Jong-Gook Ko

Iris Recognition using Cumulative SUM based Change Analysis

Iris recognition has received increasing attention recently. Compared with other biometric features such as fingerprint and face, iris patterns are more reliable and stable. Iris recognition includes iris imaging, iris segmentation and iris recognition and so on. This paper focus on the iris feature extraction in iris recognition system. And this paper proposes novel and efficient iris recognition method that employs cumulative SUM based grey change analysis. Experimental results show that proposed method can be used for human identification in efficient manner

Design of Embedded Multimodal Biometric Systems

The embedded devices in biometrics have gained increasing attention due to the demand for reliable and cost-effective personal identification systems. However, the current available embedded devices are not suitable for the real-time implementation of a biometric application system because of the limited computational resource and memory space. In this paper, we describe the design of embedded biometric systems that identify person by using face-fingerprint or iris-fingerprint multimodal biometrics technology. To implement real-time system, the biometric algorithms are efficiently enhanced for fixed-point representation and optimized for memory and computational capacity. In addition, the most time consuming components of each biometric algorithm are implemented in a field programmable gate arrays (FPGA).

Rectified Trajectory Analysis Based Abnormal Loitering Detection for Video Surveillance

Trajectory analysis for detection of abnormal loitering has attracted significant research interest in recent years. We present a new approach for abnormal loitering detection using trajectory analysis. Trajectory Direction History Analysis method is proposed to detect abnormal loitering and Inverse Perspective Mapping (IPM) is presented to resolve distortion of trajectory direction because of perspective effect. Proposed loitering detection method has shown good performance.

Iris Segmentation and Verification

Iris recognition includes eye imaging, iris localization and verification and so on. This paper proposes a novel method for iris localization based on mask template and an efficient iris verification that employs cumulative sum based grey change analysis. Experimental results show that proposed method can be used for human identification in efficient manner.

An immersive e-learning system providing virtual experience

This paper introduces immersive e-learning system which provides vivid learning experience using augmented reality(AR) technology. This system gives illusion that participants feel as if they are in foreign environment by synthesizing images of participants, virtual environment, foreign-language speakers in real-time. Furthermore, surrounding virtual environment reacts to the behavior of each participant including student, local teacher, remote teacher. The system has been installed along with 10 scenarios at 14 public elementary schools and conducted during regular class time. This paper presents our motivations for the system development, a detailed design, and its contents.

Hybrid Camera Based Real-Time Human Body Segmentation for Virtual Reality E-learning System

This paper proposes hybrid camera based video segmentation approach of human body for virtual reality e-learning system. Color and IR(Infra-red rays) image are used for human body segmentation at the same time. Human foreground pixels are separated from background in color and IR image respectively. And two foreground pixels are integrated as final foreground result for better performance of human body segmentation. Good foreground human segmentation is useful for virtual reality e-learning system.

H/W BASED FIREWALL FOR HIGH- PERFORMANCE NETWORK SECURITY

Recently, enterprises, service provider, and e-businesses confront increasing security and performance challenges. Securing network, host, and on-line application is absolutely important. At the same time, security function must not disturb productivity. To ensure that increasing network traffic is safe and their networks are secure, these organizations must provide security with bias toward solutions that accommodate performance demands, while providing the security and networking features required to run their businesses. That is, best solutions are those that combine high performance with topnotch security. For satisfying those requirements, we have developed hardware based and high performance Security Gateway System (SGS) which providing security functions such Firewall, IDS, Rate-limiting, and Traffic metering in wire speed. In this paper, we especially describe how H/W based Firewall features are implemented in SGS.