• KIISE Transactions on Computing Practices
• /
• v.21 no.12
• /
• pp.768-773
• /
• 2015

Emergence events are the cause of much economic damage. In order to minimize the damage that these events cause, it must be possible to predict what will happen in the future. Accordingly, many researchers have focused on real-time monitoring, detecting events, and investigating events. In addition, there have also been many studies on predictive analysis for forecasting of future trends. However, most studies provide future tendency per event without contextual compositive analysis. In this paper, we present a predictive visual analytics system using topic composition to provide future trends per event. We first extract abnormal topics from social media data to find interesting and unexpected events. We then search for similar emergence patterns in the past. Relevant topics in the past are provided by news media data. Finally, the user combines the relevant topics and a new context is created for contextual prediction. In a case study, we demonstrate our visual analytics system with two different cases and validate our system with possible predictive story lines.

• Journal of Korean Ophthalmic Optics Society
• /
• v.19 no.2
• /
• pp.217-224
• /
• 2014

Purpose: This study was conducted to compare and analyze the accommodative system (accommodative response and accommodative lag) according to the material and font size of near visual media that we often encounter in daily life. Methods: Forty adult men and women aged 20 to 30 who not had specific ocular diseases and refractive surgery experience were examined to measure and compare the accommodative response according to the material of near visual media (print paper, newspaper, magazine, the I-Phone, LCD monitor) and font size (6, 8, 10, 12) by using both eyes open-view auto-refractometer. Results: The accommodative stimulus was $2.28{\pm}0.11D$ and the accommodative response was $1.66{\pm}0.30D$. The accommodative lag namely the difference between accommodative stimulus and accommodative response was $0.62{\pm}0.28D$. The accommodative response according to material of visual media using LCD monitor was $1.35{\pm}0.26D$ (p=0.00) and using the I-Phone was $1.55{\pm}0.25D$ (p=0.04). Both of them were statistically significant lower. The accommodative lag using LCD monitor was $0.93{\pm}0.24D$ (p=0.00) and using the I-Phone was $0.73{\pm}0.25D$ (p=0.04) and they were statistically significant higher. The accommodative response and accommodative lag according to font size were not statistically significant (p>0.05). Conclusions: During near working, the accommodative system was more affected by material than font size of visual media. Especially, visual media of non-luminous material (print paper, newspaper, magazine) are considered fewer burdens on eyes than luminous material (I-Phone, LCD monitor) in terms of accommodative system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2938-2956
• /
• 2020

Objective image quality assessment (IQA) models have been developed by effective features to imitate the characteristics of human visual system (HVS). Actually, HVS is extremely sensitive to color degradation and complex texture changes. In this paper, we firstly reveal that many existing full reference image quality assessment (FR-IQA) methods can hardly measure the image quality with contrast and masking texture changes. To solve this problem, considering texture masking effect, we proposed a novel FR-IQA method, called Texture and Color Quality Index (TCQI). The proposed method considers both in the masking effect texture and color visual perceptual threshold, which adopts three kinds of features to reflect masking texture, color difference and structural information. Furthermore, random forest (RF) is used to address the drawbacks of existing pooling technologies. Compared with other traditional learning-based tools (support vector regression and neural network), RF can achieve the better prediction performance. Experiments conducted on five large-scale databases demonstrate that our approach is highly consistent with subjective perception, outperforms twelve the state-of-the-art IQA models in terms of prediction accuracy and keeps a moderate computational complexity. The cross database validation also validates our approach achieves the ability to maintain high robustness.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.273-280
• /
• 2019

360 video is attracting attention as immersive media with the spread of VR applications, and MPEG-I (Immersive) Visual group is actively working on standardization to support immersive media experiences with up to six degree of freedom (6DoF). In virtual space of omnidirectional 6DoF, which is defined as a case of degree of freedom providing 6DoF in a restricted area, looking at the scene at any viewpoint of any position in the space requires rendering the view by synthesizing additional viewpoints called virtual omnidirectional viewpoints. This paper presents the performance results on view synthesis and their analysis, which have been done as exploration experiments (EEs) of omnidirectional 6DoF in MPEG-I. In other words, experiment results on view synthesis in various aspects of synthesis conditions such as the distances between input views and virtual view to be synthesized and the number of input views to be selected from the given set of 360 videos providing omnidirectional 6DoF are presented.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.126-137
• /
• 2018

Visual characters used in television affect the viewers in a different way from printed media. This paper analyzed the visual characters presented in each home shopping channel and their year-by-year characteristics in terms of layouts. Based on the results, the readability was analyzed according to different layouts, suggesting optimal layouts that allows for better communication with the viewers. The purpose of this study is thus to focus on the visual character layouts, which have not been fully explored to date, in order to identify the most effective one among basic locations of visual characters. The results indicate that the bottom location shows higher readability than top. The right side showed higher preference than left, while readability did not demonstrate a significant difference. As for the L-bar and reverse L-bar, the L-bar arrangement was shown preferable in terms of readability. Finally, the layout should be determined considering the readability by location.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06a
• /
• pp.159-164
• /
• 1999

Homogeneous but distinct visual objects having low-contrast boundaries are usually merged in most of the segmentation algorithms. To alleviate this problem, an efficient image segmentation algorithm based on a bottom-up approach is proposed by using spatial domain information only. For initial image segmentation, we adopt an efficient marker extraction algorithm conforming to the human visual system. Then, two region-merging algorithms are successively applied so that homogeneous visual objects can be represented as simple as possible without destroying low-contrast real boundaries among them. The resultant segmentation describes homogeneous visual objects with few regions while preserving semantic object shapes well. Finally, a size-based region decision procedure may be applied to represent complex visual objects simpler, if their precise semantic contents are not necessary. Experimental results show that the proposed image segmentation algorithm represents homogeneous visual objects with a few regions and describes complex visual objects with a marginal number of regions with well-preserved semantic object shapes.

• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.425-434
• /
• 2013

Observers usually experience visual fatigue when they watch contents displayed on 3D display. There has been various research on visual fatigue incurred in stereoscopic displays that use 3D glasses, but relatively less studies have been done in the area of autostereoscopic displays. i3D system refers to interactive 3D system that makes it possible for users to interact with contents using their hands. Current research measured visual fatigue that users experience from i3D under various visual environments. We examined the effects of viewing distance, disparities and visual orientation on visual fatigue in i3D. The results indicated that visual fatigue decreased with longer distance and smaller disparity. Visual fatigue increased with angle when 3D fusion was unstable. In addition, there was an interaction effect between angle and distance in which visual fatigue increased with distance under stable 3D fusion but there was no difference in visual fatigue as a function of distance when 3D fusion was unstable. These results would be importantly used to develop autostereoscopic displays that minimize visual fatigue.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.259-260
• /
• 2019

MPEG-I Visual group is actively working on enhancing immersive experiences with up to six degree of freedom (6DoF). In virtual space of 3DoF+, which is defined as an extension of 360 video with limited changes of the view position in a sitting position, looking at the scene from another viewpoint (another position in space) requires rendering additional viewpoints using multiple videos taken at the different locations at the same time. In the MPEG-I Visual workgroup, methods of efficient coding and transmission of 3DoF+ video are being studied, and they released Test Model for Immersive Media (TMIV) recently. This paper presents the enhanced clustering method which can pack the patches into atlas efficiently in TMIV. The experimental results show that the proposed method achieves significant BD-rate reduction in terms of various end-to-end evaluation methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.868-870
• /
• 2005

스크래치는 오래된 필름에서 가장 많이 나타나는 손상 요인이다. 고화질의 멀티미디어 서비스를 제공하기 위해서는 이러한 스크래치들은 반드시 검출 및 복원되어야 한다. 이러한 중요성 때문에 지금까지 많은 복원 알고리즘이 개발되어 왔으나, 스크래치 영역의 자동검출에 대한 연구는 거의 이루어지지 않은 실정이다. 따라서 본 논문에서는 자동으로 스크래치영역을 추출할 수 있는 신경망 기반의 검출 방법을 제안한다. 다층 퍼셉트론 (Multi-layer perceptron: MLP)을 이용하여 스크래치영역과 비 스크래치영역을 구분하는데, 이 MLP는 다양한 크기의 스크래치를 검출하기 위해 다양한 크기의 입력 영상에 대해 적용된다. 제안된 방법의 평가를 위해 principal/ secondary 스크래치, alone/not-alone 스크래치, moving/static 스크래치등의 다양한 종류의 스크래치를 가진 영상에 대해 실험이 이루어졌고, 그 결과 제안된 방법의 강건함과 효율성을 입증되었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.399-400
• /
• 2018

해마다 방대한 양의 콘텐츠가 쏟아져 나오는 현재의 콘텐츠 시장은 '즐길 거리'가 차고 넘치는, 수요보다 공급이 많은 시장이다. 이러한 환경에서 소비자가 자신의 취향에 맞는 콘텐츠를 쉽고 빠르게 찾을 수 있게 하는 맞춤형 콘텐츠 제공의 측면에서 빅데이터의 효율적인 활용은 중요하다. 더 나아가 콘텐츠의 소비 단계 뿐만 아니라 기획 및 제작 단계에서도 빅데이터는 소비자가 흥미를 느낄만한 콘텐츠를 미리 예측하며, 성공 가능성 높은 콘텐츠를 기획 및 제작할 수 있게 하는데 기인하는 중요한 핵심 요소이다. 이미 게임, 영상, 음악 등의 분야에서는 개인의 기호와 취향에 맞춤화된 콘텐츠를 제공하거나 소비자에게 더 인기를 얻을 수 있는 콘텐츠 기획 및 개발에 빅데이터를 활용하고 있으며, 앞으로는 더욱 다양한 장르에서 빅데이터 활용 사례가 증가할 전망이다.