• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• 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.

• Journal of KIISE:Databases
• /
• v.30 no.3
• /
• pp.237-251
• /
• 2003

In this paper, we propose a video retrieval system to search logical structure and semantic contents of video data efficiently. The proposed system employs a layered modelling method that orBanifes video data in raw data layer, content layer and key frame layer. The layered modelling of the proposed system represents logical structures and semantic contents of video data in content layer. Also, the proposed system supports various types of searches such as text search, visual feature based similarity search, spatio-temporal relationship based similarity search and semantic contents search.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.156-159
• /
• 2010

vp tree는 기준점(vantage point)과의 거리를 기준으로 데이터베이스 내의 자료를 색인하는 자료구조이다. 멀티미디어 자료 검색에서 비슷한 정도는 객체간의 거리를 바탕으로 비교하고, vp tree 색인 구조는 이 과정을 내포하고 있기 때문에 최근 멀티미디어 검색 연구에서 많이 사용되고 있다. 검색 방법에는 query와 가장 가까운 대상을 찾는 Nearest Neighbor Search, 또는 query와 가까운 k등까지를 검색하는 k-Nearest Neighbor Search가 있다. 본 논문에서는 Content-based retrieval에서 최근 자주 사용되는 vp tree에서 효과적인 k-NNS 방법을 제안하고, 기존의 전형적인 k-NNS 방법과의 비교 실험 결과를 보인다.

• Journal of KIISE:Databases
• /
• v.36 no.5
• /
• pp.366-373
• /
• 2009

In this paper, we propose a similarity search algorithm for image databases. One of the central problems regarding content-based image retrieval (CBIR) is the semantic gap between the low-level features computed automatically from images and the human interpretation of image content. Many search algorithms used in CBIR have used the Minkowski metric (or $L_p$-norm) to measure similarity between image pairs. However those functions cannot adequately capture the aspects of the characteristics of the human visual system as well as the nonlinear relationships in contextual information. Our new search algorithm tackles this problem by employing new similarity measures and ranking strategies that reflect the nonlinearity of human perception and contextual information. Our search algorithm yields superior experimental results on a real handwritten digit image database and demonstrates its effectiveness.

• Journal of KIISE:Databases
• /
• v.27 no.2
• /
• pp.199-208
• /
• 2000

The k-nearest neighbor search query based on similarity is very important for content-based multimedia information retrieval(MIR). The conventional exact k-nearest neighbor search algorithm is not efficient for the MIR application because multimedia data should be represented as high dimensional feature vectors. Thus, an approximate k-nearest neighbor search algorithm is required for the MIR applications because the performance increase may outweigh the drawback of receiving approximate results. For this, we propose a new approximate k-nearest neighbor search algorithm for high dimensional data. In addition, the comparison of the conventional algorithm with our approximate k-nearest neighbor search algorithm is performed in terms of retrieval performance. Results show that our algorithm is more efficient than the conventional ones.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.853-867
• /
• 2005

A number of content-based image search methods have been proposed to this point. Each of these systems uses different image data and generates different data depending on the extraction method of different characteristics that the search capabilities of each system cannot be compared and assessed. In particular, there is a problem of applying the identical image data onto the contents based image search system on the web that cannot be compared and assessed. To resolve such a problem, the XML-based FEMAL is hereby presented for extracting data of characteristics generated from specific search system in a way that can be recognized from other starch system. In the experiment using FEMAL, the extract data for characteristics is mutually communicated and integrated and the comparison assessment of search capability is seemed to be available.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.

• International Journal of Knowledge Content Development & Technology
• /
• v.2 no.2
• /
• pp.17-29
• /
• 2012

All academic information on the web or elsewhere has its creator, that is, a subject who has created the information. The subject can be an individual, a group, or an institution, and can be a nation depending on the nature of the relevant information. Most information is composed of a title, an author, and contents. An essay which is under the academic information category has metadata including a title, an author, keyword, abstract, data about publication, place of publication, ISSN, and the like. A patent has metadata including the title, an applicant, an inventor, an attorney, IPC, number of application, and claims of the invention. Most web-based academic information services enable users to search the information by processing the meta-information. An important element is to search information by using the author field which corresponds to a personal name. This study suggests a method of efficient indexing and using the adjacent operation result ranking algorithm to which phrase search-based boosting elements are applied, and thus improving the accuracy of the search results of personal names. It also describes a method for providing the results of searching co-authors and related researchers in searching personal names. This method can be effectively applied to providing accurate and additional search results in the academic information services.

• Journal of Information Processing Systems
• /
• v.7 no.3
• /
• pp.447-458
• /
• 2011

This study presents a comprehensive solution to the collection management, which is based on the model for Cultural Objects (CCO). The developed system manages and spreads the collections that are safeguarded in museums and galleries more easily by using IT. In particular, we present our approach for a non-structured search and recovery of the objects based on the annotation of artwork images. In this methodology, we have introduced a faceted search used as a framework for multi-classification and for exploring/browsing complex information bases in a guided, yet unconstrained way, through a visual interface.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.6
• /
• pp.388-392
• /
• 2014

This paper proposes an early termination method of a block vector search for fast encoding of high efficiency video coding (HEVC) screen content coding (SCC). In the proposed algorithm, two blocks indicated by two block vector predictors (BVPs) were first employed as an intra block copy (IBC) search. If the sum of absolute difference (SAD) value of the block is less than a threshold defined empirically, an IBC BV search is terminated early. The initial threshold for early termination is derived by statistical analysis and it can be modified adaptively based on a quantization parameter (QP). The proposed algorithm is evaluated on SCM-2.0 under all intra (AI) coding configurations. Experimental results show that the proposed algorithm reduces IBC BV search time by 29.23% on average while the average BD-rate loss is 0.41% under the HEVC SCC common test conditions (CTC).