Janarbek's Research page

Home | Research | Projects| Classes | Some fun stuff

Bio
I am a PhD student in my third year at Computer Science and Engineering department of UCSD. My advisor is Prof. Ryan Kastner. Before joining to the UCSD, I was working at Electronicsd and Telecommunications Research Institute in South Korea between 2007 and 2009. Betwen 2005 and 2007, I was a Master student at KAIST-ICC (formerly known as Information and Commnunications University) in South Korea. In 2000~2004, I was a undergrad student at Computer and Management School of Mongolian University of Science and Technology (MUST) where I majored in Computer Science.

Research
My current research interests are image processing, parallelising image processing algorithms on FPGA, GPU and multi-core. Previously, I have done some work on networked Robotics and Web services area. Below are some of my publications.

Janarbek Matai, Ali Irturk and Ryan Kastner, "Design and Implementation of an FPGA-based Real-Time Face Recognition System", IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM), May 2011 - Acceptance Rate: 42/119 = 35.3% BibTeX
Ali Irturk, Janarbek Matai, Jason Oberg, Jeffrey Su and Ryan Kastner, "Simulate and Eliminate: A Top-to-Bottom Design Methodology for Automatic Generation of Application Specific Architectures" , IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 30, issue 8, August 2011 BibTeX
Hyun Min Do, Janarbek Matai, Young-Ho Suh, Yong-Shik Kim, Bong Keun Kim, Hyoung-Sun Kim, Tamio Tanikawa, Kohtaro Ohba, Jae-Yeong Lee, Wonpil Yu, Connection Framework of RT-Middleware and CAMUS for Maintaining Ubiquity between Two Ubiquitous Robot Spaces, Advanced Robotics, 23(12-13): 1703-1723 (2009)
Janarbek Matai, Young-Ho Suh, Hyuongsun Kim, Kang-Woo Lee, Hyun Kim, Integration framework for interoperability of distributed and heterogeneous robot middlewares, International Conference on Control, Automation, Robotics and Vision (ICARCV), 2008: 2337-2343 BibTeX
Hyun Min Do, Janarbek Matai, Young-Ho Suh, Yong-Shik Kim, Bong Keun Kim, Hyoung-Sun Kim, Tamio Tanikawa, Kohtaro Ohba, Jae-Yeong Lee, Wonpil Yu, Connection methodology for two ubiquitous robot spaces - connection of RT-Middleware and CAMUS, Advanced Intelligent Mechatronics (AIM) , 2008, China. BibTeX
Janarbek Matai, Dongsoo Han, Learning-Based Trust Model for Optimization of Selecting Web Services, Asia-Pacific Web Conference/WAIM 2007: 642-649 BibTeX
Dongsoo Han, Jisoo Song, Janarbek Matai,“ A Probability-Based Prediction Framework for Stress Identification”, The ninth IEEE International Conference on e-Health Networking, Applications & Services (IEEE Healthcom 2007), BibTeX

Projects

1. A Complete Face Recognition System

What is a complete face recognition system ? We define a complete face recognition system as a system which interfaces with a video source, detects all face(s) images in each frame, and sends only the detected face images to face recognition subsystem which in turn identifies the detected face images.
What does a Complete Face Recognition System includes? (Architecture)? It should have face detection module which detects face(s) in each frame, and face recognition module which identifies detected face images from detection module as a name or identity number. The overall architecture of a Complete Face Recognition System is shown in the following figure.

How is the system works?
Current system is implemented on a Virtex-5 FPGA. It has a camera which is attached to the FPGA board. The FPGA reads 640×480 size frame and stores in a blockRAM of an FPGA. Then the face detection subsystem detects faces in current frame. The face detection subsystem is based on Viola-Jones object detection algorithm and uses Haar features from OpenCV distribution. Detected face(s) are sent to the Face Recognition subsystem which identifies face as a person number. Based on the person number, we draw a box around the face in the frame which shows on the display. (1=blue=John, 2=Bob=green..etc). The face recognition subsystem uses Eigenface face recognition algorithm. The following picture shows current set-up of the system implementation.

Classes

Contacts