaces based
on a 2D model-based contour retrieval algorithm.
First, a 3D dentition model is loaded to the system
and a range image is created. Second, binarised
2D sectional images are generated and contours are
extracted. During several processing steps a set of
tooth contour candidates are produced and they are
evaluated. The best-fitting contour for each tooth
is refined using snakes. Finally, the 2D contours are
integrated to full 3D segmentation results. Due to
its excellent experimental results, our algorithm has
been applied in the practical realisation of a so-called
virtual articulator currently being developed for
dentistry. Today, only mechanical articulators are
applied in the dental practice. They are used in the
fabrication and testing of removable prosthodontic
appliances (dentures), fixed prosthodontic restorations
(crowns, bridges, inlays and onlays), and
orthodontic appliances. Virtual articulators are
supposed to simulate the same functionality, however,
in a much more flexible and convenient way},
|
NOTE=
|
{Teeth Segmentation, Active Contours,
3D Dentition Models, Virtual Articulator},
|
| PAGES= |
{29--35} } |
| @ARTICLE |
{P1151052916, |
| AUTHOR
= |
{S. Metari and F. Deschênes}, |
| TITLE
= |
{A novel polychromatic model for light dispersion},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{In computer vision, the majority of research works
covering the subject of vision through participating
media are based on the concept of single scattering
of light rays. Only few works deal with multiple scattering
and they do so under restrictive constraints.
In this paper we introduce a new multiple-scattering
based polychromatic model (PM) for vision through
participating media. This model involves two basic
concepts, namely attenuation and ambient illumination.
The resulting model can be applied to a wide
range of media. For instance, it can be devoted to the
modeling of atmospheric vision, underwater vision
and vision through misty glass. We show that it can
be used to accurately restore the original versions of
degraded images taken through atmosphere. Experimental
results confirm that the proposed model is
both in good agreement with the theory, and useful
in practice},
|
NOTE=
|
{Multiple scattering, participating media,
vision model},
|
| PAGES= |
{37--42} } |
| @ARTICLE |
{P1151052917, |
| AUTHOR
= |
{S. Verstockt and C. Hollemeersch and C. Poppe and P. Lambert and R. Van de Walle}, |
| TITLE
= |
{Multi-Sensor Fire Detection by Fusing
Visual and LWIR Flame Features},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{This paper proposes a feature-based multi-sensor fi re detector operating on ordinary video and long
wave infrared (LWIR) thermal images. The detector automatically extracts hot objects from the thermal images by dynamic background subtraction and
histogram-based segmentation. Analogously, moving objects are extracted from the ordinary video
by intensity-based dynamic background subtraction.
These hot and moving objects are then further analyzed using a set of ame features which focus on
the distinctive geometric, temporal and spatial disorder characteristics of ame regions. By combining
the probabilities of these fast retrievable visual and
thermal features, we are able to detect the re at anearly stage. Experiments with video and LWIR sequences of re and non- re real case scenarios show
good results and indicate that multi-sensor re analysis is very promising}, |
NOTE=
|
{fi re detection, multi-sensor, LWIR,
moving object detection, disorder analysis, histogram-based segmentetion, ame features},
|
| PAGES= |
{43--50} } |
| @ARTICLE |
{P1151052918, |
| AUTHOR
= |
{
Vivan Cho and Wm. Douglas Withers}, |
| TITLE
= |
{Circle Location by Moments},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| PAGES= |
{51-55} } |
| @ARTICLE |
{P1151052919, |
| AUTHOR
= |
{T. ZAKI and D. MAMMASS and A. ENNAJI and S. NICOLAS}, |
| TITLE
= |
{A generic model with radial basis for the indexing of the Arab documents based
on the semantic graphs},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{In this paper, we proposed a generic system for the
extraction of the elements index that appear within the
multilingual documents by extending the vectorial model
of Salton by a combination of the calculation of the TFIDF
with the formula of Okappi in order to identify the
relevant terms which characterize best document.
Indeed, we have proposed a new measure Okappi-
TFIDF-ABR which takes in consideration the concept of
semantic vicinity using a measure of similarity between
terms by combining the calculation of TF-IDF-Okapi
with a kernel approach (Radial Basis function).
Afin d'avoir une bonne indexation, nous nous sommes
basés sur les graphes sémantiques pour mettre en
évidence les connexions sémantiques entre termes, ainsi
nous avons utilisé un dictionnaire auxiliaire pour
augmenter la connexité du graphe ainsi construit et par
conséquent le poids sémantique des termes de l'index.
This indexing therefore provides a contextual and
semantic research, and our system showed a better
robustness especially for the documents written in Arab
language.},
|
NOTE=
|
{Document indexation, semantic graph,
semantic vicinity, dictionary, kernel function, okapi
formula, similarity, TF-IDF, vectorial model},
|
| PAGES= |
{57--63} } |
| @ARTICLE |
{P1151052920, |
| AUTHOR
= |
{Fattah Zirari and M’Bark Iggane and Driss Mammass and S. NICOLAS and Abdellatif Ennaji and F. Nouboud}, |
| TITLE
= |
{Text/Image separation in multistructured documents},
|
| JOURNAL
= |
{ICGST International Journal on Graphics, Vision and Image
Processing, GVIP}, |
| YEAR
= |
{2010}, |
| MONTH= |
{December}, |
| VOLUME
= |
{10}, |
| ISSUE
= |
{VI}, |
| ABSTRACT= |
{The separation of text / image is a major step in the
processing of multi-structured documents. It consists of
separating the document into two classes: text and image.
In this context, it is important to implement approaches
that can handle such documents.
This paper presents a new method of separating text /
image into a multi-structured document. The method
developed is based on statistical analysis of texture
coupled with a classification method of k-means. This is,
initially, to browse the document by a sliding window,
and calculate the texture parameters for each pixel, using
a method to extract features such as co-occurrence matrix
to obtain the characteristic vectors of the document. The
distribution of these vectors using the k-means algorithm
into two classes used to classify the pixels of the
document as part of the text or image. Examples within
the issue of separating text / image on newspapers
illustrate this article},
|
NOTE=
|
{co-occurrence matrix, texture, segmentation,
K-means, document image},
|
| PAGES= |
{63-73} } |
|
