• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.11-21
• /
• 2014

Multi-scale image segmentation is important in many applications such as image stylization and medical diagnosis. This paper proposes a novel segmentation algorithm based on MSER(maximally stable extremal region) which captures multi-scale structure and is stable and efficient. The algorithm collects MSERs and then partitions the image plane by redrawing MSERs in specific order. To denoise and smooth the region boundaries, hierarchical morphological operations are developed. To illustrate effectiveness of the algorithm's multi-scale structure, effects of various types of LOD control are shown for image stylization. The proposed technique achieves this without time-consuming multi-level Gaussian smoothing. The comparisons of segmentation quality and timing efficiency with mean shift-based Edison system are presented.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.767-776
• /
• 2020

GcGAN is a deep learning model to translate styles between images under geometric consistency constraint. However, GcGAN has a disadvantage that it does not properly maintain detailed content of an image, since it preserves the content of the image through limited geometric transformation such as rotation or flip. Therefore, in this study, we propose a new image-to-image translation method, MSGcGAN(Multi-Scale GcGAN), which improves this disadvantage. MSGcGAN, an extended model of GcGAN, performs style translation between images in a direction to reduce semantic distortion of images and maintain detailed content by learning multi-scale images simultaneously and extracting scale-invariant features. The experimental results showed that MSGcGAN was better than GcGAN in both quantitative and qualitative aspects, and it translated the style more naturally while maintaining the overall content of the image.

• Tunnel and Underground Space
• /
• v.32 no.2
• /
• pp.131-143
• /
• 2022

The lunar exploration autonomous vehicle operates based on the lunar topography information obtained from real-time image characterization. For highly accurate topography characterization, a large number of training images with various background conditions are required. Since the real lunar topography images are difficult to obtain, it should be helpful to be able to generate mimic lunar image data artificially on the basis of the planetary analogs site images and real lunar images available. In this study, we aim to artificially create lunar topography images by using the location information-based style transfer algorithm known as Wavelet Correct Transform (WCT2). We conducted comparative experiments using lunar analog site images and real lunar topography images taken during China's and America's lunar-exploring projects (i.e., Chang'e and Apollo) to assess the efficacy of our suggested approach. The results show that the proposed techniques can create realistic images, which preserve the topography information of the analog site image while still showing the same condition as an image taken on lunar surface. The proposed algorithm also outperforms a conventional algorithm, Deep Photo Style Transfer (DPST) in terms of temporal and visual aspects. For future work, we intend to use the generated styled image data in combination with real image data for training lunar topography objects to be applied for topographic detection and segmentation. It is expected that this approach can significantly improve the performance of detection and segmentation models on real lunar topography images.

• Digital Contents
• /
• no.5 s.132
• /
• pp.72-73
• /
• 2004

한국정보문화진흥원이 운영하는 정보통신체험관‘IT월드’(과천 서울대공원내)에서 지난 4월 3일부터 11일까지 미국 자연사박물관, 영국 내셔널 스페이스센터, 스페인 아일라 메지카 등 선진 체험학습관에서 제작해 선보여 왔던‘세계 디지털 돔영상 페스타’를 개최해 가족단위 관람객들이 몰려 매회 매진사례를 기록했다.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.345-352
• /
• 2021

Based on the exploration of the reasons why Shunji Iwai is called "Wong Kar-wai of Japan", this paper compared and studied the image style of two directors films, and explored the theoretical characteristics of their similarities and differences, so as to provide inspiration for the development of Chinese national films. This is the purpose of this paper. Through the search of literature, cultural background analysis of the two directors, film style comparison and film aesthetics comparative analysis and other research methods, this paper made a more in-depth theoretical research on the films of the two directors. It was found that the films of the two directors showed the characteristics of narrative abstraction and image beautification, but there were also some differences in the choice of narrative subjects. The research of this paper provided a new train of thought and starting point for us to study and explore the films of two directors, and pointed out a new direction for us to explore the trend of national films.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.35-43
• /
• 2022

Makeup is the most common way to improve a person's appearance. However, since makeup styles are very diverse, there are many time and cost problems for an individual to apply makeup directly to himself/herself.. Accordingly, the need for makeup automation is increasing. Makeup transfer is being studied for makeup automation. Makeup transfer is a field of applying makeup style to a face image without makeup. Makeup transfer can be divided into a traditional image processing-based method and a deep learning-based method. In particular, in deep learning-based methods, many studies based on Generative Adversarial Networks have been performed. However, both methods have disadvantages in that the resulting image is unnatural, the result of makeup conversion is not clear, and it is smeared or heavily influenced by the makeup style face image. In order to express the clear boundary of makeup and to alleviate the influence of makeup style facial images, this study divides the makeup area and calculates the loss function using HoG (Histogram of Gradient). HoG is a method of extracting image features through the size and directionality of edges present in the image. Through this, we propose a makeup transfer network that performs robust learning on edges.By comparing the image generated through the proposed model with the image generated through BeautyGAN used as the base model, it was confirmed that the performance of the model proposed in this study was superior, and the method of using facial information that can be additionally presented as a future study.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.365-366
• /
• 2019

3d 애니메이션 제작 기술의 발전은 시청자의 수요를 충족시키기 위해 다양한 방면에서 성장을 해오고 있는데 툰 쉐이딩 기술역시 빠른 발전을 거듭해오고 있다. 2019년 개봉한 스파이더맨 애니메이션은 마블과 DC코믹스의 그래픽 노블 애니메이션의 새로운 시각적 스타일을 제시하고 있다. 기존의 툰 쉐이딩 스타일에서 벗어나서 캐릭터 뿐 아니라 배경, 카메라, 애니메이션, 편집에 이르기까지 영화의 전 영역에서 그래픽 노블을 보는듯한 착각을 일으키게 한다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.12
• /
• pp.665-682
• /
• 2007

Line drawing is a widely used style in non-photorealistic rendering because it generates expressive descriptions of object shapes with a set of strokes. Although various techniques for line drawing of 3D objects have been developed, line drawing of 2D images has attracted little attention despite interesting applications, such as image stylization. This paper presents a robust and effective technique for generating line drawings from 2D images. The algorithm consists of three parts; filtering, linking, and stylization. In the filtering process, it constructs a likelihood function that estimates possible positions of lines in an image. In the linking process, line strokes are extracted from the likelihood function using clustering and graph search algorithms. In the stylization process, it generates various kinds of line drawings by applying curve fitting and texture mapping to the extracted line strokes. Experimental results demonstrate that the proposed technique can be applied to the various kinds of line drawings from 2D images with detail control.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.2
• /
• pp.27-33
• /
• 2008

We propose a stylized facial illustration method that expresses important features of a target highly abstractly but effectively from a human facial picture. Our method first detects facial components such as eyes and their associated regions from an input image, and then uses the detected results to render a stylized portrait. Our illustration method mainly consists of two key components and additional components: a tonal illustration component to draw simple tones, a line illustration component to draw a set of lines, and additional illustration components for hair, clothes. etc. The illustration part of the proposed method aims at illustrating features of a target effectively in a highly abstracted way like hand-drawn paintings. In order to achieve this goal, our method adopts an oriental black-ink painting style, which expresses objects effectively with empty spaces and simple expressions such as abstracted lines.

• Trans-
• /
• v.13
• /
• pp.59-90
• /
• 2022

Short-form content, which means "short video content within 10 minutes," is rapidly emerging as a recent trend among MZ generations based on the fact that it can be viewed whenever there is a short running time, and they are physically short, colorful, and deliver a lot of information in a compressed time, showing differences in both long-form content and format. In addition, entertainment videos such as information delivery videos, eating shows, web entertainment, and dance challenges are mainly produced and distributed, so there is no need to take expertise as a creative work of video experts, and consumers often become producers by directly participating in production using low-end equipment such as smartphones. For these reasons, shortform content creates new image styles rather than general existing image forms such as long-form contents, and this study focuses on changes in editing styles. This study summarized the following five characteristic changes by analyzing the editing style of short form content that has changed compared to long form content according to the 'visual' aspect. The use of frames, memes, screen division, blue screen, and subtitles are included, and by organizing each characteristic, we identified the editing style of shortform content that has emerged as a recent trend and learned about the changes.