• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.1
• /
• pp.75-81
• /
• 2016

The main characters play leading roles in novels. In the previous studies, they recognize the main characters in a novel mainly based on dictionaries that built beforehand. In English, names begin with upper cases and are used with some words. In this paper, we propose a recognition method for main characters name in Korean novels by using predicates, rules and weights. We first recognize candidates for the characters name by predicates and propose some rules to exclude candidates that cannot be characters. We assign importances for candidates, considering weights that given by the number of candidates appeared in a sentence. Finally, if the importance of the character is more than a threshold, we decide that the character is one of main characters. The results from the experiments for 300 novels show that an average accuracy is 85.97%. The main characters name may be used to grasp relationships among characters, character's action and tendency.

• The Korean Publising Journal, Monthly
• /
• s.95
• /
• pp.4-5
• /
• 1991

기존의 대하소설들이 취하고 있는 것과 비슷한 시기의 민중들의 삶을 담아낸 "먼동"은, 그러나 그것들과는 변별되는 특징을 지닌다. 이 작품의 등장인물들은, 설혹 중심인물이라 할지라도 철저하게 평범한 민초로서의 보평성을 벗어나지 않는다. "먼동"에는 한 개인의 두드러진 행적의 묘사가 없다.

• (The)Study of the Eastern Classic
• /
• no.63
• /
• pp.83-113
• /
• 2016

This paper is focused on objective and meaning of its compilation through reviewing system, composition, method of description, and content of "Jwagyebudam". "Jwagyebudam" has all round form of a history and character book by recording via arranging figures from the end of 16th century to the middle of 18th century in a chronological order. Figure were not only assigned at close range by steretyping people into groups to a degree in it, but also recorded in a chronological order. In view of method of description, "Jwagyebudam" concentrated a theme by recording via separating different people associated from a figure and content of the same event by using the same method like 'Hogeonbeom(互見法)' shown in "Sagiyeoljeon(史記列傳)". In addition, it obtained effect to objectify evaluation of figures included. In a method of embodying figures, it has described concretely and in a three dimensions figures by recording anecdotes and poems associated with them via focusing on lifelong characteristic aspect of corresponding figures. In other words, "Jwagyebudam" can be called by biographies or character books, writings specialized in characters center among writings of method to weave freely experience. In a broad sense, it can be called a writing to cover a function of history book, poem and picture. This was located to a starting point of variation of inclusive and descriptive method. Namely, several kinds of writings in late Joseon dynasty can show aspect to fulfill specialized aspect gradually.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.147-148
• /
• 2014

The analysis of the various settings for modal Composition used for characterization of the characters in an epic movie. We set the mode along the role of the profession, gender of the characters in the movie. The mode is used, from Gregorian chant. Analysis reveals the Dorian, Phrygian, Lydian, Mixolydian, Aeolian, Locrian, Ionian character of the seven total Mode how the character is portrayed in the characters for each Mode specificity. The analysis of the reasons for the musical approach and the nature of the characters cited for Mode a portion of Plato's [Republic].

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.4
• /
• pp.163-168
• /
• 2005

In this paper, we propose a character-based summarization algorithm using speaker identification method from the dialog in video. First, we extract the dialog of shots containing characters' face and then, classify the scene according to actor/actress by performing speaker identification. The classifier is based on the GMM(Gaussian Mixture Model) using the 24 values of MFCC(Mel Frequency Cepstrum Coefficient). GMM is trained to recognize one actor/actress among four who are all trained by GMM. Our experiment result shows that GMM classifier obtains the error rate of 0.138 from our video data.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.127-141
• /
• 2012

With the help of information technology for a film, characteris both the composition of the story and one of the most important elements that lead the story. Character has a close relationship with personality description, and the character's age, background, education, and occupation help decide his or her personality. Charades are important in that by describing a character's psychology using charade techniques, it gives a stronger impression than by describing with merely lines or narration. When a man's thought changes, their behavior changes; when a behavior is repeated, it becomes habit; when a habit is repeated, it becomes nature. The nature is the person's personality, otherwise called character. Therefore, charade techniques describe a character's psychology well, and consequently, it has maintained its importance. Because human nature and in-depth psychological description have a connection with a character's personality development, I would like to discuss the topic through this research. By using Director Shunji Iwai's "April Story" as the text, the effects of charade techniques on a character's personality development in film will be analyzed by seeking and presenting the methodology shown within the work through charade-acting techniques used by the characters for the development of character's personality.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.3
• /
• pp.119-126
• /
• 2013

In this paper, we propose and describe the system to visualize the story of contents such as movies and novels. Character-net is applied as story model in order to visualize story. However, it is the form to be accumulated for total movie story, though it can depict the relationship between characters. We have developed the system that analyzes and shows the variation of Character-net and characters' tendency in order to represent story variation depending on movie progression. This system is composed by two windows that can play and analyze sequential Character-nets by time, and can analyze time variant graph of characters' degree centrality. First window has a function that supports to find important story points like the scenes that main characters appear or meet firstly. Second window supports a function that track each character's tendency or a variation of his tendency through analyzing in-degree graph and out-degree. This paper describes the proposed system and discusses additional requirements.

• The Journal of the Korea Contents Association
• /
• v.14 no.9
• /
• pp.64-75
• /
• 2014

This study has attempted to explore the audience's visual attention about the subtitles types of CATV entertainment program. To achieve this, this research has measured the dwell time and average fixation data through the eye-tracking test and analysed the reason of particular visual attention by in-depth interview. According to the eye-tracking research findings, four types of subtitles(character metaphor, character metonymy, event metaphor, event metonymy) were measured the highest dwell time and average fixation time. Also, according to in-depth interview, visual attention was clearly turned up that event metonymy constructs the conflicts between characters and overstates the trip place romantically. This results means that staffs of intensify the reality and visual pleasure through event metonymic subtitles.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.219-220
• /
• 2017

영화 장르에 있어 등장인물의 전형적인 이미지는 매우 중요한 관객 수용의 요인이 될 수 있다. 하지만 그럼에도 불구하고 영화 장르별 등장인물의 이미지 표현방법에 대한 관객 인식유형의 연구는 현재까지 많이 이루어지지 않고 있다. 이에 본 연구는 질적방법론 중 하나인 Q방법론을 사용하여 영화 장르 내 캐릭터이미지의 전형성에 대한 수용자의 주관적 감정의 상태를 유형별로 분석해 보았다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.523-525
• /
• 2003

방송 프로그램이나 영화와 같은 동영상을 인터넷에서 검색하는 서비스가 활성화됨에 따라 특정 인물이 등장하는 부분을 검색하는 기능은 일반 사용자나 프로그램을 만드는 제작자 모두에게 필요한 기능이 되었다. 등장인물 중심의 검색을 위해서는 해당 인물의 얼굴 검출 및 인식 기능이 필수적이며, 특히 방송영상의 특성에 적합하고 등장인물 검색 서비스에 적용 가능한 얼굴 검출 및 인식 기술이 요구된다 이를 위해 본 논문에서는 고속 얼굴 인식 시스템을 제안하고, 실시간 수행이 가능한 얼굴 검출 및 인식 알고리즘을 제안하다. 제안한 얼굴 검출 및 인식 알고리즘은 DCT 기법을 전처리 단계로 두어 계산량을 최소화하면서도 특징값의 정보량은 유지하는 방법을 사용한다. 본 논문에서는 제안하는 알고리즘이 기존 방법에 비해 우수한 성능을 보이며, 실제 방송 영상을 구현된 시스템에 적용하여 시간과 검출률/인식률 측면에서 우수한 결과를 나타냄을 보인다.