Tai-Yun Kim

Automatic text extraction in digital videos using FFT and neural network

Popular methods for extracting a text region in video images are in general based on analysis of a whole image such as merge and split method, and comparison of two frames. Thus, they take long computing time due to the use of a whole image. Therefore, this paper suggests the faster method of extracting a text region without processing a whole image. The proposed method uses line sampling methods, FFT and neural networks in order to extract texts in real time. In general, text areas are found in the higher frequency domain, thus, can be characterized using FFT. The candidate text areas can be thus found by applying the higher frequency characteristics to neural network. Therefore, the final text area is extracted by verifying the candidate areas. Experimental results show a perfect candidate extraction rate and about 92% text extraction rate. The strength of the proposed algorithm is its simplicity, real-time processing by not processing the entire image, and fast skipping of the images that do not contain a text.

Development of multimedia E-mail system providing an integrated message view

E-mail is the most popular method for information exchange through communication networks. As multimedia technologies are developed rapidly, networks need to support multimedia data. In order to transmit multimedia messages, MIME (Multipurpose Internet Mail Extensions) was proposed, but a multimedia message consisting of different media is not viewed as an integrated form. In this paper, a multimedia E-mail system has been developed according to the MIME standard in order to solve the limitations of multimedia message transmission. A redefined HTML (Hypertext Markup Language) syntax is applied to the E-mail system for the purpose of viewing a multimedia message as an integrated form. It allows users to understand a message better. The proposed E-mail system also provides convenient functions of message authoring and display for users.

Ticket based authentication and payment protocol for mobile telecommunications systems

In third generation mobile telecommunication systems such as UMTS, one of the important problems for value-added services is to check the recoverability of costs used by a mobile user. We present an efficient public-key protocol for mutual authentication and key exchange designed for value-added services in UMTS. The proposed ticket based authentication and payment protocol provides an efficient way for VASP to check the recoverability of costs without communication with the online TTP. Furthermore, the ticket based protocol can provide anonymous service usage for a mobile user.

Convertible undeniable signature scheme

In this study, a convertible undeniable signature scheme based on the El-Gamal signature scheme is proposed. The proposed scheme satisfies the undeniable property and can convert the undeniable signature to the ordinary one. The number of public keys and signatures are less than those of Boyars scheme (1991). It also reduces the number of communication steps of the signature confirmation protocol.

Generic Engineering Approach for Agent-Based System Development

It is necessary to support user-centric service provision paradigm in distributed, dynamic and complex computing environment. Software agent technology is considered as one of the technologies suitable to adopt such computing environment. Many researchers have emphasized on the necessity of agent technology, but the research on agent-based system development methodology is not sufficient. We propose the engineering approach for agent-based system development from problem domain modeling to design phase. We survey existing methodologies and extract considerations to improve them. Based on the considerations, we establish six steps in which modeling method and activities are systematically defined. Also we apply the proposed methodology to virtual example in order to show applicability of the methodology. The proposed methodology is more systematic and useful than existing methodologies. This methodology helps system engineer develop agent-based system and provides ideas to establish more complete methodology.

Connection management for QoS service on the Web

The current Web service model treats all requests equivalently, both while being processed by servers and while being transmitted over the network. For some uses, such as multiple priority schemes, different levels of service are desirable. We propose application-level TCP connection management mechanisms for Web servers to provide two different levels of Web service, high and low service, by setting different time-outs for inactive TCP connections. We evaluated the performance of the mechanism under heavy and light loading conditions on the Web server. Our experiments show that, though heavy traffic saturates the network, high level class performance is improved by as much as 25?28%. Therefore, this mechanism can effectively provide QoS guaranteed services even in the absence of operating system and network support.

A method for original image recovery for caption areas in video

It is sometimes necessary to remove the captions from video images already broadcast and recover the original images. Traditional research on image restoration has focused on restoring blurred images to sharp images using frequency filtering. This paper proposes a method for extracting caption regions and a method for automatically recovering original. The caption region detection method extracts caption candidate regions using TF (topographic feature) of characters, and verifies candidate regions to determine the final caption regions. From the result of caption region detection, we know the start and end frames of captions in video and the character areas in the caption regions. For original image recovery, we use information such as the start and end frames of the detected caption, camera operation, scene change and motion vector of extracted characters in caption regions. The direction for the recovery is decided using information on the scene change, the start and end frame for captions. According to the direction, we recover the original image using information of camera operation and Block Matching Algorithm (BMA) for character components in extracted caption region. Experimental results show that the case of stationary images having little motions is well recovered. We see that the case of images having motion in complex background is also recovered.

Design of key recovery system using multiple agent technology for electronic commerce

When a receiver of a cipher text message cannot decrypt the message due to the fact that he has lost his private-key, the private-key of the receiver and session-key of the message need to be recovered. In this paper, the authors design a new n-way key recovery system (n-KRS) that is characterized by a key encapsulation approach, n-way key recovery, secret designation of key recovery agents, fork and join of session-key with random keys, recovery request by a new key pair, certificate attaching scheme, component based software engineering and conformance to international standards. n-KRS is specified and analyzed by an extended cryptographic timed Petri net (ECTPN) model that is a new formal and graphical specification model for cryptographic protocols. Recoverability, performance characteristics of n-KRS are evaluated by means of a reachability graph of ECTPN. A prototype of n-KRS is developed and evaluated by means of a CC 2.0 based information security system evaluation scheme.

Text extraction in videos using topographical features of characters

Traditional character extraction methods use split-and-merge or color segmentation methods from the whole image. These methods do not reflect characteristics of characters such that character regions can be extracted incorrectly. In this paper, we use topographical features of characters to extract the character points and use the density of those points to extract the candidate regions for captions. Character regions are determined by testing several conditions and verifying those candidate regions. Experimental results show that the candidate region extraction rate is 100%, and the character region extraction rate is 99%. Non-character regions can exist within the extracted character regions which are removed using the Isodata color clustering method.

Integrated multimedia e-mail handler with authoring tool

Multipurpose Internet mail extensions (MIME) were proposed for the transmission of multimedia messages. Multimedia e-mail information can be transmitted by the proposed MIME format. However, an integrated environment for authoring multimedia e-mail has not been provided, until now. Using both a multimedia e-mail handler and integrated authoring tool, advanced private communication can be accomplished. In this study, the integrated multimedia e-mail handler and authoring tool has been designed and implemented according to the MIME standard in order to solve the bounded e-mail system environment limitations of media messages. The multimedia e-mail authoring tool is designed and applied to the multimedia e-mail handler for the purpose of viewing a message consisting of different media as an integrated form. It provides users with an environment for understanding e-mail messages. The proposed e-mail system also provides convenient functions of message authoring and display for users.