• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.657-660
• /
• 2006

자연영상이나 스팸메일 영상으로부터 텍스트 영역을 추출하고 추출한 텍스트 영역에 이진화를 수행하고 나면 가로 방향이나 세로획 방향으로 놓여 있는 "1" 그리고 "ㅡ" 에 해당하는 한글의 종성부분이 이미지 내의 잡영을 지울 때 종종 지워지는 결과를 볼 수 있다. 이렇게 지워진 획 부분을 되살리기 위한 방법으로 텍스트 Hinting 알고리즘을 제안한다. 텍스트 Hinting 알고리즘은 이진화된 이미지의 텍스트 픽셀 위치와 동일한 좌표에 해당하는 원본 이미지의 RGB 값을 추출하여 추출된 텍스트 후보 영역의 색상을 알아낸다. 추출된 텍스트 색상 레이어 이미지와 이진화된 이미지에 OR연산을 수행하게 되면 지워진 획 부분을 복원할 수 있다. 제안한 방법을 스팸 이미지에 적용한 결과 텍스트 추출결과를 획기적으로 개선할 수 있음을 보였다.

• Digital Contents
• /
• no.9 s.112
• /
• pp.52-59
• /
• 2002

인터넷의 보급과 함께 세계적으로 문제가 되고 있는 것 중의 하나는 바로 스팸메일이다. 따라서 각 국은 스팸메일에 대한 법적 규제를 통해 사용자의 피해를 줄이기 위해 노력하고 있다. 본고는 일본의 경우 스팸메일에 대한 법적 규제를 고찰하고 있다. 또한 일본에서 신규제정된 법과 구법을 비교고찰 함으로써 법률의 변화를 살펴보고 있다. 우리나라의 법적 규제와 비교 및 참고가 되기를 바라면서 본지에 게재한다.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.1-7
• /
• 2007

Since the DirectTV started its digital broadcasting services in 1994 for the first time in the U.S., digital broadcasting widened its services in many areas. In korea, TIT(Transport Information Technology) based IP-TV services have been provided in Saemaeul trains and some sections of subway trains. But the software systems for the service performed in alternated fashions and suffered from many problems such as suspension, memory leaking and overflow. These problems increased playback loss time and resulted in bad reliabilities. In this paper, a software TIT monitor is designed and implemented for the TIT system in physically poor environments. The designed system formalized monitoring time intervals for effective monitoring. Through the real experiments, playback time is improved in 14% comparing to existing system.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1393-1399
• /
• 2019

With the rapid growth of the Internet, millions of indiscriminate advertising SMS are sent every day because of the convenience of sending and receiving data. Although we still use methods to block spam words manually, we have been actively researching how to filter spam in a various ways as machine learning emerged. However, spam words and patterns are constantly changing to avoid being filtered, so existing machine learning mechanisms cannot detect or adapt to new words and patterns. Recently, the concept of Lifelong Learning emerged to overcome these limitations, using existing knowledge to keep learning new knowledge continuously. In this paper, we propose a method of spam filtering system using ensemble techniques of naive bayesian which is most commonly used in document classification and LLML(Lifelong Machine Learning). We validate the performance of lifelong learning by applying the model ELLA and the Naive Bayes most commonly used in existing spam filters.

• Journal of Industrial Convergence
• /
• v.19 no.6
• /
• pp.37-47
• /
• 2021

Today, people share information and communicate with others using various information and communication media such as e-mail, smartphones, SNS, etc. However, it is being used in malicious attacks to send a large amount of illegal spam or to use it for fraud by using illegally collected personal information and devices that are vulnerable to security. Illegal spam, smishing, and fraudulent mail(SCAM) cause a lot of direct and indirect damage to companies and users, including not only social costs such as mental fatigue, but also unnecessary consumption of IT infrastructure resources and economic losses. Although there are regulations related to spam, violators of the law are still on the rise by circumventing the law, and victims are constantly occurring, so it is necessary to review what the problem is. This study examined domestic and foreign spam-related regulations and spam-related response activities, identified problems, and suggested improvement countermeasures. Through this study, it was intended to suggest directions for improving spam-related systems in order to block illegal spam and prevent fraudulent damage.

• Journal of Advanced Navigation Technology
• /
• v.15 no.2
• /
• pp.287-297
• /
• 2011

As electronic mails are being widely used for facility and speedness of information communication, as the amount of spam mails which have malice and advertisement increase and cause lots of social and economic problem. A number of approaches have been proposed to alleviate the impact of spam. These approaches can be categorized into pre-acceptance and post-acceptance methods. Post-acceptance methods include bayesian filters, collaborative filtering and e-mail prioritization which are based on words or sentances. But, spammers are changing those characteristics and sending to avoid filtering system. In the case of Korean, the abnormal usages can be much more than other languages because syllable is composed of chosung, jungsung, and jongsung. Existing formal expressions and learning algorithms have the limits to meet with those changes promptly and efficiently. So, we present an methods for recognizing Korean abnormal language(Koral) to improve accuracy and efficiency of filtering system. The method is based on syllabic than word and Smith-waterman algorithm. Through the experiment on filter keyword and e-mail extracted from mail server, we confirmed that Koral is recognized exactly according to similarity level. The required time and space costs are within the permitted limit.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.2
• /
• pp.61-75
• /
• 2009

Modern day people can easily use an e-mail client for general communication, because of using Internet and cellular phone. The mail client for the purpose of private and business affair, advertisement, news searching, and business letter is widely used and has side effects. People could send an important document via an electronic mail client. It is important to support an e-mail client intelligent. We think that many kinds of techniques of natural language processing must be provided in the client with human's emotion. We consider to design a new mail client with six kinds of senders' emotional information; delight, angry, sad feeling and message to express, manner of talking, a discomfort index etc. Before sending an e-mail, we suggest a user to correct a bad word because we do not want to feel bad to a receiver. We present a proper process of sending/receiving for users with a new designed e-mail clients.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.576-579
• /
• 2009

The amount of incoming e-mails is increasing rapidly due to the wide usage of Internet. Therefore, it is more required to classify incoming e-mails efficiently and accurately. Currently, the e-mail classification techniques are focused on two way classification to filter spam mails from normal ones based mainly on Bayesian and Rule. The clustering method has been used for the multi-way classification of e-mails. But it has a disadvantage of low accuracy of classification. In this paper, we propose a novel multi-way e-mail classification method that uses PCA for automatic category generation and dynamic category hierarchy for high accuracy of classification. It classifies a huge amount of incoming e-mails automatically, efficiently, and accurately.

• Journal of Information Technology Services
• /
• v.2 no.1
• /
• pp.25-34
• /
• 2003

Spam mail is one of the side effect of the development and improvement of the internet that restrains the privacy of the individual on line. However indiscriminate application of Spam mail blocking can also cause significant violation on freedom of doing business to the fluent commercial transactions on line. Therefore this research looks at the exact understanding of the concept of Spam mail and inquiry on Its issues. Also it looks at the case studies of its institutional solutions in USA and Europe as well as the advantage and disadvantage of the case studies on its technical solution. Finally, the research inquires into overall prevention of Spam mail, which considers both technical and institutional soiution. With this research, limitations of current Spam mail prevention system and technology are pointed out and more effective course of overall Spam mail prevention solution is studied.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.1238-1241
• /
• 2007

웹 게시판 서비스에서의 비정상행위 탐지 및 블러킹 방안 제시는 서비스를 제공하는 주체에게는 대량의 광고성 게시글로부터 안정적 서비스 운영이 가능하게끔 하고, 서비스를 이용하는 사용자에게는 원하지 않는 게시글로부터 블러킹 방안을 제공 받아 깨끗한 웹 게시판 서비스를 가능한 방안으로 인터넷 환경이 제공되면서 필터링 기술 발전 수준이 가장 높은 스팸 메일 필터링 기술을 응용하여 웹 게시판 서비스에 적용하여 필터링 효과 수준을 측정하고 다른 웹 서비스 등에 활용할 수 있는 방안을 제시한다.