• Journal of Digital Convergence
• /
• v.12 no.10
• /
• pp.265-270
• /
• 2014

Existing speech recognition algorithm have a problem with not distinguish the order of vocabulary, and the voice detection is not the accurate of noise in accordance with recognized environmental changes, and retrieval system, mismatches to user's request are problems because of the various meanings of keywords. In this article, we proposed to event based semantic ontology inference model, and proposed system have a model to extract the speech recognition feature extract using ERB filter. The proposed model was used to evaluate the performance of the train station, train noise. Noise environment of the SNR-10dB, -5dB in the signal was performed to remove the noise. Distortion measure results confirmed the improved performance of 2.17dB, 1.31dB.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.2
• /
• pp.134-144
• /
• 1996

In this paper, we propose a new access method, called the HG-tree, to support indexing and retrieval by image content in large image databases. Image content is represented by a point in a multidimensional feature space. The types of queries considered are the range query and the nearest-neighbor query, both in a multidimensional space. Our goals are twofold: increasing the storage utilization and decreasing the area covered by the directory regions of the index tree. The high storage utilization and the small directory area reduce the number of nodes that have to be touched during the query processing. The first goal is achieved by absorbing splitting if possible, and when splitting is necessary, converting two nodes to three. The second goal is achieved by maintaining the area occupied by the directory region minimally on the directory nodes. We note that there is a trade-off between the two design goals, but the HG-tree is so flexible that it can control the trade-off. We present the design of our access method and associated algorithms. In addition, we report the results of a series of tests, comparing the proposed access method with the buddy-tree, which is one of the most successful point access methods for a multidimensional space. The results show the superiority of our method.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.344-356
• /
• 2001

This paper deals with the subsequence searching problem under time-warping in sequence databases. Our work is motivated by the observation that subsequence searches slow down quadratically as the average length of data sequences increases. To resolve this problem, the Segment-Based Approach for Subsequence Searches (SBSS) is proposed. The SBASS divides data and query sequences into a series of segments, and retrieves all data subsequences that satisfy the two conditions: (1) the number of segments is the same as the number of segments in a query sequence, and (2) the distance of every segment pair is less than or equal to a tolerance. Our segmentation scheme allows segments to have different lengths; thus we employ the time warping distance as a similarity measure for each segment pair. For efficient retrieval of similar subsequences, we extract feature vectors from all data segments exploiting their monotonically changing properties, and build a spatial index using feature vectors. Using this index, queries are processed with the four steps: (1) R-tree filtering, (2) feature filtering, (3) successor filtering, and (4) post-processing. The effectiveness of our approach is verified through extensive experiments.

• The KIPS Transactions:PartD
• /
• v.10D no.3
• /
• pp.459-470
• /
• 2003

It is required to research on high-dimensional index structures for efficiently retrieving high-dimensional data because an attribute vector in data warehousing and a feature vector in multimedia database have a characteristic of high-dimensional data. For this, many high-dimensional index structures have been proposed, but they have so called ‘dimensional curse’ problem that retrieval performance is extremely decreased as the dimensionality is increased. To solve the problem, the cell-based filtering (CBF) scheme has been proposed. But the CBF scheme show a linear decreasing on performance as the dimensionality. To cope with the problem, it is necessary to make use of parallel processing techniques. In this paper, we propose a parallel CBF scheme which uses a horizontally-partitioned technique as declustering. In order to maximize the retrieval performance of the proposed parallel CBF scheme, we construct our parallel CBF scheme under a SN (Shared Nothing) cluster architecture. In addition, we present a data insertion algorithm, a rage query processing one, and a k-NN query processing one which are suitable for the SN cluster architecture. Finally, we show that our parallel CBF scheme achieves better retrieval performance in proportion to the number of servers in the SN cluster architecture, compared with the conventional CBF scheme.

• Journal of KIISE:Databases
• /
• v.36 no.4
• /
• pp.263-279
• /
• 2009

Shape features in a content-based image retrieval (CBIR) system are divided into two classes: contour-based and region-based. Contour-based shape features are simple but they are not as efficient as region-based shape features. Most systems using the region-based shape feature have to extract the region firs t. The prior works on region-based systems still have shortcomings. They are complex to implement, particularly with respect to region extraction, and do not sufficiently use the spatial relationship between regions in the distance model In this paper, a region extraction method that is the combination of an edge-based method and a region growing method is proposed to accurately extract regions inside an object. Edges inside an object are accurately detected based on the Canny edge detector and the Hough transform. And the modified Integrated Region Matching (IRM) scheme which includes the adjacency relationship of regions is also proposed. It is used to compute the distance between images for the similarity search using shape features. The experimental results show the effectiveness of our region extraction method as well as the modified IRM. In comparison with other works, it is shown that the new region extraction method outperforms others.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.362-364
• /
• 1999

본 논문에서는 Quadtree 구조를 기반으로 한 효율적인 색상 정보 추출과 영상 검색을 수행하는 시스템을 구현한다. 제시한 시스템은 원 영상으로부터 DC영상을 추출하고, DC 영상의 화소들을 RGB에서 HSV의 색상 좌표계로 변환한다. 변환된 영상에서 색상의 분포에 따라 Quadtree 형태로 영역을 분할하고 대표 색상을 추출한다. 마지막으로 추출한 색상과 그 색상의 분포에 따라 Quadtree 형태로 영역을 분할하고 대표 색상을 추출한다. 마지막으로 추출한 색상과 그 색상의 분포값을 영역의 위치에 따라 Quadtree의 단말 노드에 저장한다. 그리고, 사용자가 질의 영상을 주었을 때 Quadtree에 저장된 정보를 이용하여 본 논문에서 제안한 유사도 측정을 통하여 결과 영상을 보여준다. 본 논문에서 제안한 방법으로 실험한 결과 64개의 영역으로 나눈 방법에 비해 비교하는 평균 영역의 개수는 28.9개였고, 검색시간은 2~6초 정도 감소하였다. 또한, 전체 영상의 색상 정보 저장량도 25% 정도 줄어들었지만 질의에 대한 두 방법의 검색 결과는 유사하게 나타났다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.590-595
• /
• 2009

With respect to the exponential increment of web documents on the internet, it is important how to improve performance of clustering method for web documents. Web document clustering techniques can offer accurate information and fast information retrieval by clustering web documents through semantic relationship. The clustering method based on mesh-graph provides high recall by calculating similarity for documents, but it requires high computation cost. This paper proposes a clustering method using hyperlinks which is structural feature of web documents in order to keep effectiveness and reduce computation cost.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2S
• /
• pp.629-637
• /
• 2000

The content-based information retrieval for a multimedia database uses feature information extracted from the compressed videos. This paper presents an effective method to detect scene changes from compressed videos. Scene changes are detected with DC values of DCT coefficients in MPEG-1 encoded video sequences. Instead of decoding full frames. partial macroblocks of each frame, horizontal and vertical macroblocks, are decoded to detect scene changes. This method detects abrupt scene changes by decoding minimal number of blocks and saves a lot of computation time. The performance of the proposed algorithm is analyzed based on the precision and the recall. The experimental results show the effectiveness in computation time and detection rate to detect scene changes of various MPEG-1 video streams.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.348-353
• /
• 2008

이미지의 사용이 증가함에 따라 이미지 중 사용자가 원하는 이미지를 효율적으로 검색하기 위한 방법들이 연구되어 왔다. 본 논문에서는 질의 이미지를 분석하여 이미지 특징(feature)을 추출한 후 이미지 특징에 대한 유사도 평가를 통한 이미지 검색 및 온톨로지를 기반으로 검색된 이미지들과 유사하다고 판단된 이미지와 그러한 이미지들의 의미적 정보를 추출하는 방법을 제안한다. 제안된 시스템은 질의 이미지에서 색상, 질감, 모양 등의 특징을 추출하여 유사도 평가를 통해 검색된 이미지를 제공하고, 내용기반 이미지 검색 방식을 통해 이미지를 검색하고, 온톨로지를 이용해 이미지의 의미적 정보를 추출하여 사용자에게 이미지와 관련된 의미적 정보를 제공한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.2
• /
• pp.769-786
• /
• 2016

Object recognition and object location have always drawn much interest. Also, recently various computational models have been designed. One of the big issues in this domain is the lack of an appropriate model for extracting important part of the picture and estimating the object place in the same environments that caused low accuracy. To solve this problem, a new Salient Based Bag of Visual Word (SBBoVW) model for object recognition and object location estimation is presented. Contributions lied in the present study are two-fold. One is to introduce a new approach, which is a Salient Based Bag of Visual Word model (SBBoVW) to recognize difficult objects that have had low accuracy in previous methods. This method integrates SIFT features of the original and salient parts of pictures and fuses them together to generate better codebooks using bag of visual word method. The second contribution is to introduce a new algorithm for finding object place based on the salient map automatically. The performance evaluation on several data sets proves that the new approach outperforms other state-of-the-arts.