• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.465-475
• /
• 2007

With the spread of Internet, web users express their daily life by articles, pictures and cartons to recollect personal memory or to share their experience. For the easier recollection and sharing process, this paper proposes diverse cartoon generation methods using the landmark lists which represent the behavior and emotional status of the user. From the priority and causality of each landmark, critical landmark is selected for composing the cartoon scenario, which is revised by story ontology. Using similarity between cartoon images and each landmark in the revised scenario, suitable cartoon cut for each landmark is composed. To make cartoon story more diverse, weather, nightscape, supporting character, exaggeration and animation effects are additionally applied. Through example scenarios and usability tests, the diversity of the generated cartoon is verified.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.173-185
• /
• 2022

Nowadays, Korean webtoons are leading the global digital comic market. Webtoons are being serviced in various languages around the world, and dramas or movies produced with Webtoons' IP (Intellectual Property Rights) have become a big hit, and more and more webtoons are being visualized. However, with the success of these webtoons, the working environment of webtoon creators is emerging as an important issue. According to the 2021 Cartoon User Survey, webtoon creators spend 10.5 hours a day on creative activities on average. Creators have to draw large amount of pictures every week, and competition among webtoons is getting fiercer, and the amount of paintings that creators have to draw per episode is increasing. Therefore, this study proposes to generate webtoon background images using deep learning algorithms and use them for webtoon production. The main character in webtoon is an area that needs much of the originality of the creator, but the background picture is relatively repetitive and does not require originality, so it can be useful for webtoon production if it can create a background picture similar to the creator's drawing style. Background generation uses CycleGAN, which shows good performance in image-to-image translation, and CartoonGAN, which is specialized in the Cartoon style image generation. This deep learning-based image generation is expected to shorten the working hours of creators in an excessive work environment and contribute to the convergence of webtoons and technologies.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.522-526
• /
• 2008

In this paper, we propose a system to convert a video motion into cartoon-style animation automatically. Our system is a new video cartoon stylization method that can apply natural transformation with satisfying physical constraints. It applies physically reasonable transformation to a selected video object with considering physical information such as momentum, movement direction and force. We construct several deformation scenarios which correspond with traditional animation techniques, then a scenario can be easily selected to apply the effects. Finally, this system gene-rates a dynamic cartoon-style video by timing control and a cartoon rendering technique.

• Cartoon and Animation Studies
• /
• s.13
• /
• pp.223-236
• /
• 2008

The video game industry is obsessed by the perception of "Next Generation Game". Appearance of the next generation game console has required the video game industry to renovate new technologies for their entire production. This tendency increases a huge mount of production cost. Game companies have to hire more designers to create a solid concept, artists to generate more detailed content, and programmers to optimize for more complex hardware. All those high cost efforts provide great locking games, but the potential of next generation game consoles does not end there. They also bring possibilities of the new types of gameplay. Next generation game contains a much larger pool of memories for every video game elements. The entire video game used to use roughly 800 animation files, but next generation game is pushing scripted event well over 4000 animation flies. That allows a lot of very unique custom animation for pretty much every action in the game. It gives game players much more vivid and realistic appreciation of the virtual world. Players are not being able to see any recycling of the same animation over and over when they are playing next generation game. The main purpose of this thesis is that defines the concept of next generation game and analyzes new animation-pipeline to be used in the shooter games.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.409-413
• /
• 2008

최근, 3차원 그래픽스 기술은 애니메이션 필름 제작에 있어서 자주 사용된다. 그러나 많은 애니메이션 필름들은 3차원 그래픽스 기술을 사용하여 제작되더라도, 2차원 셀 애니메이션 효과를 내려고 한다. 3차원 그래픽스 기술을 이용하여 2차원 셀 애니메이션의 효과를 내기 위해서는 렌더링에는 카툰 렌더링이 사용 된다. 그러나 이를 제외하고도 몇 가기 기술이 더 필요한데, 그중 하나가 만화 캐릭터(character)의 만화스러운 움직임이다. 기존의 연구 중에는 기존의 모션을 만화적 모션으로 변형하려는 시도가 있었으나, 셀 애니메이션의 캐릭터 움직임과 차이가 있었다. 또 생성된 모션이 만화적 모션인가 하는 의문에 대한 평가 기준이 없기 때문에, 만화적 모션의 모호성 문제가 발생하였다. 본 논문에서는 직접 애니메이션에서 모션을 얻어내는 시스템을 제안한다. 2차원 애니메이션 동영상에서 2차원 캐릭터의 자세를 보고 3차원 캐릭터의 자세로 반자동 맵핑하여, 3차원 캐릭터의 애니메이션 키 프레임을 생성하고, 이 키 프레임간의 보간을 통해 3차원 캐릭터 애니메이션을 생성한다. 생성된 3차원 캐릭터 애니메이션은 만화적 움직임을 갖게 되며, 2차원 캐릭터의 자세와 움직임을 기준으로 만들었기 때문에, 만화적 모호성을 극복할 수 있다.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.92-98
• /
• 2024

The current software industry has an emerging issue with natural language-based requirement specifications. However, the accuracy of such requirement analysis remains a concern. It is noted that most errors still occur at the requirement specification stage. Defining and analyzing requirements based on natural language has become necessary. To address this issue, the linguistic theories of Chomsky and Fillmore are applied to the analysis of natural language-based requirements. This involves identifying the semantics of morphemes and nouns. Consequently, a mechanism was proposed for extracting object state designs and automatically generating code templates. Building on this mechanism, I suggest generating natural language-based comic images. Utilizing state diagrams, I apply changes to the states of comic characters (protagonists) and extract variations in their expressions. This introduces a novel approach to comic image generation. I anticipate highly productive comic creation by applying software processes to Cartoon ART.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10a
• /
• pp.195-196
• /
• 2007

우리는 비디오의 모션을 전통적인 애니메이션과 같은 스타일로 변환하는 시스템을 제안한다. 우리의 시스템은 비디오의 물리적인 상황에 맞게 자연스러운 변형을 손쉽게 적용할 수 있는 새로운 비디오의 만화화 방법이다. 선택된 비디오 오브젝트의 운동량, 운동방향, 힘과 같은 물리적인 요인들을 분석하여 물리적으로 타당한 변형을 적용함으로써 자연스러운 효과를 적용한다는 것이 장점이다.

• Cartoon and Animation Studies
• /
• s.13
• /
• pp.1-12
• /
• 2008

We can make the foundation of culture and contents solid with a mental altitude to make out and protect copyright. It'll be the basis of the cultivating student, the next generation in this field who are majoring in animation, comics and characters now. It will give them a good environment to learn more about copyright and motivate surroundings. With this kind of education, We can make and protect works better. This thesis is a result of study to show how to and when to instruct people copyright even though we have faced constant argument on copyright and new approach to the economic value of cultural contents which has been under industrialization. Also, another big issue is what class would be a good target of the education on copyright. College may be the last place in the regular course for education before starling his or her career. Thus, the education that is focused on the importance of copyright is recommendable at this time. Particularly, the students who are majoring carton, animation and character can keep a good attitude to protect copyrights for others through the timely education on copyright. What's more, we can build better environment for students who will start their career in the field of the cultural contents and copyrights because they will not only try protect copyrights for others but also they know their works will be protected through thls kind of education on copyright. I believe this kind of education in college will promote the development in the field of cultural contents and copyrights. Also, it will support social and economic development In culture after all.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.99-107
• /
• 2024

In AI image generation tools, most general users must use an effective prompt to craft queries or statements to elicit the desired response (image, result) from the AI model. But we are software engineers who focus on software processes. At the process's early stage, we use informal and formal requirement specifications. At this time, we adapt the natural language approach into requirement engineering and toon engineering. Most Generative AI tools do not produce the same image in the same query. The reason is that the same data asset is not used for the same query. To solve this problem, we intend to use informal requirement engineering and linguistics to create a toon. Therefore, we propose a sequence diagram and image generation mechanism by analyzing and applying key objects and attributes as an informal natural language requirement analysis. Identify morpheme and semantic roles by analyzing natural language through linguistic methods. Based on the analysis results, a sequence diagram and an image are generated through the diagram. We expect consistent image generation using the same image element asset through the proposed mechanism.