• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.197-198
• /
• 2021

반려동물에 대한 인식변화와 고령화, 저출산 문제로 반려동물을 키우는 사람이 계속해서 증가하고 있다. 하지만 반려동물을 유기하는 경우도 많아져 정부에서는 반려동물 등록제를 시행하여 동물 유기를 예방하고 있다. 그럼에도 불구하고 동물 등록 절차의 번거로움과 부작용 우려로 인해 많은 사람이 등록을 하고 있지 않는 실태이다. 본 논문에서는 딥러닝 이미지 분석을 활용한 동물 외형분석 기술을 제안한다. 제안하는 기술은 동물 이미지에서 특징점 추출을 위해 CNN과 구글에서 제공하는 딥러닝 프레임워크인 텐서플로우(TensorFlow)를 활용하며 동물의 외형을 분석해 동물의 고유한 외형 정보를 얻을 수 있다. 이를 통해 각 개체를 특정할 수 있어 현재 시행되고 있는 동물 등록방법을 대체하여 동물 유기문제 해결에 기여할 것으로 기대한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.1C
• /
• pp.47-55
• /
• 2003

This paper proposes a composition method of mosaic image from the compressed MPEG-2 video stream, in which the displacement between successive frames according to the camera operation is estimated directly from the information involved in the stream. In the proposed method. the approximated optical flow is constructed from motion vectors of macro blocks, and it is used to determine the parameters of the displacements according to the camera operation associated with pan and tilt. The extracted parameters are used to determine the geometric transform of successive video frames in order to construct a mosaic image. The construction of mosaic uses several blending techniques including the one proposed by Nichols in which an analytic weight is used to determine pixel values. Through the experiment, the blending technique based on analytic weights was superior to the others such as averaging and median-based techniques. It provided more smooth changes in background and made use of instantaneous frame information to construct a mosaic. The mosaic in the paper puts the emphasis on the reduction of computation because it is constructed from the motion vectors included in the compressed video without decoding and recalculating exact optical flows. The constructed mosaic can be used in the retrieval of the compressed video as the representative frame of a shot.

• Journal of Digital Convergence
• /
• v.10 no.11
• /
• pp.243-251
• /
• 2012

Digital items, considered as virtual assets, include avatars, accessories for the avatars, digital wallpapers, and game items, etc. The objective of this study is to examine the factors influencing the purchase of digital items. Factors, based upon Uses and Gratifications theory, including image making, self-expression, social awareness and fun-seeking, are introduced as salient variables for purchasing digital items. In addition, social identification and flow are also considered as key motivators. Statistical results indicates that social identification affects both flows and the intension to purchase digital items, and then flow next influences intension to purchase. It was also found that motives based upon Uses and Gratifications theory influences social identification, but have no impact on flow. As a conclusion, the academic and practical implications of these findings are also discussed.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.313-321
• /
• 2022

As 5G is getting developed, people are getting interested in immersive content. Some predicts that immersive content may be implemented in real life such as holograms, which were only possible in movies. Holograms, which has been studied for a long time since Dennis Gabor published the basic theory in 1948, are constantly developing in a new direction with digital technology. It is developing from a traditional optical hologram, which is produced by recording the interference pattern of light to a computer generated hologram (CGH) and a digital hologram printer. In order to produce a hologram using a digital hologram printer, holographic element (Hogel) image must first be created using multi-view images. There are a method of directly photographing an actual image and a method of modeling an object using 3D graphic production tool and rendering the motion of a virtual camera to acquire a series of multi-view images. In this paper, we propose a new method of getting image, which is one of the visual effect, VFX, producing multi-view images using chroma key composition. We shoot on the green screen of actual object, suggest the overall workflow of composition with 3D computer graphic(CG) and explain the role of each step. We expected that it will be helpful in researching a new method of image acquisition in the future if all or part of the proposed workflow to be applied.

• Journal of Software Assessment and Valuation
• /
• v.15 no.1
• /
• pp.63-70
• /
• 2019

These days, as Interest in Image recognition with deep learning is increasing, there has been a lot of research in image recognition using deep learning. In this study, we propose a system for classifying rocks through rock images of 18 types of rock(6 types of igneous, 6 types of metamorphic, 6 types of sedimentary rock) which are addressed in the high school curriculum, using CNN model based on Tensorflow, deep learning open source framework. As a result, we developed a classifier to distinguish rocks by learning the images of rocks and confirmed the classification performance of rock classifier. Finally, through the mobile application implemented, students can use the application as a learning tool in classroom or on-site experience.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.594-596
• /
• 2000

인터넷 환경에서 프록시(proxy)는, 효율적인 데이터의 전송을 위해 다양한 클라이언트 장치들과 WWW 서버들간의 다리역할을 수행한다. 특히, 최근의 인터넷 환경은 이미지 같은 복잡하고 대량의 크기를 갖는 데이터 전송을 많이 요구하고 있으므로, 클라이언트 환경에 맞는 최선의 화질과 최소의 지연시간을 갖도록 데이터를 변환하여 재전송하는 트랜스코딩(transcoding)이 중요시되고 있다. 본 연구에서는 트랜스코딩을 수행하는 다수의 프록시들이 존재할 때, 클라이언트의 요구(request)와 장치(device), 또는 네트워크의 여러 가지 조건에 가장 적합한 프록시를 선택할 수 있는 수리적인 모델을 제안한다. 이러한 수리적 모델은 경로연결(redirector)내에서 동작하는 알고리즘으로서, 예상되는 지연시간과 오버플로우의 가능성을 최소화할 수 있는 최선의 프록시를 클라이언트와 서버사이에 연결함으로서 이미지 전송에 있어서 더 큰 효과를 얻을 수 있다. 실험 결과, 전체적인 지연시간을 줄일 수 있을 뿐만 아니라 클라이언트에게 적절한 양과 질의 데이터 전송효과를 가진다.

• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.129-141
• /
• 2010

In this paper, we present a wearable intelligent device based on multi-sensor for monitoring human activity. In order to recognize multiple activities, we developed activity recognition algorithms utilizing an image sensor and a 3-axis accelerometer sensor. We proposed a grid?based optical flow method and used a SVM classifier to analyze data acquired from multi-sensor. We used the direction and the magnitude of motion vectors extracted from the image sensor. We computed the correlation between axes and the magnitude of the FFT with data extracted from the 3-axis accelerometer sensor. In the experimental results, we showed that the accuracy of activity recognition based on the only image sensor, the only 3-axis accelerometer sensor, and the proposed multi-sensor method was 55.57%, 89.97%, and 89.97% respectively.

• Fashion & Textile Research Journal
• /
• v.16 no.6
• /
• pp.908-920
• /
• 2014

As social networking service (SNS) users' needs and wants have become more diverse, SNS is designed to provide various services and functions. As a result, an image based SNS with the purpose of sharing various interests has emerged. More and more fashion companies are using image based SNS to use it as a medium to better communicate with their customers. This study investigates the effect of usage motivation of image based SNS with the emotion of pleasure as the mediator and its impact towards flow and brand attitude. In order to verify the research model and to test the proposed hypotheses, we conducted a pilot test on 8 image based SNS heavy users, and followed through with 215 questionnaires which were collected via online survey. The results of this study are as follows. Each usage motivation of image based SNS had significant effect on each pleasure. The visual impact had a positive effect on sensory pleasure and the common interest significantly influenced on user's affective preference. Curating, simplicity and interconnecting had a positive effect on cognitive pleasure. Affective and cognitive pleasures except sensory pleasure positively impacted the user on flow. The cognitive pleasure had a positive effect on the brand attitude. Lastly, flow had a positive effect on the brand attitude. This study is the foundation of the image based SNS academically in the new media research. Furthermore, it suggests managerial implications of a company to provide effective marketing strategy to make the best use of image based SNS.

• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.98-105
• /
• 2011

Recent advances in computer technologies support real-time image processing and special effects on personal computers. This paper presents and analyzes a real-time interactive video system. The motivation of this work is to realize an artistic concept that aims at transforming the timeline visual variations in a video of sea water waves into sound in order to provide an audience with an experience of overlapping themselves onto the nature. In practice, the video of sea water waves taken on a beach is processed using an optical flow algorithm in order to extract the information of visual variations between the video frames. This is then masked by the silhouette of an audience and the result is projected on a gallery space. The intensity information is extracted from the resulting video and translated into piano sounds accordingly. This work generates an interactive space realizing the intended concept.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.849-857
• /
• 2023

Volumetric Studio is catalyzing the expansion of the XR content market. Consequently, there is a rising demand for in-depth research on volumetric capture technology. This research delves into the methodology and outcomes of capturing dancers' movements in the form of 3D video images. Furthermore, this research examines the practical applications of volumetric capture technology by assessing the infrastructure and operational workflow of the studio specializing in this domain, aiming to derive significant findings. Notably, this research highlights constraints associated with video image distortion and extended rendering durations within Volumetric Studio system.