• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.1-11
• /
• 2020

Image-based virtual try-on (VTON) is becoming popular for online apparel shopping, mainly because of not requiring 3D information for try-on clothes and target humans. However, existing 2D algorithms, even when utilizing advanced non-rigid deformation algorithms, cannot handle large spatial transformations for complex target human poses. In this study, we propose a 3D clothing reconstruction method using a 3D human body model. The resulting 3D models of try-on clothes can be more easily deformed when applied to rest posed standard human models. Then, the poses and shapes of 3D clothing models can be transferred to the target human models estimated from 2D images. Finally, the deformed clothing models can be rendered and blended with target human representations. Experimental results with the VITON dataset used in the previous works show that the shapes of reconstructed clothing are significantly more natural, compared to the 2D image-based deformation results when human poses and shapes are estimated accurately.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.901-909
• /
• 2015

In this paper, to build a parallel corpus between Korean and English in Wikipedia. We proposed a method to find similar sentences based on language resources and topic modeling. We first applied language resources(Wiki-dictionary, numbers, and online dictionary in Daum) to match word sequentially. We construct the Wiki-dictionary using titles in Wikipedia. In order to take advantages of the Wikipedia, we used translation probability in the Wiki-dictionary for word matching. In addition, we improved the accuracy of sentence similarity measuring method by using word distribution based on topic modeling. In the experiment, a previous study showed 48.4% of F1-score with only language resources based on linear combination and 51.6% with the topic modeling considering entire word distributions additionally. However, our proposed methods with sequential matching added translation probability to language resources and achieved 9.9% (58.3%) better result than the previous study. When using the proposed sequential matching method of language resources and topic modeling after considering important word distributions, the proposed system achieved 7.5%(59.1%) better than the previous study.

• Journal of KIISE:Databases
• /
• v.37 no.4
• /
• pp.209-219
• /
• 2010

Online social network services that are rapidly growing recently store tremendous data and analyze them for many research areas. To enhance the effectiveness of information, companies or public institutions publish their data and utilize the published data for many purposes. However, a social network containing information of individuals may cause a privacy disclosure problem. Eliminating identifiers such as names is not effective for the privacy protection, since private information can be inferred through the structural information of a social network. In this paper, we consider a new complex attack type that uses both the content and structure information, and propose a model, $\ell$-degree diversity, for the privacy preserving publication of the social network data against such attacks. $\ell$-degree diversity is the first model for applying $\ell$-diversity to social network data publication and through the experiments it shows high data preservation rate.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1306-1313
• /
• 1999

본 연구는 인터넷 기반 공유가상공간에서 시스템의 확장성을 유지하기 위하여 이동객체를 대상으로 하는 이벤트 필터링 기법을 제안하고자 한다. 제안된 다중격자 모델 기법은 이동객체의 경로 상에서 대표적인 이벤트를 샘플링하는 방식을 사용한다. 이 방식은 메시지 트래픽의 양을 동적으로 조절하기 위하여 이동객체 간의 관심정도 정보를 수치적으로 변환하여 이벤트 갱신빈도에 반영한다. 대량의 이동객체를 생성하여 제안된 기법을 적용한 성능평가 실험에서 기존의 방식에 비하여 평균 메시지 전송량이 50%이상 감소하는 것으로 확인할 수 있었다. 다중격자 모델은 참여자의 수와 메시지 트래픽 상황에 따라 가상환경의 공유 QoS를 동적으로 조절할 수 있으며, 인터넷 상에서 다수 사용자를 위한 3차원 가상사회 구축 및 온라인 네트워크 게임 개발 등에 활용될 수 있을 것이다.Abstract This paper proposes an event filtering technique that can dynamically control a large amount of event messages produced by moving objects like avatars or autonomous objects in a distributed virtual environment. The proposed multi-level grid model technique uses the method that extracts the representative events from the paths of moving objects. For dynamic control of message traffics, this technique digitizes the DOIs of the avatars and reflects the interest information controlling the frequency of message transmission. For the performance evaluation, a large number of moving objects were created and the model was applied to these avatar groups. In the experiments, more than 50% of messages have been reduced in comparison with the existing AOI-based filtering techniques. The proposed technique can dynamically control the QoS in proportion to the number of users and the amount of messages where a large number of users share a virtual space. This model can be applied to the development of 3D collaborative virtual societies and multi-user online games in the Internet.

• Journal of KIISE:Software and Applications
• /
• v.29 no.7
• /
• pp.487-497
• /
• 2002

As component-based reuse technology is being introduced, software components are more likely distributed on Internet. In order to promote Internet based on-line distribution, distribution model of components should be defined and a distribution system should also be constructed. Furthermore, to run the component distribution system effectively, a logical and practical schema for classifying components should be defined and standardized. In this paper, we propose a classification schema using BNF and representation standards of components using six different views. To verity the effectiveness of proposed classification and compare to other classification methods, we assess proposed classification by measuring hit ratio and correctness. By using the proposed methods that support six views on components, the search for right components and registering new components can be done more effectively.

• The Journal of the Korea Contents Association
• /
• v.6 no.6
• /
• pp.16-25
• /
• 2006

Most water tanks operating have been managed by people's five senses. A human material resource have been wasted awfully at this. In the present study, we suggest the wireless integrated system for managing water tank of reducing the wastage human resources and on-line real time managing efforts of water tanks. Water level sensor works the pump sending the data from water tank control to the wireless control on sensing water level. At this time, every kind data which happens in the water tank transmits the line transmission modem. Data to be received from the line transmission modem is stored at the database after we record the logs by each hour. We display the result to the web pages, after checking the pump motion, the pump error, the water level, the solar battery error, the chemicals, and the telephone line to the foundation data to be saved. Furthermore, this paper suggests empirical applications of the proposed wireless integrated system for managing water tank in order to verify its feasibility.

• Korean Journal of Remote Sensing
• /
• v.18 no.6
• /
• pp.359-367
• /
• 2002

In this paper, a new embedded wavelet packet image coder algorithm is proposed for an effective image coder using correlation between partitioned coefficients. This new algorithm presents parent-child relationship for reducing image reconstruction error using relations between individual frequency sub-bands. By parent-child relationship, every coefficient is partitioned and encoded for the zerotree data structure. It is shown that the proposed wavelet packet image coder algorithm achieves low bit rates and rate-distortion. It also demonstrates higher PSNR under the same bit rate and an improvement in image compression time. The perfect rate control is compared with the conventional method. These results show that the encoding and decoding processes of the proposed coder are simpler and more accurate than the conventional ones for texture images that include many mid and high-frequency elements such as aerial and satellite photograph images. The experimental results imply the possibility that the proposed method can be applied to real-time vision system, on-line image processing and image fusion which require smaller file size and better resolution.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.135-140
• /
• 2021

In this paper, we propose an on-line mechanism that simultaneously detects cracks and profiling pavement blocks to detect the displacement of ground surface adjacent to the excavation in the urban area. The proposed method utilizes a 2D laser to profile the information about pavement blocks including the depth and distance among them. In particular, it is designed to enable the detection of cracks and portholes at runtime. For the experiment, real data was collected through Gocator, and trainng was carried out using Faster R-CNN. The performance evaluation shows that our detection precision and recall are more than 90% and the pavement blocks are profiled at the same time. Our proposed mechanism can be used for monitoring management to quantitatively detect the level of excavation risk before a large-scale ground collapse occurs.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.1-8
• /
• 2021

In online meetings and classes using webcams, the chromakey technique is a very necessary part to produce content. We proposed a technology that enables background synthesis without using a cloth for chromakey. The proposed method consists of three steps: an HSI image conversion step, a step of detecting a region changed from a background, and a step of replacing the background region with a chromakey and applying it. In the input video, the block average image of each frame is calculated, and the difference between the block average image of the background image and the block average image of the input image is used to detect the change area. The developed chromakey effect technology uses a technique of acquiring a background image without an object from a single camera and extracting only an object by distinguishing the moving object and the background. The proposed method is not only capable of processing even if the background has a variety of colors, but also has the seamless processing of the boundary lines of objects.

• Journal of Science Education
• /
• v.45 no.2
• /
• pp.201-218
• /
• 2021

The purpose of this study is to investigate qualitatively two cases of general citizens' scientific participation and activities responding to fine dust problem. The processes of their scientific actions were investigated and categorized inductively based on three stages: problem recognition stage, information collection and analysis stage, and sharing and spreading stage. As a result, in the 'problem recognition' stage, two participants recognized the seriousness of the fine dust problem as they felt a threat to their health and began to act practically by questioning the accuracy of public data. In the 'information collection and analysis' stage, a participant collected as much information as possible and compared them in order to obtain more accurate information for her situation. On the other hand, another participant conducted various experiments in person to get the information which is appropriate to his situation. Finally, in the 'Sharing and Spreading' stage, both participants created and shared various materials based on online environment, and continued their activities with a sense of contribution through others assistance. Educational implications are discussed in terms of civic science education and scientific literacy.