• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.881-883
• /
• 2015

실제적인 표정인식 응용에서는 테스트 시 등장하는 인물이 트레이닝 데이터에 존재하지 않는 경우가 빈번하여 성능 저하가 발생한다. 본 논문에서는 인물에 독립적인(subject-independent) 표정인식을 위한 얼굴특징을 제안한다. 제안방법은 인물에 공통적인 얼굴 근육 움직임(Action Unit(AU))에 기반한 기하학 정보를 표정 특징으로 사용한다. 따라서 인물의 고유 아이덴티티(identity)의 영향은 감소되고 표정과 관련된 정보는 강조된다. 인물에 독립적인 표정인식 실험결과, 86%의 높은 표정인식률과 테스트 비디오 시퀀스 당 3.5ms(Matlab 기준)의 매우 빠른 분류속도를 달성하였다.

• The Korean Publising Journal, Monthly
• /
• s.221
• /
• pp.16-17
• /
• 1997

대개 인물사진 속에서 인물의 시선은 카메라 시선과 일치하거나 거부하는 대결을 보인다. 그러나 책이 등장할 때 책 읽는 인물의 시선은 강렬하게 책 속에 파묻혀 있다. 책을 읽을 때의 시각적 경험이 생각보다 훨씬 강렬하고 진지한 것임을 말해주는 것이다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.624-632
• /
• 2022

Relationship networks such as an interpersonal relationship network or navigation route search can be expressed in graph form. However, as the amount of data increase, there is a problem that it is difficult to search for the desired data when it is displayed on one screen. In this paper, we propose a visualization method for searching for people, searching for the shortest path between people, and using graphs to express an interpersonal relationship network with many nodes. Unlike the search for the shortest path in the routing table, the shortest path in the interpersonal relationship network should be changeable according to the intension or importance of the researcher or user who is analyzing it. To this end, the BFS algorithm was modified to apply the characteristics of the interpersonal relationship network. For the verification of the results, the data in the character relationship information of the Korean Classics DB in the Korean Classics Translation Institute was used.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.169-178
• /
• 2009

There are various approaches that retrieve information from video. However, previous approaches have considered just object information and relationship between objects without story information to retrieve contents. To retrieve exact information at video, we need analyzing approach based on characters and community since these are body of story proceeding. Therefore, this paper describes video information retrieval methodology based on character information. Characters progress story to form relationship through conversations. We can analyze the relationship between characters in a story with the methods that classifies role grades and clusters communities of characters. In this paper, for these, we propose the Character-net and describe how to classify role grades and cluster communities at Character-net. And we show this method to be efficient.

• The Science & Technology
• /
• v.30 no.1 s.332
• /
• pp.32-34
• /
• 1997

1861년 대동여지도를 만든 김정호는 어디서 태어나 언제 죽었는지도 모르는 신비 속의 인물이다. 지금의 마포 근처에서 살았다는 김정호는 22첩으로 된 가로 3m, 세로 7m의 대동여지도를 목판으로 인쇄하여 펴낸 과학인물이다. 대동여지도는 지금의 16만분의 1지도와 비슷한 것으로 산, 하천, 고을, 길 등이 정확하게 표시되어 있다. 평생을 지도제작에 바친 그의 뛰어난 과학정신이 새롭게 평가되고 있다.

• Journal of Korean Library and Information Science Society
• /
• v.32 no.4
• /
• pp.283-302
• /
• 2001

Current states of Korean biographical databases are evaluated based on the dissatis faction factors identified by a user survey. currency, coverage, completeness, and variety of the Korean biographical databases are evaluated and compared with overseas biographical databases. The results of the analysis are given with problems and suggestions for the future improvements.

• (The)Study of the Eastern Classic
• /
• no.67
• /
• pp.69-104
• /
• 2017

This paper examines the aspect of the novel which appeared in the union of the male and female relationship of "OkSuki", one of the novels of the 19th century. "Oksuki" is a work focusing on the relationship between men and women. It takes a narrative structure based on the relationship. It shows various aspects of the relationship through the structure in which the pluralities of plural persons are repeated. Other events and illustrations, except for the talk, are both an occasion of the alliance and an auxiliary role. At the beginning of the work, the main character's parents are described in detail.By arranging the prophecies related to the relationship between the protagonist and the brothers, it suggests that subsequent narratives will flow into the center of the relationship. The male characters that make up the alliance are characteristically trained and have a good taste, and the Caines are colorfully colored. It is believed that the marriage pattern faithfully follows the medieval status order. The reason why the figure of the person who becomes his wife and the person of the concubine are set differently is because the image of the wife and the concubine are different from each other ideally. The characters who are going to be hungry are emphasized on the clause, efficacy, knowledge, and inner peace, and are actively involved in. On the other hand, conciliatory characters emphasize talent and craftsmanship, and their role is reduced after marriage. The wife is a person who has both Confucian culture and knowledge and is able to care for her husband and family well. Concultation is shaped as a person who can enjoy joyful life and emphasize more affection in relation with his wife.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.5
• /
• pp.73-85
• /
• 2020

This paper analyzes the types of characters in the drama by applying Gremas's Actantial model and Enneagram's character typology and examines how they are shaped. As the Korean Wave is important, it is necessary to study the type of characters and how to describe them. Character is the most important factor in the influence of drama. As a result of applying to the Actantial model, and the following results were obtained. The main subjects are Yu-jin Choi and Ko Ae-sin, the Helpers are many people helping the subject, the opponent is the pro-Japanese figures, the Sender is Gojong, and the recivers are the people of Joseon. Analysis results by personality type of Enneagram, it was found that the subjects are 3 and 5 type, the Helpers are various types, the opponent is 3 type, the Sender is 5 type, and the receivers all types. In the method of describing the subject, internal description (direct description) is used, and the other is only formed by indirect description. Some of the Helpers and the Sender are used an image-telling method to show the inside. However, the opponent is image-telling only to show indirectly. As a result, it was possible to confirm the differences and effects on the method of image-telling by character type.

• The Korean Publising Journal, Monthly
• /
• s.124
• /
• pp.4-5
• /
• 1993

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.131-138
• /
• 2013

In this paper, I propose and evaluate the method that classifies emotional type of characters with their emotional words. Emotional types are classified as three types such as positive, negative and neutral. They are selected by classification of emotional words that characters speak. I propose the method to extract emotional words based on WordNet, and to represent as emotional vector. WordNet is thesaurus of network structure connected by hypernym, hyponym, synonym, antonym, and so on. Emotion word is extracted by calculating its emotional distance to each emotional category. The number of emotional category is 30. Therefore, emotional vector has 30 levels. When all emotional vectors of some character are accumulated, her/his emotion of a movie can be represented as a emotional vector. Also, thirty emotional categories can be classified as three elements of positive, negative, and neutral. As a result, emotion of some character can be represented by values of three elements. The proposed method was evaluated for 12 characters of four movies. Result of evaluation showed the accuracy of 75%.