• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.892-911
• /
• 2019

Biometric recognition systems have been widely used for information security. Among the most popular biometric traits, there are fingerprint and face due to their high recognition accuracies. However, the security system that uses face recognition as the login method are vulnerable to face-spoofing attacks, from using printed photo or video of the valid user. In this study, we propose a fast and robust method to detect face-spoofing attacks based on the analysis of spatial frequency differences between the real and fake videos. We found that the effect of a spoofing attack stands out more prominently in certain regions of the 2D Fourier spectra and, therefore, it is adequate to use the information about those regions to classify the input video or image as real or fake. We adopt a divide-conquer-aggregate approach, where we first divide the frequency domain image into local blocks, classify each local block independently, and then aggregate all the classification results by the weighted-sum approach. The effectiveness of the methodology is demonstrated using two different publicly available databases, namely: 1) Replay Attack Database and 2) CASIA-Face Anti-Spoofing Database. Experimental results show that the proposed method provides state-of-the-art performance by processing fewer frames of each video.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2345-2358
• /
• 2022

This paper presents a method to generate stained-glass animation from video inputs. The method initially segments an input video volume into several regions considered as fragments of glass by mean-shift segmentation. However, the segmentation predominantly results in over-segmentation, causing several tiny segments in a highly textured area. In practice, assembling significantly tiny or large glass fragments is avoided to ensure architectural stability in stained glass manufacturing. Therefore, we use low-frequency components in the segmentation to prevent over-segmentation and subdivide segmented regions that are oversized. The subdividing must be coherent between adjacent frames to prevent temporal artefacts, such as flickering and the shower door effect. To temporally subdivide regions coherently, we obtain a panoramic image from the segmented regions in input frames, subdivide it using a weighted Voronoi diagram, and thereafter project the subdivided regions onto the input frames. To render stained glass fragment for each coherent region, we determine the optimal match glass fragment for the region from a dataset consisting of real stained-glass fragment images and transfer its color and texture to the region. Finally, applying lead came at the boundary of the regions in each frame yields temporally coherent stained-glass animation.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• The Journal of Art Theory & Practice
• /
• no.14
• /
• pp.187-215
• /
• 2012

In recent studies of art historical methodology, such as Critical Terms for Art History and The Art of Art History, subjectivity, identity, abjection, and other terms have been placed safely in the genealogy of contemporary art history. This paper questions the contemporaneity in the story of contemporary art in our time in relation to two other critical terms that have been regularly cited by contemporary critics, not only in Euro-American fields but also in Korea. The terms are postmedium and postproduction, respectively, as used by Rosalind Krauss and Nicolas Bourriaud. This paper stems from the critical condition in which art criticism and theory have their power in the rise of neo-liberalism. But this paper does not deal with the contemporary as a chronological term for art history but rather examines the three critical terms-contemporaneity, post-medium, and postproduction-that have garnered scholarly attention. I would like to put aside postmodernism for the moment; I don't disregard the postmodern condition although the death of postmodern critical terms has resulted in the loss of its polemical power in art worlds such as in exhibitions, etc. To look at "the postproduction in the age of post-medium age after postmodernism," I first explore Krauss's notion of post-medium because, unlike media artists like Lev Manovich and Peter Weibel, Krauss's post-medium condition is different and insists on medium specificity. In this sense, Krauss has turned out to be another Greenberg in disguise. For her, photography and video are expanded mediums after Greenberg, because Krauss has spent her life explicating those mediums. Under the Cup, her recent publication, came out in 2011, and discusses her desire to defend medium-specificity against the intermedia of installation art found ubiquitously in international exhibitions and biennales. Her usage of post-medium has been taken up by Weibel as postmedia in a broader sense. But whether the post-medium condition or the postmedia age, we nonetheless enter the new age of the contemporary. Consequently, this paper questions what constitutes contemporaneity in our times. It is said that there is nothing new on earth, yet I find original artistic strategies among the younger generation in the postmedia age. The contemporary justifies its place in art fields and criticism by keeping its distance from postmodernism although we still find the remnants of postmodern artistic practices and theoretical foundations. By looking at materials written by Terry Smith, I would like to examine contemporaneity as a rhetoric where artists, critics, and curators endeavor to set up a new spirit of criticism, distant from the past of modernism and postmodernism. In discussions, modernism and postmodernism act as catalysts interacting with each other while justifying their own place. In conclusion, my paper reaches to delineate where the contemporary finds its place among artists' responses and working methods. It explores the postproduction of the Internet and the World Wide Web generations, where images become data rather than representation (of modernism) and appropriation (of postmodernism). This paper analyzes Bourriaud's text, as well as relevant artists like Pierre Huyghe, Liam Gillick, and others. By examining the aforementioned critical terms, I would like to reconsider our own contemporary art in Korea, especially among young artists influenced by digital media and the World Wide Web in the 1990s.

• Journal of Broadcast Engineering
• /
• v.15 no.4
• /
• pp.527-539
• /
• 2010

Most video coding systems use YCbCr color space for their inputs, but RGB space is more preferred in the field of high fidelity video because the compression gain from YCbCr becomes disappeared in the high quality operation region. In order to improve the coding performance of RGB video signal, this paper presents an adaptive frequency-selective weighted prediction algorithm. Based on the sign agreement and the strength of frequency-domain correlation of residual color planes, the proposed scheme adaptively selects the frequency elements as well as the corresponding prediction weights for better utilization of inter-plane correlation of RGB signal. Experimental results showed that the proposed algorithm improves the coding gain of around 13% bitrate reduction, on average, compared to the common mode of 4:4:4 video coding in the state-of-the-art video compression standard, H.264/AVC.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.2080-2089
• /
• 2015

In 3D video compression, a disparity vector (DV) pointing a corresponding block position in an adjacent view is a key coding tool to exploit statistical correlation in multi-view videos. In this paper, neighboring block-based disparity vector (NBDV) is shown with detail algorithm descriptions and coding performance analysis. The proposed method derives a DV from disparity motion vector information, obtained from spatially and temporally neighboring blocks, and provides a significant coding gain about 20% BD-rate saving in a texture-video-first-coding scheme. The proposed DV derivation method is adopted into the recent 3D video coding standards such as 3D-AVC and 3D-HEVC as the state-of-the-art DV derivation method.

• Journal of Korean Theatre Studies Association
• /
• no.53
• /
• pp.167-202
• /
• 2014

When video composes mise-en-scene during the performance, it reflects the aspect of contemporary image culture, where the individual as creator joins in the image culture through the device of cell phone and computer remediating the former video technology. It also closely related with the contemporary theatre culture in which 1960's and 1970's video art was weaved into the contemporary performance theatre. With these cultural background, theatre practitioners regarded media-friendly mise-en-scene as an alternative facing the cultural landscape the linear representational narrative did not correspond to the present culture. Nonetheless, it can not be ignored that video in the performance theatre is remediating its historical function: to criticize the social reality. to enrich the aesthetic or emotional reality. I focused video in the performance theatre could feature the object with the image by realizing the realtime relay, emphasizing the situation within the frame, and strengthening the reality by alluding the object as a gesutre. So I explored its two historical manuel. First, video recorded the spot, communicated the information, and arose the audience's recognition of the object to its critical function. Second, video in performance theatre could redistribute perceptual way according to the editing method like as close up, slow motion, multiple perspective, montage and collage, and transformation of the image to the aesthetic function. Reminding the historical function of video in contemporary performance theatre, I analyzed two shows, Schaubuhne's Hamlet and Lenea de Sombra's Amarillo which were introduced to Korean audiences during the 2010 Seoul Theatre Olympics. It is known to us that Ostermeir found real social reality as a text and made the play the context. In this, he used video as a vehicle to penetrate the social reality through the hero's perspective. It is also noteworthy that Ostermeir understood Hamlet's dilemma as these days' young generation's propensity. They delayed action while being involved in image culture. Besides his use of video in the piece revitalized the aesthetic function of video by hypermedial perceptual method. Amarillo combined documentary theatre method with installation, physical theatre, and video relay on the spot, and activated aesthetic function with the intermediality, its interacting co-relationship between the media. In this performance theatre, video has recorded and pursued the absent presence of the real people who died or lost in the desert. At the same time it fantasized the emotional aspect of the people at the moment of their death, which would be opaque or non prominent otherwise. As a conclusion, I found the video in contemporary performance theatre visualized the rupture between the media and perform their intermediality. It attempted to disturb the transparent immediacy to invoke the spectator's perception to the theatrical situation, to open its emotional and spiritual aspect, and to remind the realities as with Schaubuhne's Hamlet and Lenea de Sombra's Amarillo.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.727-741
• /
• 2022

This article focused on contemporary American animation since the 1990s and later detailed clues to the theory that contemporary pop art style influenced contemporary American animation art creation expression and contemporary American animation. Knowing why American animation swept the world summarizes the art creation characteristics of modern American animation. After a combination of theoretical and actual animation works, the main manifestations of the postmodern pop art style in contemporary American animation: exaggerated and superficial shapes highlight character characteristics; rebellious colors reconstruct emotional perception; creation impacts the mass media-dependence; bizarre collage and repetition, embodying the postmodern pop spirit of jokes and spoofs, Etc. Through this, it is expected that the current analysis of American animation will provide new innovative ideas for domestic animation design and increase the competitiveness of domestic animation in international video animation.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.165-171
• /
• 2024

The processes of society's informatization and digitalization necessitate the widespread use of new pedagogical technologies. Through these technologies, comprehensive disclosure of didactic functions of new methods of educational activity and the realization of the potential and creative potential. The use of information and computer multimedia technologies in teaching music art is especially relevant in the intensification of the development of interactive technologies, the transition to mixed forms of learning, and a period of socio-economic and sociopolitical upheavals. The study aims to substantiate the theoretical and applied principles of the analysis of multimedia technology learning musical art in modern conditions and assess the status and trends in their use in conducting educational activities. The study uses general scientific and unique methods of economic analysis, in particular, analysis and synthesis, analogy and comparison, generalization and systematization, and graphic ways. Regarding the results of the study of multimedia technologies for teaching musical art in current conditions, it was found that they contribute to the development of the seeker's creative, creative, and cognitive activity, have a positive impact on learning material, and diversify the educational process. Multimedia technologies such as presentations, programs for watching a video, listening to audio, music and singing karaoke, electronic encyclopedias, and Internet resources are proven to be the most used in music education. They have several qualitative and quantitative advantages, manifested in the possibilities of audio-visual presentation of educational material and significantly higher information density. It is suggested to strengthen the use of such computer programs as Microsoft Word, Ahead Nero, Finale, Adobe Audition, Sound Forge, and Microsoft PowerPoint for musical art classes.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.247-256
• /
• 2014

"Artist Welfare Act" from the November 18, 2012 is being implemented. However, in the field of traditional culture and art the artists are the subject of a variety of policies by the newly launched Korean Artist Welfare Foundation Artists, but most of video production professionals are not aware of law enforcement and their legal status is ambiguous. This research raised the issue of poor video production workers welfare, and to seek the ways took a look at the key information of "Artist Welfare Act" and social issues. To this end, by in-depth interviews with video workers I analyzed the relationship between the parties, such as comments about the issues. Accordingly, a wide range of video production to reflect the welfare of workers in the "Artist Welfare Act" of the amendment shall be made. Above all, this should be reflected in measures to raise funds for artist welfare.