• Journal of architectural history
• /
• v.15 no.2
• /
• pp.163-170
• /
• 2006

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.123-126
• /
• 2020

딥러닝이 정답을 찾아가는 연구과정이라면 미술은 정답이나 오답의 단정적 결과보다는 미추(아름다움과 추함)를 포함하는 과정적, 창조적 행위에 가깝다고 할 수 있다. 다시 말하면 미술은 0과 1로만 환원할 수 없는 세계를 기술하여 감동을 주는 유기적 규칙이 내재되어 있고 때로는 과학이 만들어낸 결론을 뒤집는 반상식적 추론을 하기도 한다. 그러므로 딥러닝은 예술적 방식을 통하여 과학의 상식적 추론과의 좋은 거리(Fine distance)를 유지할 필요성이 있는데, 이를 위해서 기존 딥러닝의 이미지 생성과 관련하여 Distance, Classification, Optimization 등의 문제를 미술 표현 기법과 목적이 담겨있는 창작자의 Statement 키워드와의 유사성과 차이점을 비교 분석할 필요가 있다고 생각한다. 시각적 표현과 관련된 딥러닝의 성능은 아직 사람의 표현능력에 못 미치고 있어 본 논문에서는 콜라주 기법에 의한 비디오 생성을 위한 탐색적 실험 분석을 목적으로 GAN을 활용한 콜라주 비디오를 제작하고 그 문제점과 개선점을 제안하고자 한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.6
• /
• pp.86-92
• /
• 2010

This paper proposes a new steganography scheme based on frequency domain using various image frames and collages that can protect the copyright of digital contents for users and securely perform to exchange the security information in the digital communication environments. The main idea of our proposed scheme is that the security informations related its copyright embed into the frequency domain of the image frame and collages when a user decorates the original image by using various image frames and collages. The strengths of our proposed scheme are as follows: (1) It allows to freely control the quantity of embedded information by changing the number of image frames and collages. (2) It is secure to variety image distortion attacks. (3) It maintains high PSNR(Peak Signal to Noise Ratio). As a result, the proposed steganography scheme can be used practically diverse multimedia security fields such as digital copyright protect, secure message communication and digital watermarking.

• The monthly packaging world
• /
• s.335
• /
• pp.82-89
• /
• 2021

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.297-302
• /
• 2022

Contemporary viewers familiar with the digital space show their desire for self-expression and use voice, text and gestures as tools for expression. The purpose of this study is to create interactive art that expresses the narrative uttered by the viewer in the form of a collage using the viewer's figure, and reproduces and expands the story by the viewer's movement. The proposed interactive art visualizes audio and video information acquired from the viewer in a text collage, and uses gesture information and a natural user interface to easily and conveniently interact in real time and express personalized emotions. The three pieces of information obtained from the viewer are connected to each other to express the viewer's current temporary emotions. The rigid narrative of the text has some degree of freedom through the viewer's portrait images and gestures, and at the same time produces and expands the structure of the story close to reality. The artwork space created in this way is an experience space where the viewer's narrative is reflected, updated, and created in real time, and it is a reflection of oneself. It also induces active appreciation through the active intervention and action of the viewer.

• Cartoon and Animation Studies
• /
• s.39
• /
• pp.365-391
• /
• 2015

The purpose of this study is to comprehend the characteristics of collaborative examples in mobile games by analyzing the types of cultural fusion and their utilization in mobile game industry. The major examples of collaborations include the collaborative works utilizing artists, characters, and products by examining the practical collaborations within international mobile games between the years 2010 to 2014. The most typical kind of collaboration among them is the utilization of characters, composed of using characters between games, applying animation characters, borrowing cartoon or web-cartoon characters, hiring famous celebrities, or even including great men in their games. Therefore, the characteristics of mobile game's collaborative types are confirmed as below by studying the above examples. (1) There are many examples of collaborating between different types of businesses defined as 'conversion type fusion.' (2) The character utilization is the most sought after type of collaboration. (3) The applied content's target audience seems to share the same age groups of the game's audience. (4) The game industry always adopts the components that could be recognized instantly. (5) The status and influence of mobile game have risen greatly. Consequently, this research has important role in establishing the strategic collaborative plans for mobile game business by expanding the prospects of game related researches and industrial and academic theories.

• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 2007.10a
• /
• pp.45-50
• /
• 2007

• 대한지구과학교육학회:학술대회논문집
• /
• 2010.08a
• /
• pp.17-18
• /
• 2010

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.39-60
• /
• 2021

In the field of deep learning, there are many algorithms mainly after GAN in research related to generation, but in terms of generation, there are similarities and differences with art. If the generation in the engineering aspect is mainly to judge the presence or absence of a quantitative indicator or the correct answer and the incorrect answer, the creation in the artistic aspect creates a creation that interprets the world and human life by cross-validating and doubting the correct answer and incorrect answer from various perspectives. In this paper, the video generation ability of deep learning was interpreted from the perspective of collage and compared with the results made by the artist. The characteristic of the experiment is to compare and analyze how much GAN reproduces the result of the creator made with the collage technique and the difference between the creative part, and investigate the satisfaction level by making performance evaluation items for the reproducibility of GAN. In order to experiment on how much the creator's statement and purpose of expression were reproduced, a deep learning algorithm corresponding to the statement keyword was found and its similarity was compared. As a result of the experiment, GAN did not meet much expectations to express the collage technique. Nevertheless, the image association showed higher satisfaction than human ability, which is a positive discovery that GAN can show comparable ability to humans in terms of abstract creation.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.721-731
• /
• 2022

The purpose of this study is to examine and categorize the cases of luxury fashion brands and art collaboration and find out their effects. The research method examined the theoretical background of luxury fashion brand and art collaboration and proceeded with content analysis through major cases. The research results were classified into the following two types through case analysis. The first is art collaboration for product design, and the second type is art collaboration for exhibition works. Content analysis according to type was organized from the perspective of brands and artists, respectively, and the resulting collaboration effect was finally derived. The main effects are the integration of design and art, diversification of social and cultural backgrounds, and innovative vision of expression. This study is meaningful in examining the expanded design methods and effects of luxury fashion brands through grafting artworks and presenting basic data for future fashion art collaboration design research.