• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1277-1282
• /
• 2006

본 논문에서는 배경과 오브젝트 합성 시 사실적인 그림자 효과를 표현하기 위해 HDR 영상을 기반으로 한 소수의 방향성 광원을 추정하는 기법을 제안한다. 실 세계 정보를 모두 포함하는HDR 영상을 가시화 하기 위해 톤 맵핑(tone mapping)하여 그 영상으로부터 광원의 위치가 되는 밝은 영역들을 찾아내고 그 위치들로부터 방향성 광원을 추정한다. 카메라의 노출시간을 짧게 하여 촬영한 영상에서 나타나는 부분을 실제 광원이 위치하는 부분으로 볼 수 있으므로 톤 맵핑한 영상을 이미지 프로세싱을 거쳐 노출 시간을 짧게 하여 촬영한 영상과 비슷한 결과를 얻을 수 있도록 한 후 밝은 영역만 표현 되도록 한다. 전 처리를 거친 영상을 기반으로 밝은 영역을 추정하기 때문에 보다 정확한 광원의 위치 추정이 가능하며, 추정된 밝은 영역과 일치하는 HDR 영상의 데이터를 사용하기 때문에 정확한 광원의 위치와 데이터를 얻을 수 있다. 또한 추정된 광원은 실제 렌더링에 곧바로 사용이 가능하며, 이를 통해 사실적인 shadowing 효과를 얻을 수 있다.

• Journal of Korea Game Society
• /
• v.12 no.1
• /
• pp.43-55
• /
• 2012

In SNG, actual users enter virtual space with their real identity. They can enter the game space easily and rapidly from the real space and can get out of it easily. For such free crossing between the virtual and the real, every character, space image and game play has symbolic reality. While paying attention to the game play process of SNG such symbolic reality is constructed into the virtual world in the game, this study intends to identify that it follows an order of simulacre by Baudrillard. As the result of analysis, it shows that SNG promotes easy entering the game space while reflecting the reality to the most in the opening part of game play. And, gradually concealing reality, it reaches a pure simulacre step while covering up and distorting absence of the reality. If we compare it with the direct entering the pure similacre step in the existing Online games like MMORPG, we can know that such a game play process according to the similacre order may be the distinct game characteristic of SNG.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.701-704
• /
• 2020

이미지 초해상도는 딥러닝의 발전과 함께 이를 활용하며 눈에 띄는 성능향상을 이루었다. 딥러닝을 기반으로 한 대부분의 이미지 초해상도 연구는 딥러닝 네트워크 모델의 구조에 대한 연구 위주로 진행되어 왔다. 그러나 최근 들어 딥러닝 기반의 이미지 초해상도가 합성된 데이터에 대해서는 높은 성능을 보이지만 실제 데이터에 대해서는 높은 성능을 보이지 못한다는 사실이 주목받고 있다. 이에 따라 모델 구조를 바꿔 성능을 향상 시키는 것에는 한계가 있어 데이터의 활용이나 학습 방법에 대한 연구의 필요성이 증대되고 있다. 따라서 본 논문은 이미지 초해상도를 위한 난이도 조절 기반 전이학습법(transfer learning)을 제안한다. 제안된 방법에서는 이미지 초해상도를 배율을 난이도가 쉬운 낮은 배율부터 순차적으로 전이학습을 진행한다. 이는 이미지 초해상도의 배율이 높아질수록 학습이 어렵기 때문이다. 결과적으로 본 논문에서는 높은 배율의 이미지 초해상도를 진행하기 위해 낮은 배율의 이미지 초해상도, 즉 난이도가 쉬운 학습부터 점진적으로 학습을 진행하였을 때 더욱 빠르고 효과적으로 학습할 수 있음을 보여준다. 제안된 전이학습 방법을 통해 적은 횟수의 업데이트로 학습을 진행하였을 때 일반적인 학습방법 대비 약 0.18 dB 의 PSNR 상승을 얻어, RealSR [9] 데이터셋에서 28.56 dB의 성능으로 파라미터 수 대비 높은 성능을 얻을 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.540-543
• /
• 2020

본 논문에서는 대표적인 이미지 분류 모델인 CNN(Convolutional Neural Network)과 시간에 따른 이미지의 변화를 학습할 수 있는 LSTM(Long Short-Term Memory) 기반의 온라인 서명인식 모델을 제안한다. 실제로는 위조서명을 미리 구하기 어렵다는 사실을 고려해 서명검증 대상자가 아닌 타인의 진서명과 대상자의 일반 필기 데이터를 음의 데이터로서 학습에 사용하였다. 실험 결과, 전체 이미지 중 서명 부분의 비율에 따라 좋은 성능을 보이는 검증 모델이 다르며 Accuracy 성능지표를 통해 이 비율이 높거나 낮을 경우 CNN-LSTM 이, 중간일 경우 CNN 이 적합하다는 것을 확인하였다.

• Journal of the Korean Society for information Management
• /
• v.19 no.3
• /
• pp.123-143
• /
• 2002

Developing good methods for image description and indexing is fundamental for successful image retrieval, regardless of the content of images. Researchers and practitioners in the field of image indexing have developed a variety of image indexing systems and methods with the consideration of information types delivered by images. Such efforts in developing image indexing systems and methods include Panofsky's levels of image indexing and indexing systems adopting different approaches such as thesauri-based approach, classification approach. description element-based approach, and categorization approach. This study investigated users' perception of the objectiveness of image indexing, especially the iconographical analysis of image information advocated by Panofsky. One of the best examples of subjectiveness and conditional-dependence of image information is emotion. As a result, this study dealt with visual emotional information. Experiments were conducted in two phases : one was to measure the degree of agreement or disagreement about the emotional content of pictures among forty-eight participants and the other was to examine the inter-rater consistency defined as the degree of users' agreement on indexing. The results showed that the experiment participants made fairly subjective interpretation when they were viewing pictures. It was also found that the subjective interpretation made by the participants resulted from the individual differences in terms of their educational or cultural background. The study results emphasize the importance of developing new ways of indexing and/or searching for images, which can alleviate the limitations of access to images due to the subjective interpretation made by different users.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.2
• /
• pp.238-246
• /
• 2018

The production of hyper-realistic digital rendering images has been available due to radical improvements of recent digital rendering and CGI (Computer-Generated Imagery) software technologies. The photorealism of digital architectural rendering images requires further studies and discussions in that architectural visualization becomes a foundation of other fields using digital rendering technology, such as movies, games, and VR industry. The principles for achieving photorealism on digital architectural rendering images were re-defined and detailed elements were analyzed through theoretical analysis of the former studies. Four principles were drawn from the architectural rendering images produced by newly-developed technologies: physically-accurate lighting calculations, accurate object geometry representation, realistic material and texture, and characteristics of photography. The sub-elements of those four principles are categorized into either essential or selective for photorealistic imagery and the randomness of the selective elements could explain the variety of photorealistic architectural rendering styles.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.1
• /
• pp.17-24
• /
• 2002

In this paper, we propose a new watermarking method using isolation of invalid blocks for image authentication. We embed messages into the high frequency band in the DCT domain because of its imperceptibility and fragility. And we were able to inspect the identity of valid blocks between error corrected original images and watermarked images through experiments. As a result, we found that the watermarked image is enough to extract binary messages. Therefore, the extra information such as the original image or watermark was not necessary in our extracting process. Experiment results show that the proposed method can be used successfully for image authentication.

• The Journal of the Korea Contents Association
• /
• v.22 no.6
• /
• pp.145-159
• /
• 2022

The purpose of this study is to analyze the structural relationship between politicians' YouTube information service quality, politician's image and trust, and voters' social and political participation intentions. To investigate this, 306 voters were sampled through an online survey. The quality factors of the politician's YouTube information service were found to have a positive effect on the image of a politician. Among them, timeliness and reliability had a positive effect on the trust of politicians, but playfulness did not. Both the image and trust of politicians through YouTube were found to have a positive effect on voters' intention to participate in society and politics. As a result of examining the indirect effect, it was found that the image of a politician had an indirect effect on the quality of information service and the intention to participate in society and politics. This study is significant in revealing that the fact that the image and trust of politicians is a major variable that appeals to citizens' social and political participation is also applicable to YouTube.

• The Journal of the Korea Contents Association
• /
• v.17 no.10
• /
• pp.576-586
• /
• 2017

This thesis is a result of studying the combination of text and image based on the achievement of LTP (Literacy Through Photography), a communication education program for young people. This paper presents the LTP program that emphasizes communication functions of images and introduces the results of education conducted to improve the ability of visual communication for adolescents. Adolescents's creative images are analyzed on the basis of three categories of anchors, ealais and illustrations. The questionnaire was a quantitative survey of communication conducted before and after the LTP training. As a result, LTP education showed higher achievement in communication with adolescents when using images than text. In conclusion, this study gives meaning to image utilization education for creativity enhancement and present it as a new education by examining the LTP works and questionnaires of adolescents from communication point of LTP.

• Cartoon and Animation Studies
• /
• s.9
• /
• pp.220-234
• /
• 2005

The article deals with the reality subject of animations. Animations are created on the basis of fantasy. Disney's introduction of the narratives and styles of live action film into the field of animation, which laid a foundation for the hyper-reality animation, has produced an unintended consequence of marginalizing other animation genres which have emphasized fantasy through free experimentations of various images. A combination of Disney's world view of hyper-reality with later-developed 3D computer animation technology has made fantastic figures and spaces much more real than the real ones, and succeeded in creating a matrix of simulacre, a world of mere copies without the original.