• Journal of Korea Society of Industrial Information Systems
• /
• v.10 no.3
• /
• pp.15-20
• /
• 2005

Since the invention of Web, it became part of our daily life replacing the routine information search and effecting many activities which otherwise could have been done off-line without it. It was a natural evolution of the web technology, which had started out as a simple test based pattern matching, to be based on the optimized match process for its multi-media Web environment, like still images, music and movies that we are to face today. In this paper, we proposed and implemented the model which the multimedia resources can be efficiently shared in semantic web. After converting multimedia resource information(metadata) into RDF, for efficient management, the model separate and allotment actual multimedia resource and corresponding metadata changed to RDF to each server. The proposed model could be applied in all multimedia resources. For easy explanation and implementation, however, we applied it to the digital photograph in example.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.882-885
• /
• 2014

이미지 혹은 영상에 대한 자동 태깅은 해당 콘텐츠에 대한 추가적인 정보를 자동으로 시스템에 제공하는 기술로써 영상 인식, 콘텐츠 매시업, 정보 검색 등 다양한 기술/서비스 분야에서 여러 목적으로 활용되고 있다. 특히, 방송 콘텐츠는 많은 양의 정보를 제한된 영역 및 시간에 축약하여 담고 있기 때문에 영상 처리 기술을 통한 객체 인식이나, 콘텐츠 매시업, 추천 서비스 등의 성능 향상을 위해 자동 혹은 수동 태깅을 통한 정보 제공이 요구된다. 본 논문에서는 블로그를 이용한 프레임 단위의 방송 콘텐츠 태깅 기술을 제안한다. 제안하는 기술은 기존의 콘텐츠 단위의 정보 제공이나, 수동 태깅 된 정보를 제공하는 기술들과 달리, 영상의 각 프레임에 대한 자동 태깅을 목표로 한다. 제안하는 방법은 거리 학습을 통해 영상의 각 프레임이 가지는 특성을 고려한 모델을 구축한 후, 이를 토대로 영상의 프레임들과 블로그의 이미지를 매칭한다. 매칭된 결과를 기반으로 특정 블로그는 영상 내 특정 프레임 구간에 태깅 된다. 제안한 방법은 이미지 매칭 성능을 측정하여 평가하였다. 블로그 이미지에 대해 Top 1 매칭 프레임을 살펴본 결과, 70%의 정확률을 보였다. 소프트 매칭(Top n)의 경우, 최대 90%의 성능을 얻을 수 있음을 실험을 통해 알 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.329-346
• /
• 2022

Recently, as the market for short form videos (Instagram, TikTok, YouTube) on social media has gradually increased, research using them is actively being conducted in the artificial intelligence field. A representative research field is Video to Shop, which detects fashion products in videos and searches for product images. In such a video-based artificial intelligence model, product features are extracted using convolution operations. However, due to the limitation of computational resources, extracting features using all the frames in the video is practically impossible. For this reason, existing studies have improved the model's performance by sampling only a part of the entire frame or developing a sampling method using the subject's characteristics. In the existing Video to Shop study, when sampling frames, some frames are randomly sampled or sampled at even intervals. However, this sampling method degrades the performance of the fashion product search model while sampling noise frames where the product does not exist. Therefore, this paper proposes a sampling method MF (Missing Fashion items on frame) sampler that removes noise frames and improves the performance of the search model. MF sampler has improved the problem of resource limitations by developing a keyframe mechanism. In addition, the performance of the search model is improved through noise frame removal using the noise detection model. As a result of the experiment, it was confirmed that the proposed method improves the model's performance and helps the model training to be effective.

• Smart Media Journal
• /
• v.3 no.4
• /
• pp.28-34
• /
• 2014

Recently the depth-image-based rendering (DIBR) method is usually used in 3D image application filed. Virtual view image is created by using a known view with associated depth map to make a virtual view point which did not taken by the camera. But, disocclusion area occur because the virtual view point is created using a depth image based image 3D warping. To remove those kind of disocclusion region, many hole filling methods are proposed until now. Constant color region searching, horizontal interpolation, horizontal extrapolation, and variational inpainting techniques are proposed as a hole filling methods. But when using those hole filling method some problem occurred. The different types of annoying artifacts are appear in texture region hole filling procedure. In this paper to solve those problem, the multi-directional extrapolation method is newly proposed for efficiency of expanded hole filling performance. The proposed method is efficient when performing hole filling which complex texture background region. Consideration of directionality for hole filling method use the hole neighbor texture pixel value when estimate the hole pixel value. We can check the proposed hole filling method can more efficiently fill the hole region which generated by virtual view synthesis result.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.5
• /
• pp.1677-1684
• /
• 2010

Recently, due to the development of mobile phone and supply of smart phone, many contents have been developed. Especially, since the small-sized cameras are equiped in mobile devices, people are interested in the image based contents development, and it also becomes important part in their practical use. Among them, the character recognition system can be widely used in the applications such as blind people guidance systems, automatic robot navigation systems, automatic video retrieval and indexing systems, automatic text translation systems. Therefore, this paper proposes a system that is able to extract text area from the natural images captured by smart phone camera. The individual characters are recognized and result is output in voice. Text areas are extracted using Adaboost algorithm and individual characters are recognized using error back propagated neural network.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1273-1284
• /
• 2016

In this paper, we analyzed the patents on machine learning using keyword network analysis and clique analysis. To construct a keyword network, important keywords were extracted based on the TF-IDF weight and their association, and network structure analysis and clique analysis was performed. Density and clustering coefficient of the patent keyword network are low, which shows that patent keywords on machine learning are weakly connected with each other. It is because the important patents on machine learning are mainly registered in the application system of machine learning rather thant machine learning techniques. Also, our results of clique analysis showed that the keywords found by cliques in 2005 patents are the subjects such as newsmaker verification, product forecasting, virus detection, biomarkers, and workflow management, while those in 2015 patents contain the subjects such as digital imaging, payment card, calling system, mammogram system, price prediction, etc. The clique analysis can be used not only for identifying specialized subjects, but also for search keywords in patent search systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.1
• /
• pp.55-68
• /
• 2012

In this paper, we propose a novel method to solve the problem of excessive segmentation out of the method of segmenting regions from an image using Homogeneity Threshold($H_T$). The algorithm of the previous image segmentation based on $H_T$ was carried out region growth by using only the center pixel of selected window. Therefore it was caused resulting in excessive segmented regions. However, before carrying region growth, the proposed method first of all finds out whether the selected window is homogeneity or not. Subsequently, if the selected window is homogeneity it carries out region growth using the total pixels of selected window. But if the selected window is not homogeneity, it carries out region growth using only the center pixel of selected window. So, the method can reduce remarkably the number of excessive segmented regions of image segmentation based on $H_T$. In order to show the validity of the proposed method, we carried out multiple experiments to compare the proposed method with previous method in same environment and conditions. As the results, the proposed method can reduce the number of segmented regions above 40% and doesn't make any difference in the quality of visual image when we compare with previous method. Especially, when we compare the image united with regions of descending order by size of segmented regions in experimentation with the previous method, even though the united image has regions more than 1,000, we can't recognize what the image means. However, in the proposed method, even though image is united by segmented regions less than 10, we can recognize what the image is. For these reason, we expect that the proposed method will be utilized in various fields, such as the extraction of objects, the retrieval of informations from the image, research for anatomy, biology, image visualization, and animation and so on.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1343-1350
• /
• 2019

Converting boundary images to time-series makes it feasible to perform boundary matching even on a very large image database, which is very important for interactive and fast matching. In recent research, there has been an attempt to perform fast matching considering partial denoising by converting the boundary image into time series. In this paper, to improve performance, we propose an index-building method considering all possible arbitrary denoising parameters for removing arbitrary partial noises. This is a challenging problem since the partial denoising boundary matching must be considered for all possible denoising parameters. We propose an efficient single index-building algorithm by constructing a minimum bounding rectangle(MBR) according to all possible denoising parameters. The results of extensive experiments conducted show that our index-based matching method improves the search performance up to 46.6 ~ 4023.6 times.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.20 no.5
• /
• pp.10-16
• /
• 2002

디지털 기술의 급속한 발전에 의한 디지털 방송의 도입은 방송환경에 커다란 변혁을 초래하고 있다. 기술의 발전은 방송, 통신, 컴퓨터를 융합시킨 새로운 미디어 서비스를 등장시키고 있으며, 이러한 미디어의 융합은 지금까지 독자적인 영역에서 발전하여 오던 각각의 미디어들이 가지고 있는 한계성 또는 단점을 상호보완적으로 개선함으로써 서비스 능력을 대폭적으로 향상시키는 방향으로 전개되고 있다. 이와같은 디지털 시대의 대변혁은 멀티미디어 서비스를 그 중심축으로 하고 있으며, 이른바 방송통신 융합시대의 경쟁력 있는 서비스를 도입하기 위한 미디어간, 국가간의 경계영역을 초월한 글로벌 경쟁체제가 급속히 진전되어 가고 있다. 이와 같은 미디어의 융합 현상에 따라 제작 환경도 새로운 디지털 방송 서비스를 효율적으로 지원하도록 전환되어야 한다. 디지털 방송의 특징인 고품질 및 다채널 시대를 맞아 방송 콘텐츠의 재활용도를 높이는 것은 매우 중요하며, 데이터 방송, 인터넷 방송 등 다양한 기능의 서비스를 도입하기 위해선 제작 체계의 개선이 뒷받침되어야 한다. 따라서 본 논문에서는 새로운 제작 환경에 대해서 살펴보고자 한다. 특히, 컴퓨터 기반의 제작 환경 구축에 핵심 요소인 넌리니어 편집시스템과 방송 콘텐츠를 효율적으로 관리하고 재활용할 수 있는 디지털 아카이브에 대해 소개하고자 한다. 테이프 대신 하드디스크를 기록 매체로 하는 넌리니어(non-linear) 시스템의 등장에 따라 방송 프로그램 제작에 대한 새로운 개념의 정립이 필요하게 되었으며, 이를 근간으로 하는 새로운 프로그램 제작환경, 즉 네트워크에 의해 컴퓨터와 데이터베이스를 연결하여 제작으로부터 송출가지 통합관리가 가능한 새로운 방송 프로그램 제작환경, 이른바 멀티미디어 제작환경을 구축하는 것이 디지털 방송 시대의 방송 사업자에게 가장 중요한 과제중의 하나가 되었다. 멀티미디어 제작환경을 구축함으로써 영상, 음성 및 다양한 부가 데이터를 포함하는 멀티미디어 프로그램을 편리하게 제작할 수 있으며, 데이터베이스로부터 필요한 영상 이미지를 자유롭게 합성, 조작하는 등, 매우 다양하고 편리한 제작기법을 활용할 수 있다. 또한 멀티미디어를 응용한 제작 분야로서 컴퓨터 그래픽스 기술은 방송의 사전제작에 커다란 기여를 하고 있으며, 이미 선거방송을 비롯한 여러가지 프로그램은 가상스튜디오와 가상캐릭터 기술을 활용하여 제작하고 있다. 방송사업자는 이러한 멀티미디어 제작시스템을 근간으로 영상검색, 영상 합성, 스크립트 편집, 가상현실 응용 등 고도의 제작 기법을 활용함으로써 사용자 친화성, 다이나믹한 표현, 실시간, 대화성을 특징으로 하는 다양한 멀티미디어 서비스를 시청자에게 제공할 수 있을 것이다.