• 한국의류산업학회지
• /
• 제7권2호
• /
• pp.211-217
• /
• 2005

The purpose of this study is to analyze the image evaluation and the preference of tailored jacket focused on the variation of the length according to the body type and the degree of satisfaction with the body of middle-aged women. For this study, twenty seven different types of tailored jacket were designed with some variation of their silhouette, the length and the collar's figure on three hundred and twenty three middle-aged women ranging from 35 to 50 years old. There was a significant difference in the image evaluation and the preference of tailored jacket according to the body type of middle-aged women. The women of the body type I evaluated that tailored jackets of the long length were more attractive, graceful, and active, soft and preferred the style, and the women of the body type II and III, them of the middle length. The women of the body type I evaluated that tailored jackets of the short length were more attractive, graceful, active, soft and preferred the style. Also there was a meaningful difference in the image evaluation and the preference of tailored jacket according to the degree of satisfaction with their bodies. As satisfied with their face size, they thought tailored jackets of the long length were more attractive, graceful and active, soft and they preferred the style. As satisfied with the girth of the hip, they evaluated the short/long tailored jackets were more attractive, graceful and active, soft and they preferred the style. As satisfied with their height they valued the long tailored jacket was more attractive, graceful and active, soft and they preferred the style.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1447-1456
• /
• 2019

As artificial intelligence technology is actively used in image processing, it is possible to generate high-quality fake images based on deep learning. Fake images generated using GAN(Generative Adversarial Network), one of unsupervised learning algorithms, have reached levels that are hard to discriminate from the naked eye. Detecting these fake images is required as they can be abused for crimes such as illegal content production, identity fraud and defamation. In this paper, we develop a deep-learning model based on CNN(Convolutional Neural Network) for the detection of StyleGAN fake images. StyleGAN is one of GAN algorithms and has an excellent performance in generating face images. We experiment with 48 number of experimental scenarios developed by combining parameters of the proposed model. We train and test each scenario with 300,000 number of real and fake face images in order to present a model parameter that improves performance in the detection of fake faces.

• The International Journal of Costume Culture
• /
• 제7권1호
• /
• pp.1-16
• /
• 2004

Pop art, an artistic trend which was actively popular centering around popularization of America in the 1960's, appears as punk style in the 1970's and as one of diversified style in the 1980's, and have co-existed in the third culture and pluralistic combination since the 1990's. The image of pop art includes complexity, familiarity and popularity as well as extension of media, and so directly influences the fashion in the end of the 20th century. Especially, sportslook show up by the virtue of rising lower cultural area such as street fashion becoming influential and change in life style, which was recreated as clothes by developing characteristics of design including style, details and colors showed in active sports wear. This study is aimed to ana analyze the image of pop art showed again in the modern fashion in the end of the 20th century and graffiti-art which was well known to the general public after the 1980's. Through this analysis, I will study characteristics of pop art showed in sportslook which is the mainstream in modern fashion and graffiti of Keith Haring. Consequently, I suggested a functional, esthetic and future-oriented sports look design which comprises the image of the graffiti-art of Keith Haring by using Design CAD(photoshop & primavision) enabling to attempt variously and to derive quickly the output of design and textile.

• 스마트미디어저널
• /
• 제5권4호
• /
• pp.63-68
• /
• 2016

텍스처전이(Texture Transfer) 기법은 타겟영상의 고주파 성분인 텍스쳐를 소스영상에 적용시키는 영상처리 방법이다. 이 텍스쳐 전이기법은 입력 영상에 표현되고 있는 질감 등의 스타일을 대상 영상에 전이시키는데 사용 될 수 있다. 본 연구에서는 이러한 텍스쳐 전이기법을 비디오에 적용시키기 위한 방법을 제안한다. 특히 동영상에 적용시키기 위한 실시간 병렬 처리 알고리즘을 제안한다. 이를 위해서 기존 텍스쳐 전이기법에 사용되는 커널의 모양을 변경하여 병렬화가 가능하도록 하였으며, 동영상 적용 시 발생하는 시간적 일관성문제를 해결하기 위한 방법으로 비디오 프레임 영상의 다중해상도를 사용한 광류측정법을 제안하여 적용함으로써 실시간 비디오 처리를 가능하게 하였다.

• 한국BIM학회 논문집
• /
• 제14권2호
• /
• pp.13-24
• /
• 2024

This research suggests a novel visualization approach utilizing Generative AI to render photorealistic architectural alternatives images in the early design phase. Photorealistic rendering intuitively describes alternatives and facilitates clear communication between stakeholders. Nevertheless, the conventional rendering process, utilizing 3D modelling and rendering engines, demands sophisticate model and processing time. In this context, the paper suggests a rendering approach employing the text-to-image method aimed at generating a broader range of intuitive and relevant reference images. Additionally, it employs an Text-to-Image method focused on producing a diverse array of alternatives reflecting architects' styles when visualizing the exteriors of residential buildings from the mass model images. To achieve this, fine-tuning for architects' styles was conducted using the Low-Rank Adaptation (LoRA) method. This approach, supported by fine-tuned models, allows not only single style-applied alternatives, but also the fusion of two or more styles to generate new alternatives. Using the proposed approach, we generated more than 15,000 meaningful images, with each image taking only about 5 seconds to produce. This demonstrates that the Generative AI-based visualization approach significantly reduces the labour and time required in conventional visualization processes, holding significant potential for transforming abstract ideas into tangible images, even in the early stages of design.

• 한국의류산업학회지
• /
• 제14권5호
• /
• pp.701-712
• /
• 2012

This study examines the various expressions and immanent value of fashion and beauty style based on Craig Owens's Allegory theory. I analyzed four application elements of Borrow, Site Specificity, Accumulation of Strategy, and Hybridization in? Ladygaga's Music Videos. The results are as follows. 'Borrow' presents a kitsch style and playful Pop-art style, transformation of gender from Mini Mouse body suit, telephone headpiece, and can hair. 'Site specificity' presents the temporarity of fashion material through rebirth, aging, natural extinction from the chain over the black jump suit, crime scene tape, and skull-face makeup with masculine style. 'Accumulation of strategy' presents a futuristic chic fashion style from a layered style, retrospective fashion, repetition and duplication in Music Videos. It shows the physical beauty of an Asian warrior style in Poker Face. 'Hybridization' present Cyborg feminism and 'Will of Power' from iPOD LCD glasses and Pyro-Bra. The Pyro-Bra represents how the female body can be used as a weapon in the outfits of Lady Gaga. In addition, Immanent value is as follows. Textual interaction with high art is accomplished through a combination of contemporary social and cultural significance to understand the cultural code and to extend the value. Combined with high culture, popular music genre is accomplished through musical appreciation by a woman in fashion styling and sensual pleasures of the body as a tool to express a sublime advantage. Fashion style is accomplished by overcoming a self-transcendent body image representation. The way in which mutual coupling dismantling, destruction, and uncertainty is to re-launch the static, with a pluralistic context of Textuality.

• 방송공학회논문지
• /
• 제25권6호
• /
• pp.980-993
• /
• 2020

딥-러닝 기반 스타일 전이 기법은 영상의 고차원적 구조적 특성을 적절하게 반영하여 높은 품질의 스타일 전이 결과를 제공함으로써 최근 크게 주목받고 있다. 본 논문은 이러한 딥-러닝 기반 스타일 전이 방식의 안정적이고 보다 다양한 스타일 전이 결과 제공에 대한 문제를 다룬다. 스타일 전이를 위한 광범위한 초-매개변수 설정에 따른 실험 결과에 대한 고찰을 바탕으로 스타일 전이 결과의 안정성 및 다양성에 대한 문제를 정의하고, 이러한 문제를 해결하기 위한 부분 손실 정규화 방법을 제안한다. 제안된 정규화 방식을 이용한 스타일 전이는 입력 영상의 특징에 상관없이 초-매개변수 설정을 통해 동일 수준의 스타일 전이 정도를 조절할 수 있을 뿐 아니라, 스타일 손실을 정의하는 계층 별 가중치 설정의 조절을 통해 기존 방식과 달리 보다 다양한 스타일 전이 결과를 제공하며, 입력 영상의 해상도 차이에 대해 보다 안정적인 스타일 전이 결과를 제공하는 특징을 가진다.

• 한국콘텐츠학회논문지
• /
• 제10권4호
• /
• pp.76-83
• /
• 2010

본 논문에서는 입력된 실제 영상을 판화와 같은 느낌이 나는 영상으로 변환하는 기법을 제안한다. 즉 이 기법은 입력된 영상을 영상처리 기법을 이용하여 사람이 작업한 것과 같은 고무 판화 느낌이 나는 영상으로 변환한다. 먼저 원본 영상에서 윤곽선을 검출한 후 반전시키고, 잡음 성분의 선이나 점들을 제거하고, 선명화 처리를 하여 첫 번째 영상을 만든다. 다음, 첫 번째 영상과 유사한 방법으로 두 번째 영상을 만든 후, 마지막으로 논리곱을 이용하여 이 두 영상을 합성한다. 이와 같이 처리하여 고무판과 조각칼이 함께 만드는 효과를 표현한다. 또한, 외곽선 검출의 이중 적용이 선폭을 강화하고 잡음 성분의 미세 선을 제거 하는데 효과적임을 보인다.

• 한국의류학회지
• /
• 제33권3호
• /
• pp.500-510
• /
• 2009

The purpose of this study was to examine the effects of facing plan on store image and preference of young casual fashion store. The subjects were 545 male and female university students in Chungnam province. The measuring instruments were 7 stimuli manipulated by facing plan, an important VMD element, and self-administrated questionnaire consisted of store image, store preference and subject's demographic characteristics. The data were analyzed by t-test, ANOVA and Duncan's multiple range test, using SPSS program. The results were as follows. First, facing type significantly affected consumer' store image; folded type had more neat and elegant image than other facing types, and face out type had most comfort image, whereas sleeve out type had discomfort image. Second, arrangement of facing types also affected store image; style arrangement had more sophisticated image than color arrangement in sleeve out type, and vertical and horizontal arrangement had more neat, sophisticated, attractive and comfort image than separate arrangement in folded type. Third, facing type affected store preference; folded type showed higher store preference than sleeve out type. Forth, arrangement of folded type affected store preference; vertical and horizontal arrangement showed higher store preference than separate arrangement. Fifth, store image and preference were different by subject's sex; male subjects perceived style arrangement as more elegant, characteristic and attractive image, and showed higher store preference than female subjects on separate arrangement of folded type.

• 건축역사연구
• /
• 제1권2호
• /
• pp.68-84
• /
• 1992

The development of Buddhist architectures of the Unified Silla period have been generally understood to have paired pagoda instead of one which had been popular until before the unification. Besides the stylistic categorization of paired pagoda system, there had been no further investigation reported concerning whether there was any detailed process of change within the development of paired pagoda style. This paper aims to identify such change inside the development of paired pagoda style, which, externally, seems to be the same pattern of site design maintained throughout the period of Unified Silla that lasted for about three centuries. Since the temple sites of study are in the same pattern of layout, the method of investigation has to be such that can identify the subtle changes that, in external appearance, are not easily discernible. Hence, this research compared the dimensions of important measurement of five temple sites to be able to clarify the process of minor changes. Among many sites of Silla temples, only five were suitable for the research since detailed measurement were possible through field research or the report of excavation. They are the sites of Sachonwang-sa, Mangduk-sa, site of Kunsuri, and Bulguk-sa. Although the five sites have the same style of paired pagoda, it is clear that there were consistant flow of change. Even though the motivation of such change were not strong enough to change the site pattern itself, it resulted continuous minor changes such as the size and location of architectures. The size of image hall, for example, was growing larger and larger as time goes on, while, the size of Pagoda was getting smaller. In the same way, the size of middle gate became smaller while the size of lecture hall became larger, although the rate of change in these cases were not as severe as that of image hall and pagoda. At the same time, pagoda was coming closer to the middle gate leaving larger space in front of the image hall. Such aspect is even more meaningful considering the fact that the pagoda, from the 8th century in Japan and China, moved outside of the major precinct. The image hall, too, moved toward the middle gate slightly so that the space in front of the lecture hall became more spacious. Such changes, of course, were not accidental but they are the same continuous motivation of change that caused the changes before the period of unification. Enlargement of image hall and reduction of pagoda, for example, represent the changing relative importance of religious meaning. Hence, it is evident that one can not easily imterprete the development of one style only by categorizing it to be one same style. In the veiwpoint of the underlying motivation of change, the fact that one style persisted for a certain period of time, does not mean there had been no change, but means that it was the time of motivational accumulation, causing minor changes within the same style, to be able to create major change coming after.