|
|
|
|
|
Dr. Napoleon H. Reyes,
Ph.D. h: 83
Circumferential Road, e: [email protected] w: www.reyesnap.uni.cc |
||
|
|
||
|
Qualifications |
||
|
Recipient
of high distinction award in Ph.D. in Computer Science with extensive
background in real-time color-based object recognition system (FIRA robot
soccer) design and development. Articulate
in communicating complex ideas to others with 8 years of teaching experience
at De La Salle University, Fluent in
English and Pilipino. |
||
|
|
||
|
Education |
||
|
Ph.D. in Computer Science |
May 2004 |
|
|
De La Salle University, |
|
|
|
|
|
|
Master of Science in Computer Science |
Sept. 1999 |
|
|
De La Salle University, |
|
|
Developed an Expert System-Neural Network Hybrid System and
tested it on a popular benchmark data set called DNA Promoter Recognition
problem.
|
|
|
|
Bachelor of Science in Physics with
Specialization in Computer Applications |
Sept. 1993 |
|
|
De La Salle University, |
|
|
|
|
|
|
High School Diploma |
Mar. 1989 |
|
|
Notre Dame of Greater 12PthP Ave., Grace
Park, |
|
|
|
|
|
|
|
||
|
Professional Experience |
||
|
Assistant Professor 4 |
2002-2003 |
|
|
De La Salle University, |
|
|
Helped in setting-up a Beowulf cluster system for
bioinformatics researches, and in
conducting colloquiums and meetings.
Helped in managing and directing the Physics Society’s activities
all-year round. |
|
|
|
Assistant Professor 3 |
(2001-2002) |
|
|
Assistant Professor 2 |
(2000-2001) |
|
|
Lecturer 2 |
(1999-2000) |
|
|
Lecturer 1 |
(1997-1999) |
|
|
Assistant Lecturer |
(1995-1997) |
|
|
De La Salle University, |
|
|
|
|
|
|
Product Design Engineer (Special Projects Group) |
1993-1994 |
|
|
Vision 8 Systems, Inc., #11 Manuela Apartelle, |
|
|
|
|
|
|
|
||
|
Journal Publications |
||
|
||
|
||
|
||
|
|
||
|
Conference Proceedings |
||
|
·
N. H. Reyes, E. P. Dadios,
(2003). Machine Vision Using Fuzzy Logic, Proc. of the 2003 International
Conference on Instrumentation and Control, Nov. 27-28, 2003, Heritage
Hotel, Manila, Philippines. |
||
|
·
N. H. Reyes, E. P. Dadios,
(2003). Combining Fuzzy Techniques in Color Object Detection, Proc. of
First Humanoid, Nanotechnology, Information Technology, Communication and
Control Environment and Management (HNICEM) International Conference, |
||
|
·
N. H. Reyes, E. P. Dadios,
(2002). A Fuzzy Approach in Color Object Detection, Proc. of 2002 IEEE
International Conference on Industrial Technology, |
||
|
·
N. H. Reyes, E. P. Dadios,
(2002). Color-based Fuzzy Vision System for the FIRA Robot Soccer Game, Proc.
of 2002 FIRA Robot World Congress, COEX, Seoul, Korea, pp. 684-687, May
26-29, 2002. |
||
|
·
E.A. Maravillas, N. H.
Reyes, E. P. Dadios, (2002). Fuzzy Logic Scorer for
FIRA Robot Soccer Game, Proc. of 2002 FIRA Robot World Congress, COEX,
Seoul, Korea, pp. 684-687, May 26-29, 2002. |
||
|
·
N.H. Reyes, A.P. Azcarraga,
Towards a High-Level Hybrid System of Neural Classifiers, Proc. of the First
Philippine Computing Science Congress (PCSC) 2000, Angelo King
International Center, Manila, Philippines, Nov. 29-Dec.1, 2000. |
||
|
|
||
|
Other Conferences and Seminars |
||
|
Oral Presentor
Philippine Instrumentation and Control Society (PICS)
Technical Seminar 2002 Philippine
|
||
|
Oral
Presentor
2nd Foundation Anniversary of
the International Rice Research
Institute (IRRI), Munoz, Nueva Ecija
|
||
|
Oral
Presentor
First Philippine Computing
Science Congress (PCSC) 2000
|
||
|
Oral
Presentor
2nd Annual Science and
Technology Conference De La Salle University,
|
||
|
Invited
Speaker
Hybrid Systems in Medicine St. Luke’s
|
||
|
Resource Speaker
“Hands-on Computer Literacy
Training” for the De La Salle University
|
||
|
Participant
Philippine Council for Health Research and Development (PCHRD) 20th
Anniversary Celebration. “Bioinformatics: Advancing Biotechnology, Securing our People’s
Health” Manila Midtown Hotel, Ballroom B, Pedro Gil, Ermita, |
||
|
|
||
|
Awards, Memberships, Certificates |
||
|
·
High distinction award (GPA: 4.0/4.0) in Ph.D. in Computer
Science, De La Salle University, |
||
|
·
Member, (FIRA) Federation of Robot-soccer Association,
Philippine Team |
||
|
·
Member, Computer Society of the |
||
|
·
Recipient, Ph.D. in Computer Science full-tuition
scholarship through faculty development of De La Salle University, |
||
|
·
Recipient, M.S. in Computer Science full-tuition
scholarship through faculty development of De La Salle University, |
||
|
·
Dean’s Lister, 2PndP term, SY 1989-1990, B.S. in Physics with specialization in
Computer Applications, De La Salle University, |
||
|
·
First Place Winner, 1990, College of Science Week
Poster-making and Slogan Contest, De La Salle University, |
||
|
·
First Place Winner, 1990, Linggo
ng Wika Poster-making and
Slogan Contest De La Salle University, |
||
|
·
Loyalty award, high school, Notre Dame of Greater Manila, |
||
|
·
Certificate of training, Fire Prevention and First Aid
Life Support and Water Safety Seminars ·
Driving license |
||
|
|
||
|
Computer Skills |
||
|
Software Visual C++ .NET, Visual C++ v.6.0, Visual
Basic.NET, Visual Basic v.6.0, Visual Basic for Applications, Matrox Imaging Library (MIL v.5.12), Borland C++ v.3.1,
Turbo C, Rahmonics Parallel C, Unix C, Turbo Pascal
v.7.0, Vax Pascal, MS Excel, MS-Access,
MS-PowerPoint, MS Windows 2000, XP, PaintShop Pro,
Adobe Photoshop 5.0, Adobe Illustrator 9.0, Macromedia Authorware. Some programs authored: Vision system for the Federation of
International Robot Soccer Association (FIRA) robot-soccer (Visual C++),
Expert-Neural Hybrid System (VB), Fuzzy Logic Engine (VB), Fuzzy-Logic System
for the Inverted-pendulum problem (VB), Back-Propagation Network Demo (VBA), Lidar cloud mapping system in C/C++, Database management
system for the Cytogenetics Laboratory, Philippine
General Hospital (MS-Access), Bank teller simulation (VB), Host-client
communication (TCP/IP Sockets programming, Unix C), Dining Savages Problem
(Multi-threading in C/C++), DOS-based GUI Engine (C/C++), Fractals (C/C++),
Physics simulations: Projectile motion, 3D Vector Addition, Free Fall
(VB,C/C++), Infix-to-postfix conversion (C/C++), Automated Exam (Excel, VBA) |
||
|
Hardware Micro-soccer robots, Real-time computer vision
system, IBM PC troubleshooting and assembly, INMOS Transputers,
Vax |
||
|
Fields
of Research Machine Vision, Pattern Recognition,
Intelligent Systems – Neural Networks, Expert Systems, Fuzzy Logic, Genetic
Algorithm, Hybrid Systems, Robotics, Control Systems, Graphical Modeling and
Simulation, Computational Physics and Game Programming. |
||
|
|
||
|
Career Highlights |
||
|
||
|
|
||
|
Personal Background |
||
|
Born on Interests: swimming, playing basketball, drawing and painting. Nationality: Filipino, I would need assistance in acquiring a Creative, resourceful, and independent. |
||
|
|
||
|
References |
||
Faculty, Physics Department Head, Laser, Lidar
Laboratory De La Salle University Email: [email protected] Contact.: +63 2 536 0229 (Physics Department) +63 2 524 4611 Local 424 (Laboratory)
Faculty, Department of Information
Communications Technology Email:
[email protected] Contact: +65 68704628 (Work) +65 90106520 (Mobile)
Researcher, Prof. Kasai's Laboratory,
Department of Applied Physics 2-1, Email:
[email protected]
Contact: +81 668584040 (Home) |
||
|
|
||
|
SELECTED
ABSTRACTS OF PAPERS |
||
|
The following is an abstract
of my Ph.D. dissertation: |
||
|
Abstract A novel indoor color-based object recognition algorithm is
presented in response to the challenges posed by the current machine vision
research status. Previous researches found that current color constancy
techniques are inadequate in dealing with color object recognition. Furthermore, researches in the field of
fuzzy multi-channel color imaging are rather sparse. Contrary to color constancy algorithms, the
algorithm developed focuses on manipulating a color locus depicting the
colors of an object (mobile robot), and not stabilizing the whole image
appearance per se. The rationale behind the development of the new color
object recognition algorithm is inspired by recent findings in the neurophysiological aspect of the human visual system,
which suggests that contrast computation precedes segmentation. This research
contributes in the field of Color Science by providing a new set of color
descriptors that adheres to human perception of color, in a new transformed rg-chromaticity space. Moreover, this research extends
the computing prowess of Fuzzy Logic in the realm of multi-channel color
imaging by providing a new breed of gradually adaptive multi-channel fuzzy
color inferential filter for color locus constancy, called Reyes-Dadios Color Contrast Fusion (RDCCF). RDCCF utilizes a
new color contrast degrade operator that was originally mathematically
derived in this work, along with color contrast enhance. RDCCF is the first
of its kind in the family of “true” fuzzy inferential filters for tracking
down objects via color. The RDCCF algorithm locks on a color locus depicting
the target object, while accurately compensating for the effects of glare,
and hue and saturation drifts. Experiments on color spotting similar
(hue-related) colors show that the new color descriptors and RDCCF combined,
is better than using rectangular and pie-slice decision regions in UV space.
In addition, this research provides an algorithm for recognizing mobile
robots even in the event of collisions. Also, this work presents an algorithm
for predicting the position of the ball. Empirical results of the application
of the color-based object recognition algorithm on the robot soccer game
attest to its robustness under spatially varying illumination intensities,
multiple light sources, presence of highlights, object rotation and
collision, in real-time. Keywords: dynamic color object recognition, rg-chromaticity
space, color constancy, contrast operators, color descriptors, Fuzzy Logic. |
||
|
Apart from developing a real-time object recognition algorithm,
I have also previously worked on an Expert-Neural hybrid system as my M.S.
thesis. Using a transformational
approach; that is, breaking down a rule-based Expert System into its basic
elements (antecedent and consequent - including the operators and operands),
and transforming each piece into its Neural Network structure equivalent
(artificial neuron, weight, threshold, etc.), a hybrid system that addresses
the weaknesses of the two intelligent systems, and takes advantage of their
strengths is created. Consequently,
imperfect domain knowledge from an Expert System is inculcated into a Neural
Network that is faster to execute, and trainable for corrections. In this work, the DNA promoter recognition
problem served as my algorithm’s test bed.
My paper on this research is publicly available, and can be
easily downloaded from: http://citeseer.ist.psu.edu/462013.html. The following is an abstract of the paper: Abstract Neural Networks and Expert Systems are two complementary
approaches to building intelligent systems. Neural Networks lend themselves
naturally to learning, but can be quite obscure as to their basis for the
mapping they make of input patterns and output responses. Expert Systems, on
the other hand, are particularly attractive in terms of being able to explain
the basis for the diagnosis. This type of complementarity
gives rise to hybrid systems that combine Expert Systems and Neural Networks,
and such a system is described here. This system transforms a rule-based
Expert System into a multi-layered Neural Network, then refines the system
through training using live data. A
popular benchmarking problem for hybrid systems - the DNA promoter
recognition problem, serves to demonstrate the inner workings of the hybrid
system. Keywords: Expert Systems,
Neural Networks, Hybrid Systems, Explanation-based Systems, Empirical
Learning Systems. |
||