• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.93-98
• /
• 2023

Instagram is one of the fastest-growing online photo social web services where users share their life images and videos with other users. Image tagging is an essential step for developing Automatic Image Annotation (AIA) methods that are based on the learning by example paradigm. Hashtags can be used on just about any social media platform, but they're most popular on Twitter and Instagram. Using hashtags is essentially a way to group together conversations or content around a certain topic, making it easy for people to find content that interests them. Practically on average, 20% of the Instagram hashtags are related to the actual visual content of the image they accompany, i.e., they are descriptive hashtags, while there are many irrelevant hashtags, i.e., stophashtags, that are used across totally different images just for gathering clicks and for search ability enhancement. Hence in this work, Sorting instagram hashtags all the way through mass tagging using HITS (Hyperlink-Induced Topic Search) algorithm is presented. The hashtags can sorted to several groups according to Jensen-Shannon divergence between any two hashtags. This approach provides an effective and consistent way for finding pairs of Instagram images and hashtags, which lead to representative and noise-free training sets for content-based image retrieval. The HITS algorithm is first used to rank the annotators in terms of their effectiveness in the crowd tagging task and then to identify the right hashtags per image.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.919-922
• /
• 1998

A content-base search method is required for video which has an unformatted and huge size of data. The index techniue is necessary for the content-based search of the video data. The first step of the video indexing is a cut detection. We propose a dynamic threshold method which change a threshold value during the cut detection process. We demonstrate that the proposed method is more efficient than the existing methods.

• 대한가정학회지
• /
• 제30권1호
• /
• pp.149-161
• /
• 1992

The purpose of this study is to analyze information search activity in purchasing behavior of household electric goods. Qusetionare survey method was used in this research. The sample was taken from 302 housewives living in Seoul, from 9th of Nov. to 20th of Nov, in 1991. Used statical methods were Frequency, Percentage, Crosstab, Anova, and Regression Analysis. The major findings are summarized as follows : 1) Component elements of information search : The means of acquiring information is that friends, neighbors, sales are most. A cause of choosing information is the sequence of satisfaction after using, easiness of interaction. The time in choosing goods is more month. 2) Component element of information search as social economic status housewife : children numbers and means of acquiring information(P<.01), education and a cause of choosing information(P<.05), life cost per month and a cause of choosing information(P<.05), social economic status and a time information search are significant. 3) A perception of risk as searching information : Among searching content of information a price influence a perception of risk. 4) Content of searching information and satisfaction of purchasing experience : Best choice is significant as quality of goods, difference of quality is significant as safety and degree of offering information is significant as a brand. 5) Satisfaction of purchasing experience following practical use of information : Best choice is significant as viewing of an exhibit and opinion of user. Difference of quality is not significant as any vairable. Degree of offer information influence searching pamphlet, searching an advertisement and opinion of user. 6) A perception of risk following source of an information : A perception of risk is most influenced by pamphlet.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권9호
• /
• pp.853-867
• /
• 2005

지금까지 많은 내용 기반 이미지 검색 방법들이 제안되고 있다. 이 시스템들은 각 시스템마다 다른 이미지 데이타를 이용하고, 다른 특징 추출방법에 따라 다른 특징 추출 데이타를 생성하므로, 각 시스템의 검색 성능을 비교 평가할 수가 없다 특히 웹상에서, 동일한 이미지 데이타를 서로 다른 사이트에 있는 내용 기반 이미지 검색 시스템에 적용하여 검색 성능을 비교 평가할 수 없는 문제점이 있다. 이와 같은 문제점을 해결하기 위해서, 각각의 특정한 검색시스템에서 생성된 특징 추출 데이타를 웹상의 다른 검색 시스템에서 인식할 수 있도록, XML 기반의 FEMAL을 제안한다. FEMAL을 이용한 실험에서, 특징 추출 데이타를 서로 통신하고 통합이 가능함을 보이고, 검색 성능의 비교 평가가 가능함을 보인다.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.87-96
• /
• 2021

The demand for e-learning through video lectures is rapidly increasing due to its diverse advantages over the traditional learning methods. This led to massive volumes of web-based lecture videos. Indexing and retrieval of a lecture video or a lecture video topic has thus proved to be an exceptionally challenging problem. Many techniques listed by literature were either visual or audio based, but not both. Since the effects of both the visual and audio components are equally important for the content-based indexing and retrieval, the current work is focused on both these components. A framework for automatic topic-based indexing and search depending on the innate content of the lecture videos is presented. The text from the slides is extracted using the proposed Merged Bounding Box (MBB) text detector. The audio component text extraction is done using Google Speech Recognition (GSR) technology. This hybrid approach generates the indexing keywords from the merged transcripts of both the video and audio component extractors. The search within the indexed documents is optimized based on the Naïve Bayes (NB) Classification and K-Means Clustering models. This optimized search retrieves results by searching only the relevant document cluster in the predefined categories and not the whole lecture video corpus. The work is carried out on the dataset generated by assigning categories to the lecture video transcripts gathered from e-learning portals. The performance of search is assessed based on the accuracy and time taken. Further the improved accuracy of the proposed indexing technique is compared with the accepted chain indexing technique.

• 대한인간공학회지
• /
• 제33권1호
• /
• pp.69-76
• /
• 2014

Objective: This study aims to present literature providing researchers with insights on specific fields of research and highlighting the major issues in the research topics. A systematic review is suggested using content analysis on literatures regarding "visual search", "eye movement", and "eye track". Background: Literature review can be classified as "narrative" or "systematic" depending on its approach in structuring the content of the research. Narrative review is a traditional approach that describes the current state of a study field and discusses relevant topics. However, since literatures on specific area cover a broad range, reviewers inherently give subjective weight on specific issues. On the contrary, systematic review applies explicit structured methodology to observe the study trends quantitatively. Method: We collected meta-data of journal papers using three search keywords: visual search, eye movement, and eye track. The collected information contains an unstructured data set including many natural languages which compose titles and abstracts, while the keyword of the journal paper is the only structured one. Based on the collected terms, seven categories were evaluated by inductive categorization and quantitative analysis from the chronological trend of the research area. Results: Unstructured information contains heavier content on "stimuli" and "condition" categories as compared with structured information. Studies on visual search cover a wide range of cognitive area whereas studies on eye movement and eye track are closely related to the physiological aspect. In addition, experimental studies show an increasing trend as opposed to the theoretical studies. Conclusion: By systematic review, we could quantitatively identify the characteristic of the research keyword which presented specific research topics. We also found out that the structured information was more suitable to observe the aim of the research. Chronological analysis on the structured keyword data showed that studies on "physical eye movement" and "cognitive process" were jointly studied in increasing fashion. Application: While conventional narrative literature reviews were largely dependent on authors' instinct, quantitative approach enabled more objective and macroscopic views. Moreover, the characteristics of information type were specified by comparing unstructured and structured information. Systematic literature review also could be used to support the authors' instinct in narrative literature reviews.

• 한국콘텐츠학회논문지
• /
• 제12권8호
• /
• pp.37-46
• /
• 2012

모바일 P2P 네트워크를 위해 제안된 데이터 배포 기법들은 프로파일과 일치하는 콘텐츠 검색 성능은 매우 뛰어나지만 프로파일과 일치하지 않는 콘텐츠 검색의 경우 질의 처리를 위한 추가적인 비용이 발생하기 때문에 프로파일과 일치하지 않는 콘텐츠 검색 성능 향상에 대한 추가적인 고려가 필요하다. 이러한 문제를 해결하기 위해 본 논문에서는 모바일 P2P 환경에서 효율적인 콘텐츠 검색을 위한 새로운 데이터 배포 기법을 제안한다. 제안하는 기법에서는 타임스탬프 메시지를 사용함으로써 이전 통신 경험 여부를 판단하고 이에 따른 데이터 배포를 수행한다. 또한, 제한된 메모리에 배포된 데이터를 효율적으로 저장하기 위해 랭킹 기법을 제안한다. 제안하는 랭킹 기법은 프로파일 일치여부 뿐만 아니라 주변의 배포 범위, 데이터를 배포해준 피어와의 연결성을 고려함으로서 차후의 질의 배포를 감소시킬 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.810-813
• /
• 2004

Indexing and Retrieving images from large and varied collections using image content as a key is a challenging and important problem in computer vision application. In this paper, a color Content-based Image Retrieval (CBIR) system using hierarchical Region of Interest (ROI) query and indexing is presented. During indexing process, First, The ROIs on every image in the image database are extracted using a region-based image segmentation technique, The JSEG approach is selected to handle this problem in order to create color-texture regions. Then, Color features in form of histogram and correlogram are then extracted from each segmented regions. Finally, The features are stored in the database as the key to retrieve the relevant images. As in the retrieval system, users are allowed to select ROI directly over the sample or user's submission image and the query process then focuses on the content of the selected ROI in order to find those images containing similar regions from the database. The hierarchical region-of-interest query is performed to retrieve the similar images. Two-level search is exploited in this paper. In the first level, the most important regions, usually the large regions at the center of user's query, are used to retrieve images having similar regions using static search. This ensures that we can retrieve all the images having the most important regions. In the second level, all the remaining regions in user's query are used to search from all the retrieved images obtained from the first level. The experimental results using the indexing technique show good retrieval performance over a variety of image collections, also great reduction in the amount of searching time.

• 한국통신학회논문지
• /
• 제41권7호
• /
• pp.816-822
• /
• 2016

콘텐트 기반 이미지 검색은 기존의 태그 또는 레이블이 있는 텍스트 기반의 검색이 아닌 이미지의 특징을 이용하여 검색하는 방법이다. 실생활 이미지 데이터는 태그나 레이블이 달려있는 경우가 많지 않기 때문에 텍스트 기반의 검색 방법을 사용하기 힘든 경우가 있다. 또한, 기존에 주로 사용되는 이미지 특징 벡터의 유사도를 사용하여 검색하는 방법은 추출 벡터의 유사도 기준으로 사용자가 의도한 결과가 나올지 확신할 수 없다. 예를 들어 사용자가 입력한 질의 이미지와 검색된 이미지들의 종류가 일치하는지의 문제가 있다. 본 논문에서는 사용자가 질의 이미지의 클래스를 예상하고 결과도 동일한 클래스를 원한다는 가정에 착안하여 이미지 검색 엔진의 성능을 개선하였다. 기존의 유사도 기반의 검색에 머신 러닝 기법을 사용한 이미지 분류기를 적용하여 질의와 동일한 클래스의 결과를 찾는 방법을 제안하였으며, 그 성능을 20개 카테고리에 속하는 11,530개의 이미지로 구성되어 있는 PASCAL VOC 공개 데이터를 이용하여 검증하였다.

• 한국전자거래학회지
• /
• 제14권4호
• /
• pp.215-228
• /
• 2009

디지털 콘텐츠 식별체계인 UCI(Universal Content Identifier)는 디지털 콘텐츠의 투명한 유통과정과 효율적 검색과 관리를 위해서 만든 URN(Uniform Resource Name)에 기반을 둔 식별체계이다. UCI 식별자를 부여받은 디지털콘텐츠는 사용자가 원하는 콘텐츠를 정확하게 전달하기 위해서는 다양한 메타데이터 정보를 필요로 한다. 그러나 UCI에서 제공하는 식별 메타데이터만으로는 콘텐츠에 대한 다양한 정보를 표현하기에는 부족하며, 정보의 보다 정확한 표현과 효율적 검색 및 관리를 위해서는 UCI에서 제공하는 메타데이터와 함께 메타데이터 내에 표현된 개념과 그 의미 관계를 정형화하고 명시적인 방법으로 정의하는 온톨로지를 필요로 한다. 본 논문에서는 UCI 식별체계의 메타데이터간 개념관계를 온톨로지로 확장하고 도메인 온톨로지를 설계함으로써 구축된 UCI 메타데이터 정보를 효율적으로 이용하여 의미 기반의 검색과 관리를 가능하게 하였으며, 다양한 질의어를 통하여 메타데이터만을 이용하는 UCI식별체계에 비하여 효율적인 검색과 관리가 가능함을 보였다.