• Journal of Multimedia Information System
• /
• v.1 no.1
• /
• pp.55-67
• /
• 2014

Image topic and emotion analysis is an important component of online image retrieval, which nowadays has become very popular in the widely growing social media community. However, due to the gaps between images and texts, there is very limited work in literature to detect one image's Topics and Emotions in a unified framework, although topics and emotions are two levels of semantics that often work together to comprehensively describe one image. In this work, a unified model, Joint Topic/Emotion Multi-Modal Hierarchical Latent Dirichlet Allocation (JTE-MMHLDA) model, which extends previous LDA, mmLDA, and JST model to capture topic and emotion information at the same time from heterogeneous data, is proposed. Specifically, a two level graphical structured model is built to realize sharing topics and emotions among the whole document collection. The experimental results on a Flickr dataset indicate that the proposed model efficiently discovers images' topics and emotions, and significantly outperform the text-only system by 4.4%, vision-only system by 18.1% in topic detection, and outperforms the text-only system by 7.1%, vision-only system by 39.7% in emotion detection.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.581-590
• /
• 1996

In this paper, we describe the design consideration and the system configuration of the AV service terminal which supports the multiple services simultaneously. We present a service control scheme to support the multiple services in the limited network capability and system hardware capability. The system was developed in the form of an add-on board in a PC system based on N-ISDN BRI. Through the field test in domestic N-ISDN, we confirmed the interoperability and robustness of the system. At present, the developed system can basically support the videoconference service. Also the system can support the multimedia retrieval service, messaging service, fine transmission, and group working environment.

• Journal of Korea Multimedia Society
• /
• v.22 no.3
• /
• pp.374-385
• /
• 2019

A Web Crawler is a program, which is commonly used by search engines to find the new brainchild on the internet. The use of crawlers has made the web easier for users. In this paper, we have used unstructured data by structuralization to collect data from the web pages. Our system is able to choose the word near our keyword in more than one document using unstructured way. Neighbor data were collected on the keyword through word2vec. The system goal is filtered at the data acquisition level and for a large taxonomy. The main problem in text taxonomy is how to improve the classification accuracy. In order to improve the accuracy, we propose a new weighting method of TF-IDF. In this paper, we modified TF-algorithm to calculate the accuracy of unstructured data. Finally, our system proposes a competent web pages search crawling algorithm, which is derived from TF-IDF and RL Web search algorithm to enhance the searching efficiency of the relevant information. In this paper, an attempt has been made to research and examine the work nature of crawlers and crawling algorithms in search engines for efficient information retrieval.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.161-164
• /
• 2007

최근 인터넷과 멀티미디어 기술이 발달함에 따라 이미지 데이터의 양이 급속히 증가하고 있다. 증가하는 이미지를 효과적으로 관리하고 검색하기 위해 내용기반 이미지 검색에 대한 연구가 활발히 진행되고 있다. 대부분의 내용 기반 이미지 검색 시스템은 색상, 모양, 질감 특징을 이용한 유사도-기반검색에 초점을 맞추고 있다. 따라서 본 논문에서는 이미지에 나타나는 주요 색상과 색상의 공간적 특성을 포함하는 픽셀샘플링, 그리고 이미지의 외형적 변경에 강인함을 갖는 불변 모멘트 값을 이용한 내용기반 이미지 검색 시스템을 제안한다. 첫 번째 유사성 검사 단계에서는 이미지의 영역별로 가중치를 부여하여 추출한 대표색상을 사용하여, 유사하지 않은 이미지를 제거하여 검색대상의 수를 줄이며, 두 번째 유사성 검사 단계에서는 첫 번째 단계에서 선별된 후보 이미지에 색상의 공간적 정보를 포함한 픽셀샘플링을 이용하여 색상의 공간적인 위치까지 유사한 이미지만을 선별한다. 두 번째 유사성 검사단계에서 이미지가 외형적으로 변형된 유사이미지의 검출이 어려운 점을 보완하는 방법으로 이미지의 불변 모멘트를 이용하여 검색의 정확성을 높인다. 제안한 이미지 검색 방법은 10000개의 다양한 이미지로 구성된 데이터베이스에서 검색을 효율성을 실험하였다.

• Journal of Korean Library and Information Science Society
• /
• v.32 no.2
• /
• pp.165-185
• /
• 2001

This study measured whether web-based library user education represent web-based instruction theories in education. 9 criteria used were course-related instruction, collaborative learning, evaluation of tutorials, education of information retrieval, contents tables, multimedia interaction between users and librarians, navigational aids, variation of menus. The result showed that both contents and design of web sites were important for good web-based library user education.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1547-1550
• /
• 2003

의미기반 멀티미디어 검색을 하기 위해서는 멀티미디어 대한 의미정보가 필요하며, 이러한 의미정보에는 멀티미디어 데이터 자체보다는 멀티미디어 데이터에 대한 의미 해석이 중요하다. XML은 내용정보나 의미정보의 상호연관성을 표현하기에 적절하므로 본 논문에서는 멀티미디어 정보를 구조화하여 표현하기 위한 방법으로 XML을 사용한다. 또한, 멀티미디어 정보에 따른 의미성을 부여하여 나타내기 위해 퍼지데이터 사전 적용 기술을 사용한다. 의미성을 부여하기 위해 표현되는 데이터는 거의 애매한 표현법을 많이 사용하므로, 퍼지 집합관계를 적용하여 의미 판단의 기준으로 적용한다 따라서, 인간에게 좀 더 친숙하고 편리한 검색을 가능하게 하며, 의미성을 함축한 의미기반 검색을 가능하게 한다. 본 논문에서는 XML을 활용하여 다양한 멀티미디어 정보를 표현하기 위한 스키마 구조와 의미성을 반영한 XQL에 의한 검색기법을 제안한다. 인터넷에서 가장 많이 사용하고 있는 웹 상품 카탈로그 이미지나 광고 이미지에 대하여 의미기반 검색을 지원할 수 있는 방법을 제시한다. 이러한 방법은 애매모호한 표현의 질의에 대하여 검색을 가능하게 할 뿐만 아니라, 의미성을 고려하기 때문에 검색에 대한 만족도를 증대시킬 수 있다.

• Journal of Korea Multimedia Society
• /
• v.11 no.1
• /
• pp.117-128
• /
• 2008

Recently, as the increase in interaction between the person and the person, the people plentifully use the business card to exchange personal information. So, the people have many business cards. Thus, the people are liable to lose the business cards and finding a wanted business card is very difficult in the huge business cards in offline. And, the people think the business card is a way, which can express individuality. So, the people want to have the business card, which has individuality. Thus, this paper proposes the card system, which is satisfied to solve many problems of the card system in offline and express individuality. The proposed business card system can produce various business cards and puts contents such as video, photo, voice into business cards via mobile devices in anywhere, anytime. Also, this business card system follows the vCard format, which is a file format standard for personal data interchange. Finally, we provide with content-based business card retrieval using video and photo inserted into business cards. Thus, this paper proposes the hybrid business card system, which is satisfied to produce business cards expressed individuality and follows the vCard format.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1474-1479
• /
• 2015

With mobile devices showing marked improvement in performance in the age of the Internet of Things (IoT), there is demand for rapid processing of the extensive amount of multimedia big data. However, because research on image searching is focused mainly on increasing accuracy despite environmental changes, the development of fast processing of high-resolution multimedia data queries is slow and inefficient. Hence, we suggest a new distributed image search algorithm that ensures both high accuracy and rapid response by using feature extraction of distributed images based on MapReduce, and solves the problem of memory scalability based on BIRCH indexing. In addition, we conducted an experiment on the accuracy, processing time, and scalability of this algorithm to confirm its excellent performance.

• Journal of Korea Multimedia Society
• /
• v.7 no.5
• /
• pp.648-657
• /
• 2004

A method of extracting central objects in color images without any prior-knowledge is proposed in this paper, which uses basically information of significant color distribution. A central object in an image is defined as a set of regions that lie around center of the image and have significant color distribution against the other surround (or background) regions. Significant colors in an image are first defined as the colors that are distributed more densely around center of the image than near borders. Then core object regions (CORs) are selected as the regions a lot of pixels of which have the significant colors. Finally, the adjacent regions to the CORs are iteratively merged if they are similar to the CORs but not to the background regions in color distribution. The merging result is accepted as the central object that may include differently color-characterized regions and/or two or more objects of interest. Usefulness of the significant colors in extracting the central object was verified through experiments on several kinds of test images. We expect that central objects shall be used usefully in image retrieval applications.

• Journal of the Korean Society for information Management
• /
• v.23 no.3 s.61
• /
• pp.91-125
• /
• 2006

Recent advancements in information technology and the Internet have caused an explosive increase in the information available and the means to distribute it. However, such information overflow has made the efficient and accurate search of information a difficulty for most users. To solve this problem, an information retrieval and filtering system was developed as an important tool for users. Libraries and information centers have been in the forefront to provide customized services to satisfy the user's information needs under the changing information environment of today. The aim of this study is to propose an efficient information service for libraries and information centers to provide a personalized recommendation system to the user. The proposed method overcomes the weaknesses of existing systems, by providing a personalized hybrid recommendation method for multimedia contents that works in a large-scaled data and user environment. The system based on the proposed hybrid method uses an effective framework to combine Association Rule with Collaborative Filtering Method.