• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.148-153
• /
• 2009

Few methods have dealt with segmenting multiple images with analogous content. Concurrent images of a scene and gathered images of a similar foreground are examples of these images, which we term consistent scene images. In this paper, we present a method to segment these images based on manual segmentation of one image, by iteratively propagating information via multi-level cues with adaptive confidence. The cues are classified as low-, mid-, and high- levels based on whether they pertain to pixels, patches, and shapes. Propagated cues are used to compute potentials in an MRF framework, and segmentation is done by energy minimization. Through this process, the proposed method attempts to maximize the amount of extracted information and maximize the consistency of segmentation. We demonstrate the effectiveness of the proposed method on several sets of consistent scene images and provide a comparison with results based only on mid-level cues [1].

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1996년도 Proceedings International Workshop on New Video Media Technology
• /
• pp.35-40
• /
• 1996

In this paper, a method for 3-D surface reconstruction with two real cameras is presented. The method, which combines the extraction of binocular disparity and its interpolation can be applied to the synthesis of images from virtual viewpoints. The synthesized virtual images are as natural as the real images even when we observe the images as stereoscopic images. The method opens up many applications, such as synthesizing input images for multi-viewpoint 3-D displays, enhancing the depth impression in 2-D images and so on. We also have developed a video-rate stereo machine able to obtain binocular disparity in 1/30 sec with two cameras. We show the performance of the machine.

• 디지털융복합연구
• /
• 제13권3호
• /
• pp.263-270
• /
• 2015

역사적으로 과학기술의 발전은 그 시대의 세계관에 영향을 미쳐왔고, 이는 예술매체와 콘텐츠를 통하여 시각화되어왔다. 본고에서는 20세기 초반에서 중반사이에 아메리카와 유럽을 중심으로 발전하고 단기간 주목받았던 키네틱아트에 대한 재조명을 통해서 '움직임' 의 개념이 어떠한 방식으로 작품의 물질성과 비물질성의 전환과 공존을 통해 발전해왔는지에 대해 알아보고 이러한 키네틱아트의 개념 확대가 현대의 새로운 과학기술을 반영한 뉴미디어아트에 어떠한 영향을 끼쳤는지 논하였다. 디지털미디어로 창작된 작품은 항상 관객과의 대면에 일종의 환영을 구동시키는 장치부터 물리적 공간이나 인터페이스가 필요한데, 이러한 면이 키네틱아트의 전례와 '물질과 비물질의 병치'라는 면에서 유사한 점과 차이점을 모두 내제하고 있다고 보고 두 미술사적 운동에 대하여 비교분석을 통해서 탐구하였다.

• Journal of Contemporary Eastern Asia
• /
• 제14권2호
• /
• pp.87-96
• /
• 2015

Social media comprises a vast and consequential landscape that has been poorly mapped and understood. Hundreds of millions of people have eagerly moved many of the conversations and discussions that compose civil society into these services and platforms. There is a need to document and analyze these social spaces for many academic and commercial purposes. The Social Media Research Foundation has engaged a strategy to cultivate better research into the structure and dynamics of social media. The foundation is dedicated to the creation of open tools, open data, and open scholarship related to social media. It has implemented a free and open network collection, analysis, and visualization tool called NodeXL to facilitate social media network research. Using NodeXL a group of researchers has collectively authored a publicly available archive, called the NodeXL Graph Gallery, composed of network data sets and visualizations from users around the world. This site has enabled the aggregation of tens of thousands of network datasets and images. Use of the archive has led to scholarly research results that are based on the wide range and scope of social media data sets available.

• 복식
• /
• 제61권3호
• /
• pp.83-96
• /
• 2011

It will be very effective in studying fashion images that reflect society to investigate the process of the images of military uniforms becoming fashion with the images as the original or image changes in the military look in relation to The hyperreal of the Simulation phenomenon. The foundation of the study was set up by studying simulation and simulacra. Studying the simulation phenomenon in fashion was followed by explaining the aspects of simulacra and the hyperreal in image changes in fashion to study and analyze the simulation phenomenon of the military look based on the findings. The study examined the military look from the Industrial Age to modern times through simulation and the hyperreal in the military look of modern fashion through the changes of images that started with military uniforms. Those research efforts led to the following conclusions: Looking into fashion through the military look reveals that The hyperreal made its appearance in most cases with few cases of the 1st and 2nd simulacrum. And hyperreality was closely related to media in fashion under the influence of media. In short, fashion and copy are in an inseparable relation, and the hyperreality phenomenon has always been present in modern fashion.

• 디지털산업정보학회논문지
• /
• 제9권2호
• /
• pp.99-109
• /
• 2013

In this paper, we propose a new system which captures real depth and color information from natural scene and implemented it. Based on it, we produced stereo and multiview images for 3-dimensional stereoscopic contents and introduced the production of a digital hologram which is considered to the next-generation image. The system consists of both a camera system for capturing images which correspond to RGB and depth images and softwares (SWs) for various image processings which consist of pre-processing such as rectification and calibration, 3D warping, and computer generated hologram (CGH). The camera system use a vertical rig with two paris of depth and RGB camera and a specially manufactured cold mirror which has the different transmittance according to wavelength for obtaining images with the same view point. The wavelength of our mirror is about 850nm. Each algorithm was implemented using C and C++ and the implemented system can be operated in real-time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권3호
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.699-702
• /
• 2009

This paper proposes a gender identification using shoeprint images. It is difficult for the proposed method to identify an individual if shoeprint images for identification leaked out. Because the proposed method identifies gender without the faces, the type of dress and the hair types images. Therefore we can use safely the proposed method in public place. In addition, a sensor mat which we developed is reasonable to use mechanical switches arranged in a matrix pattern without pressure switches. We had shoeprint images with the sensor mat. We measure feature parameters from shoeprint images. The feature parameters are length, width and area of shoeprint. Utilizing the feature parameters, we identified gender. In order to verify the gender identification rate of the proposed method, we set up the sensor mat at an entrance of buildings and took shoeprint images of 100 men and 100 women. As a result, we achieved about 86 percent of the gender identification rate.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.816-820
• /
• 2009

In landscape simulatin, it is necessary to express very realistic image generated by computer graphics. One solution is to use texture mapping; however, it needs a lot of work and time to obtain images for texture mapping since there are huge variety of images for buildings, roads, stations and so on, and the landscape image is diverse due to the weather and time. Especially, weathered images such as stain on walls, crack on roads and so forth, are needed to make the landscape image very realistic. These weathered images do not have to be strict so that it saves a lot of work and time for obtaining the images for texture mapping if we can generate a variety of weathered images automatically. Therefore, this paper describes how to generate a variety of weathered images automatically by changing the weathered shape of the original image.

• Journal of Information Technology Applications and Management
• /
• 제29권2호
• /
• pp.1-15
• /
• 2022

Image has more power in the 21st century than ever before. With the advance in technology and media, image is either made or received more easily and promptly using digital technology. Because of that, it has been hard for digital images to gain value as a work of art. But after NFT technology was developed and then applied to digital images, we have come to distinguish the original from the copy of it. People are trying various ways to allow digital images to be acknowledged as art, and changing the nature of digital images that makes new paradigms in the history of art. Through NFT artworks rising as a new style, this paper analyzed and investigated the new properties and changing characteristics of digital images in order to anticipate the characteristics of artworks that the public produces, enjoys, and consumes. This study is grounded on experimental analysis methods, and this author expects that it can contribute to figuring out which kinds of visual culture and artworks digital image is influencing currently from various perspectives.