مجال
التميز
|
تميز دراسي و بحثي + جائزة تفوقية
|
|
|
البحوث المنشورة
|
|
البحث (1):
|
|
عنوان البحث:
|
Robust human silhouette extraction with
Laplacian fitting
|
رابط إلى البحث:
|
Click
here
|
تاريخ النشر:
|
16/06/2014
|
موجز عن البحث:
|
Human silhouette extraction has been a primary step to estimate
human poses or classify activities from videos. While the accuracy of human
silhouettes has great impact on the follow-on human pose/gait estimation, it
has been important to guarantee the highly-accurate extraction of human
silhouettes. However, traditional methods such as motion segmentation can be
fragile due to the complexity of real-world environment. In this paper, we
propose an automated human silhouette extraction algorithm to attain this
highly-demanded task. In our proposed scheme, the initial motion segmentation
of foreground objects was roughly computed by Stauffer’s background
subtraction using Gaussian mixtures, and then refined by the proposed Laplacian
fitting scheme. In our method, the candidate regions of human
objects are taken as the initial input, their Laplacian matrices are
constructed, and Eigen mattes are then obtained by minimizing on Laplacian
matrices. RANSAC algorithm is then applied to fit the Eigen mattes
iteratively with inliers of the initially estimated motion blob. Finally, the
foreground human silhouettes are obtained from the optimized matte fitting.
Experimental results on a number of test videos validated that the
proposed Laplacian fitting scheme enhances the accuracy in
automated human silhouette extraction, exhibiting a potential use of our
Laplacian fitting algorithm in many silhouette-based applications such as
human pose estimation.
|
البحث ( 2):
|
|
عنوان البحث:
|
Deployment of CCTV in Saudi Arabia:
Security, Culture and Religion
|
رابط إلى البحث:
|
Click here
|
تاريخ النشر:
|
04/11/2015
|
موجز عن البحث:
|
Deployment of CCTV surveillance systems has now become a
worldwide practice for securing people and businesses alike. A common goal of
all CCTV surveillance systems is to detect crime and disorder in a timely
manner, enabling the law enforcers to possibly prevent it from happening. The
effective deployment of CCTV in Saudi Arabia is of particular interest to
researchers and decision-makers as in addition to the usual cons and pros,
cultural and religious factors do severely hinder its effective implementation.
In particular, as prescribed in the sharia law, men or women are not allowed to take
picture/video or acquire picture/video; hence making it very hard to argue in
favour of the case for CCTV systems. Based on a simple model of cost-benefit
analysis, this study attempts to evaluate the social costs and returns
associated with the deployment of CCTV surveillance systems in both public
and private places across the country. In so doing, the research has focused
on a case study of a large public hospital in Riyadh as a pilot case for
evaluation of effectiveness of use of CCTV. Using a large sample of doctors,
nurses, workers and patients of the hospital, the study has produced a
structured questionnaire survey. The preliminary findings are indicative of several
main issues. Firstly, due to lack of education on the part of some patients
and workers, over 52% of such participants declared that they had no
knowledge about the potential usefulness of the CCTV surveillance in crime
reduction. Secondly, a significantly large number of doctors and nurses
declared that they were fully supportive of the surveillance systems as they
believed it would help reduce theft and provide a safe and secure environment
for them to work. Thirdly, although over 50% of participants tend to believe
that CCTV systems can help reduce crimes, they were concerned that the staff
in charge of such CCTV systems may abuse the power and hence jeopardise the
true effectiveness of the system. Finally, according to the initial findings
of the study, it is anticipated that there would be more CCTV systems in
place in Saudi Arabia as the issue of security tends to overshadow other
cultural and religious issues.
|
|
|
البحث (3):
|
|
عنوان البحث:
|
Robust off-line text independent writer
identification using bagged discrete cosine transform features
|
رابط إلى البحث:
|
Click
here
|
تاريخ النشر:
|
08/11/2016
|
موجز عن البحث:
|
Efficient writer identification systems
identify the authorship of an unknown sample of text with high confidence.
This has made automatic writer identification a very important topic of
research for forensic document analysis. In this paper, we propose a robust
system for offline text independent writer identification using bagged
discrete cosine transform (BDCT) descriptors. Universal codebooks are first
used to generate multiple predictor models. A final decision is then obtained
by using the majority voting rule from these predictor models. The BDCT
approach allows for DCT features to be effectively exploited for robust hand
writer identification. The proposed system has first been assessed on the
original version of hand written documents of various datasets and results
have shown comparable performance with state-of-the-art systems. Next, blurry
and noisy documents of two different datasets have been considered through
intensive experiments where the system has been shown to perform
significantly better than its competitors. To the best of our knowledge this
is the first work that addresses the robustness aspect in automatic hand
writer identification. This is particularly suitable in digital forensics as
the documents acquired by the analyst may not be in ideal conditions.
|
|
|
جوائز التكريم:
|
|
الجائزة (1):
|
|
مسمى الجائزة:
|
Letter
of Merit
|
الجهة المانحة:
|
American
Academic & Scholarly Research Centre
|
تاريخ منح الجائزة:
|
30/05/2015
|
مجال التكريم:
|
Distinguished
Novel Contribution to Scientific Research and the Scientific Community
|
|
|
الجائزة (2):
|
|
مسمى الجائزة:
|
CESS
Innovation Prize 2016
|
الجهة المانحة:
|
Northumbria University
|
تاريخ منح الجائزة:
|
13/01/2017
|
مجال التكريم:
|
Best CESS Lab. presentation and innovation competition and the
CESS reward (an academic research book of a value of up to £200)
|
|
|
الجائزة (3):
|
|
مسمى الجائزة:
|
Best Paper Presentation
|
الجهة المانحة:
|
Ontario College for Research and Development
|
تاريخ منح الجائزة:
|
20/03/2017
|
مجال التكريم:
|
Best Paper Presentation at the International Conference on
Social Science, Arts, Economics and Education 2017
|