• Trans-
• /
• v.3
• /
• pp.29-53
• /
• 2017

The film scholar Vincent Amiel divides into three types of montage through his book The Aesthetics of Montage ; Montage narratif, Montage discursif, and Montage decorrespondances. These three categories are the concept that encompasses the aesthetic class to which most movies belong. Early films pursued the essential and basic functions of editing, which tend to be modified in the direction of enhancing the director's goals over time. In this way, "Expressive Montage" is one of most important concepts of montage, not as a 'methodology' that combines narrative but as a 'purpose'. In the montage stage, the expressive montage work is done through three steps of decision. The process of 'combining' to combine the selected films in a certain order, after the process of 'selection' which selects only necessary parts of the rush film, and 'connection' to determine the scene connection considering the duration of the shot. The connection is the final stage of the montage. There are exceptions, of course. When fiction films of classical narratives use close-ups, or when using models or objects of neutered animals, the film induces the tendency of a "montage decorrespondances" rather than a "montage narratif" or "montage discursif". This study attempts to analyze the tendency of montage of works with 'uncertain connection' through 'collage' used by close-ups and montage decorrespondances as 'fragmentation tendency of modern films'. The fragmentation of the montage in contemporary film breaks the continuous and structural nature of the film, and confuses the narration structure that is visible on the surface of the film. The tendency of the fragmentation of the montage, which started from this close-up, seems to give an answer to the extensibility of the modern image.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.453-458
• /
• 2006

본 연구에서는 몽타주와 얼굴사진의 유사도를 산출하여, 유사도에 따라 얼굴사진의 순위를 정하는 방법을 제안한다. 먼저, 얼굴부위를 눈썹, 눈, 코, 입, 이마 등 27개로 나누고, 부위별 특징은 196개로 분류한다. 눈 부위의 특징을 예로 들면, 쌍꺼풀, 외꺼풀, 큰 눈, 작은 눈, 동그란 눈, 긴 눈, 처진 눈, 치켜 올라간 눈 등으로 분류할 수 있다. 나아가서, 200명의 얼굴사진 각각에 대해 특징을 분류하여, DB로 구축한다. 임의의 얼굴에 대해 몽타주를 작성하고, 몽타주에 대한 특징을 선택하여, DB의 얼굴 사진과 유사도를 산출하여, 순위를 정한다. 10명의 얼굴에 대해 몽타주를 작성하고, DB의 얼굴사진을 유사도에 따라 순위를 정한 결과, 1위 $\sim$ 6위 사이에 동일인물이 검색되었으며, 평균은 1.9위이었다. 이 결과는 몽타주를 작성하여 200매 얼굴의 유사도 순위를 정하면, 평균적으로는 2위에서, 적어도 6위 이내에서 동일 얼굴을 검색할 수 있다는 의미이다. 몽타주를 이용한 수사는 몽타주를 배포하여 시민의 신고에 의존하는 수동적인 방법을 사용하고 있으나, 이 방법을 이용하면, 용의자를 압축하여 검거하는 능동적인 수사가 가능하다.

• Review of Korea Contents Association
• /
• v.17 no.4
• /
• pp.19-21
• /
• 2019

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.83-90
• /
• 2013

This study attempts interpretation of vertical montage expressed in assoziation montage focused on animation, Paprika. Montage has been continuously studied by Pudovkin, Eisenstein, Jacques Aumont and others till now. However, existing studies focused on the visual image of montage. Image is made of visual element and aural element. These two interact with each other and maximize the effect. It is believed that the study subject can be approached in more depth, if aural elements would be analyzed based on the assoziation montage which analyzed visual image in previous studies. Accordingly, this study explores and analyzes how vertical montage has been used in logical montage and optical conflict montage and what meanings they generated. The analysis results suggested followings. In logical montage and optical conflict montage, vertical montage complemented visual image by natural concurrence as a whole. Vertical montage also showed linked relationship, which reflects overall emotion by melodious concurrence. In addition, when there was melodious concurrence at certain time, place or unclear space, the elements showed continuity which made them link with relationship. However, when the role that cuts that continuity, in other words, when the tonal element, which let audience partially immerse, would be properly used when the space and time would change or get reversed, the effect was maximized. It also expressed a turning point of an event and enhanced the concentration of audience on the characters.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.497-501
• /
• 2010

A software montage means information that can be extracted quickly from software and includes inherent characteristics. If a montage is made from well-known programs, we can filter candidates of similar programs among the group of programs based on the montage. In this paper, we suggest software montages based on two characteristics: API calls and strings. To evaluate the proposed montages, we performed experiments to filter candidates of some similar programs to instant messenger programs. From the experiments, we confirmed that the proposed montages can be used as a forensic tool that filters a group of similar programs even when their functions are not known in advance.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.121-129
• /
• 2009

This research tries to interpret Montage der Assoziation shown in animations. Eisenstein's 'Montage' is "Montage der Assoziation" where a variety of Montage pieces are combined, symbolizing one aggregate image. Though influenced by Russian Formalist Film Theory and Kuleshov, Pudivkin and Rudolf Amheim, by contraries, he recognized Montage as an issue between an artist and the audience and an anti-representation apparatus. Especially, he developed the mind action issue previously advocated by Eikhenbaum and deemed the audience's role an essential part in completing a film. Montage expression implied in Eisenstein's theory can be regarded as attraction, collision, and dynamic and intellectual Montage. However, with an in-depth approach, Montage der Assoziation can be interpreted by repetitive, relative and juxtaposed analysis. The reason is that animation Montage is a visual action which takes place in a row among scenes and in the frame. This research addresses communications with the audience which are attained by Montage der Assoziation. In other words, this research makes an in-depth access to how Montage der Assoziation appears and communicates with the audience in an animation work.

• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.102-109
• /
• 2013

The purpose of this study is to express imagination which is not limited to the description of the facts and reproduce the photos as a media to explore the new possibilities for creative expression and the experience of the day-to-day operations for the implementation of the scheme of art genre. The art work for this study using digital images in Autodesk Combustion Workspace as the upper and lower layers were synthesized using the Transfer Mode feature. This study proposed a new photomontage production model, and challenged for the Possibility of a variety of visual representations of media art. Especially the production presents in this study can be applied to various video.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.559-564
• /
• 2002

본 논문에서는 범죄수사의 초동수사 기법으로 사용되고 있는 몽타주와 실물 사진과의 근사 영상 검색 알고리즘을 제안한다. 입력 몽타주를 얼굴인식 기법에 적용하여 이진영상화와 형태학적 필터로 영상의 잡음을 제거한 후 경계선을 추출하였다. 추출된 경계선 영상으로 레이블링 과정을 거친 후 얼굴의 중요 요소를 포함하는 특징얼굴을 구성한다. 특징얼굴은 웨이블릿 변환을 통해 다운 샘플링 된 LL대역의 계수로 변환되며, 고유값 연산을 통해 계수 매트릭스의 고유 값을 추출 한다. 입력 몽타주의 고유값은 같은 절차를 거친 실물 사진의 저장된 고유값과 계수의 분포를 비교한다. 실험 결과 몽타주와 유사한 실물 사진을 검색할 수 있었으며 영상의 크기 변화와 왜곡 및 압축에 견고한 비교 검색 결과를 얻었다.

• Cartoon and Animation Studies
• /
• s.9
• /
• pp.199-219
• /
• 2005

This paper is studying about how things are showed the montage theory and mis-en-scene effect in the screen media, what the concrete project's cases and how those theories have been supported to the animation's effects and its development. Besides, 1 tried to describe the shown things in the animation area, what the montage theory and mis-en-scene effect had been imported and expressed based on the screen studies of representative genre in the visual media. The purpose of this thesis suggests to help the creative animation scenes by liberal understanding and acceptance about the montage theory and mis-en-scene effect for the future animation's progressive aspect. With the improvement, there this thesis's suggestions could help the creative and special effects of animation asa part of Screen Arts, and would be the part of the progressive factors in the animation area.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.