• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.1009-1015
• /
• 2009

Handwriting verification is a technique of distinguishing the same person's handwriting specimen from imitations with any two or more texts using one's handwriting individuality. This paper suggests an effective verification method for the handwritten signature or text on the off-line environment using pattern recognition technology. The core processes of the method which has been researched in this paper are extraction of letter area, extraction of features employing structural characteristics of handwritten text, feature analysis employing DTW(Dynamic Time Warping) algorithm and PCA(Principal Component Analysis). The experimental results show a superior performance of the suggested method.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.380-384
• /
• 2000

Effectiveness of information conveyance in reading is affected by several factors such as line length, letter size, line spacing arrangement as well as typeface itself. This study examined relative importance of these factors by asking people to read the texts that was constituted with non-square form letter and rank the preference of texts through conjoint analysis. In the case of reading time, justification was the most important factor, followed by leading, line spacing, letter width, line length, font size, font type in their order of importance. And in the case of preference decision, letter width was the most important factor, followed by font size, justification, line spacing, leading, line length, font type. The result will be useful in understanding how to consider human preference in the hangul typography.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.1002-1013
• /
• 1996

The segmentation of characters is an important step in the automatic recognition of handwritten text. This paper proposes the segmenting method of off-line handwritten Hangul. The suggested approach is based on the structural characteristics of Hangul. The first step extracts the local features. connected component and strokes from the imput word. In the second step we identify the class of strokes. The third segmenting step specifies WRC(White Run Column) before consonant or horizontal vowel. If the segment is longer than threshold, the system estimates segmenting columns using the consonant-vowel information and column features, and then finds a cornered boundary along the strokes within the estimated segmenting columns.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.147-151
• /
• 2008

There are many attempts to transfer many applications from PC to mobile which has small screen, cause of a development of mobile technology. To display the whole information of the PC on the tiny screen, it makes many Horizontal Scroll, Horizontal Scroll in mobile screen makes people to miss where they are reading easily and such a frequent error makes readability of the information in mobile screen low. We suggest a Line Marker to help readability of the mobile screen high. This study shows the relationship between the conditions of Line Marker such as fixed or moved or not exists and the factors of the reading time and satisfaction.

• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1121-1130
• /
• 2004

This paper proposes a method for line and word segmentation for machine-printed text blocks. To separate a text region into the unit of lines, it analyses the horizontal projection profile and performs a recursive projection profile cut method. In the word segmentation, between-word gaps are identified by a hierarchical clustering method after finding gaps in the text line by using a connected component analysis. In addition, a special symbol detection technique is applied to find two types of special symbols tying between words using their morphologic features. An experiment with 84 text regions from English and Korean documents shows that the proposed method achieves 99.92% accuracy of word segmentation, while a commercial OCR software named Armi 6.0 Pro$^{TM}$ has 97.58% accuracy.y.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04b
• /
• pp.1495-1498
• /
• 2002

한국현재의 컴퓨팅환경은 Text위주의 Command Line상에서의 입출력에서 GUI(Graphic User Interface)환경으로 전환되었다. 이는 사용자에게 좀더 친근한 방법으로의 컴퓨팅환경을 제공하고 있는 것이다. 하지만 아직까지 그러한 환경에 익숙해지기 위해서는 많은 습득시간이 필요하며 또한 응용프로그램간의 인터페이싱 기능 등을 익히기 위해서는 추가적인 학습을 통해야 원활한 작업을 수행할 수 있다.이를 해결하고자 본 연구는 음성인식/ 합성과, 현재 음성마크업 언어인 VoiceXML 등을 통해서 모색해보고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.646-648
• /
• 2004

컴퓨터와 인터넷의 급속한 보급으로 인해 원격교육(Distance Learning)에 대한 많은 연구가 진행되고 있다. 그러나, 지금까지 대부분의 원격교육 시스템은 웹 기반의(Web-Based) 비동기(asynchronous) 형태로써 피교육자가 이미 제작된 컨텐츠를 다운로드하여 보는 단순한 형태의 교육방식이다. 따라서, 전통적인 면대면(Face-to-Face) 교육방식을 대체할수 있는 원격교육이 되기 위해서는 교육자와 피교육자, 피교육자와 피교육자간에 인지(awareness) 및 상호작용(interaction)이 가능한 원격교육의 기능이 지원되어야 한다. 본 논문에서는 비디오 및 오디오 컨퍼런싱(video and audio conferencing), 텍스트 기반 대화(text-based chat), 선 밀 텍스트 애노테이션이 가능한 슬라이드(slide with line and text annotation)를 제공하고 피교육자에 대한 인지정보(awareness information)를 공유하는 동기식 세미나용 원격교육 시스템을 설계하고 구현하였다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.10
• /
• pp.120-129
• /
• 1996

This paper presents an efficient block segmentation and classification using the edge information of the document image. We extract four prominent features form the edge gradient and orientaton, all of which, and thereby the block clssifications, are insensitive to the background noise and the brightness variation of of the image. Using these four features, we can efficiently classify a document image into the seven categrories of blocks of small-size letters, large-size letters, tables, equations, flow-charts, graphs, and photographs, the first five of which are text blocks which are character-recognizable, and the last two are non-character blocks. By introducing the clumn interval and text line intervals of the document in the determination of th erun length of CRLA (constrained run length algorithm), we can obtain an efficient block segmentation with reduced memory size. The simulation results show that the proposed algorithm can rigidly segment and classify the blocks of the documents into the above mentioned seven categories and classification performance is high enough for all the categories except for the graphs with too much variations.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.37 no.2
• /
• pp.186-201
• /
• 2013

This study investigates the effects of information type, direction of information, method of suggestion, tie strength, and interactions among these variables on the acceptance and diffusion of fashion product information in the mobile Facebook environment. Two subsequent studies were conducted to test the relationships among mobile SNS WOM factors. Two independent on-line surveys were implemented. Six hundred forty consumers aged between 20 and 39 were recruited for Study 1, and four hundred and eighty for Study 2. We manipulated the WOM delivery situation by information type (factual/evaluative), information directionality (positive/negative), tie-strength (strong/weak), and information presentation method (text/image/rink). Eight scenarios were developed and randomly assigned to the research participants. Frequency analysis, reliability, factor analysis, regression analysis, and ANOVA were implemented using SPSS 18.0. The Analysis of experiment data produced interesting results. Most WOM factors (including the information type, information presentation method, and tie strength) influence WOM acceptance; however, only the tie strength effected WOM activity. It was also proven that people are prone to accept information that is more realistic, objective, and negative, and they tend to accept information with visual factors, such as images and video clips rather than a simple text message. In this study, we offer a practical perspective to fashion industry and marketers who have an interest in SNS marketing. We have defined the distinct characteristics of mobile WOM that have been formed by a combination of former on/off-line WOM characteristics. To examine the moderating roles of two types of consumer innovativeness, fashion innovativeness and technology innovativeness were also measured and found to have significant moderating effects between mobile SNS WOM factors and their consequences. The paper concludes with a discussion on managerial implications and limitations.

• Journal of Information Processing Systems
• /
• v.8 no.3
• /
• pp.521-538
• /
• 2012

As the knowledge society matures, not only distant, but also off-line universities are trying to provide learners with on-line educational contents. Particularly, high effectiveness of mobile devices for e-Learning has been demonstrated by the university sector, which uses distant learning that is based on blended learning. In this paper, we analyzed previous m-Learning scenarios and future technology prospects. Based on the proposed m-Learning scenario, we designed cellular phone-based educational contents and service structure, implemented m-Learning system, and analyzed m-Learning service satisfaction. The design principles of the m-Learning service are 1) to provide learners with m-Learning environment with both cellular phones and desktop computers; 2) to serve announcements, discussion boards, Q&A boards, course materials, and exercises on cellular phones and desktop computers; and 3) to serve learning activities like the reviewing of full lectures, discussions, and writing term papers using desktop computers and cellular phones. The m-Learning service was developed on a cellular phone that supports H.264 codex in 3G communication technology. Some of the functions of the m-Learning design principles are implemented in a 3G cellular phone. The contents of lectures are provided in the forms of video, text, audio, and video with text. One-way educational contents are complemented by exercises (quizzes).