• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.225-230
• /
• 2023

With the development of AI technology, there is a growing discussion about Text-to-Image Generative AI. We presented a Generative AI video production method and delineated a methodology for the production of personalized AI-generated videos with the objective of broadening the landscape of the video domain. And we meticulously examined the procedural steps involved in AI-driven video production and directly implemented a video creation approach utilizing the VQGAN-CLIP model. The outcomes produced by the VQGAN-CLIP model exhibited a relatively moderate resolution and frame rate, and predominantly manifested as abstract images. Such characteristics indicated potential applicability in OTT-based video content or the realm of visual arts. It is anticipated that AI-driven video production techniques will see heightened utilization in forthcoming endeavors.

• International Journal of Contents
• /
• 제6권2호
• /
• pp.1-5
• /
• 2010

The rapid growth in communication technology has led to the development of effective ways of sharing ideas and information in the form of speech and images. Understanding this information has become an important research issue and drawn the attention of many researchers. Text in a digital image contains much important information regarding the scene. Detecting and extracting this text is a difficult task and has many challenging issues. The main challenges in extracting text from natural scene images are the variation in the font size, alignment of text, font colors, illumination changes, and reflections in the images. In this paper, we propose a connected component based method to automatically detect the text region in natural images. Since text regions in mages contain mostly repetitions of vertical strokes, we try to find a pattern of closely packed vertical edges. Once the group of edges is found, the neighboring vertical edges are connected to each other. Connected regions whose geometric features lie outside of the valid specifications are considered as outliers and eliminated. The proposed method is more effective than the existing methods for slanted or curved characters. The experimental results are given for the validation of our approach.

• 한국의류산업학회지
• /
• 제11권6호
• /
• pp.934-941
• /
• 2009

The purpose of this study is to examine by which correlation the pluralistic phenomenon in text is functioned in comparison with hair style and fashion in collection. As a result, the pluralistic image in text, which was shown in modern fashion, was indicated to be pluralistic phenomenon by gender, T.P.O, coordination, and material. The pluralistic image in text for hair style can be known to have been indicated to be the pluralistic phenomenon in text for gender and to be the pluralistic phenomenon in text according to material and cultural category. As for a method of this study, it did put limitation on the part that is shown in the fashion collection from 2001 to 2007, analyzed hair-style features centering on photos, which were extracted from style.com, the online site of specializing in fashion, and carried out a literature research side by side with the theoretical background on intertextuality. The analysis in work according to the pluralistic phenomenon in text made it possible for looking at with a new sight differently from the recognition in the past, and opened the potentiality for being able to understand lots of strange representations, which have been impossible so far. The process of imitating and reconstructing each text according to compositional principle led to possibly knowing the necessity of an artist's ability that can implement the originative world.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.345-359
• /
• 2017

Optical Character Recognition (OCR) that has been a main research topic of computer vision and artificial intelligence now extend its applications to detection of text area from video or image contents taken by camera devices and retrieval of text information from the area. This paper aims to implement a binarization algorithm that removes user intervention and provides robust performance to outdoor lights by using TopHat algorithm and channel transformation technique. In this study, we particularly concentrate on text information of outdoor signboards and validate our proposed technique using those data.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 춘계학술대회
• /
• pp.227-229
• /
• 2011

웹 사이트를 효과적으로 개발하기 위해 Ajax, jQuery등과 같은 다양한 기술이 개발되고 있다. 관리자 인터페이스를 강력하게 함으로써, 관리자 메뉴에서 다양한 기능을 손쉽게 제작할 수 있지만, 이러한 경우 텍스트 형태를 벗어나지 못하거나, 코드를 그 때 그 때 수정하고 있는 실정이다. 이러한 문제점을 해결하기 위해, 본 논문에서는 CSS를 데이터베이스와 연동하여 제공하고, 이러한 CSS 기능과 다양한 오픈 폰트를 이용해 텍스트를 이미지로 변환함으로써, 기존의 웹 사이트 제작 방법과의 차별화된 기능을 제공하는 방법에 대해 기술한다.

• 한국콘텐츠학회논문지
• /
• 제14권11호
• /
• pp.60-67
• /
• 2014

예술의 역사에 있어 문자와 형상이 어우러지는 형태는 고대 예술의 여러 장르에서 발견된다. 특히 불교예술의 도상은 문자와 동등한 의미전달 수단으로서 교리를 선전하는 중요한 도구였다. 이는 원래의 문학적 형식이 회화적 형식으로 소통체계가 전환됨을 말하며, 사유방식도 다른 기호적 체계를 가진다. 문자와 형상의 상호 전환은 현대 영상매체의 미적개념을 해석하는데 매우 중요하다. 그러므로, 본 논문은 형상적 사유를 통한 현대 대중매체의 시각예술에 대한 해석의 실마리를 고대 돈황벽화 <구생록본생도>에 나타난 도상적 서사와 애니메이션 <구색록>의 영상이미지 표현과의 비교분석을 통해 살펴보았다.

• 한국의류학회지
• /
• 제29권7호
• /
• pp.926-937
• /
• 2005

The analysis category of Art to Wear was text analyzed from the research material of 100 projects put together by fashion specialist. The conclusion of Art to Wear was comprehended the general features of it were compared and analyzed from a semiotics context. According to this analysis, the formative features of modern Art to Wear is categorized into three different dimensions from a semiotics light. The formative features of modem Art to Wear in the light of syntactic dimension was divided as an open constructed shape of Space Extension, non-typical Deformation, Geometrical Plasticity. The formative features of modem Art to Wear in the light of semantic dimension express symbolic meaning through metaphorical sign. These sign reflect the body image of the life and death and its objective of Abjection, Hybrid of discultural appearance and the image of Hyper-reality, which are features used to comprehend the inner meaning. The formative features of modem Art to Wear in the light of pragmatic dimension divided the artist emotion and meaning system delivered by Emotive Image, the Phatic Image that arouse inner signification and the Poetic Image which contain artistic and aesthetic meaning within it.

• 지능정보연구
• /
• 제8권1호
• /
• pp.27-39
• /
• 2002

본 논문은 다양한 웹 이미지로부터 문자영역(text block)의 위치를 알아내고 문자영역을 추출하는 방법을 제안한다. 인터넷 사용자관점에서 볼 때, 웹 이미지에 포함되어 있는 문자정보는 중요한 정보이지만 최근까지 이 분야의 연구는 그리 활발하지 못했다. 본 연구에서 제안된 알고리즘은 문자의 경사방향(skew)과 문자의 크기나 폰트에 관한 사전 정보 없이 수행되어 질 수 있도록 제안되었다 폰트 스타일과 크기에 제약되지 않고 문자영역을 적합하게 추출하기 위해 유용한 에지 검출, 문자 클러스터링 영역으로 정의되는 문자의 고유한 특성을 위한 히스토그램을 사용하였다. 다수의 실험을 통하여 제안된 방법을 테스트하고 수용할 만한 결과를 도출했다.

• International Journal of Advanced Culture Technology
• /
• 제6권4호
• /
• pp.323-330
• /
• 2018

The growth of the older population is expected to further increase social problems associated with population aging, such as isolation, poverty, and depression. The emerging issues associated with the older population are also expected to provide further momentum on studies about the dwelling environment as factors that ensure the health of older people as well as improve their quality of life. Therefore, approaches for explaining the issues of the older age group should be diversified using a variety of factors and appropriate analytic tools. Studies on measuring depression have principally focused on assessing an objective self-report questionnaire, usually in a highly structured, textual form which may not reflect the cognitive impairment of older adults. The aim of this study was to define and measure dwelling depression among older adults in Korea. There are two specific hypotheses in this study as follows: (a) there will be statistically significant relationships with dwelling dissatisfaction and depression, and (b) dwelling depression tools containing text and images will be, respectively, assessment tools that have a good construct with content validity and reliability. In the first experiment, to define and measure dwelling depression, 301 people over 65 years old living in single and two-person households were surveyed using a text-based dwelling depression questionnaires from September 1-30, 2017. In the second experiment, to examine whether the projective image questionnaire could serve as a suitable replacement for the text-based questionnaires, the same participants were surveyed from January 22 to February 2, 2018. The results show that depression has a close correlation with dwelling dissatisfaction. In addition, the geriatric dwelling depression index (GDDI) based on the projective image was refined. Additionally, the projective image questionnaire has a close correlation with the text-based questionnaire. Finally, through ROC curve analysis, it was found that the projective image questionnaire can accurately predict a depression group. To this end, this preliminary study examined the validity of the projective image questionnaire in older adults to make this instrument feasible for older populations and to contribute to a profound understanding of geriatric depression due to the living environment. We hope they will provide a basis for further research on psychological diagnoses using projective images.

• 방송공학회논문지
• /
• 제18권6호
• /
• pp.795-807
• /
• 2013

최근 2D 영상을 3D로 변환하는 2D-to-3D 변환기술에 대한 관심이 높아지고 있다. 지금까지는 영화나 애니메이션 등의 자연영상을 3D변환하는 것에 초점이 맞추어져 있었다. 그러나 텍스트, 이미지, 로고, 아이콘등이 혼재 되어 있는 윈도우영상의 경우, 이러한 3D변환기술을 적용하는데 어려움이 있다. 특히 텍스트는 동일한 깊이를 얻지 못하면 깨짐, 흔들림 등의 문제가 발생한다. 본 논문에서는 이러한 문제를 해결하기 위해 먼저 자연영상과 윈도우영상의 분류를 수행하고 윈도우영상일 경우에 텍스트나 배경을 제외하고 이미지 영역만을 검출하는 방법을 제안한다. 검출된 영역에 대해서 3D변환을 각자 수행하고 나머지 영역은 변환하지 않음으로써 상기 문제점을 해결할 수 있다. 실험에서는 10,000장 이상의 실험영상을 테스트하였다. 실험결과로는 윈도우영상의 검출률이 97%을 얻었고, 윈도우영상의 영상영역의 검출률은 87%이다.