• Journal of Internet Computing and Services
• /
• v.10 no.6
• /
• pp.173-189
• /
• 2009

Recently, video data has attracted many interest. That is the reason why efficient indexing schemes are required to support the content-based retrieval of video data. But most indexing schemes are not suitable for indexing a high-dimensional data except Hybrid Spill-Tree. In this paper, we propose an efficient high-dimensional indexing scheme to support the content-based retrieval of video data. For this, we extend Hybrid Spill-Tree by using a newly designed clustering technique and by adopting a signature method. Finally, we show that proposed signature-based high dimensional indexing scheme achieves better retrieval performance than existing M-Tree and Hybrid Spill-Tree.

• Journal of IKEEE
• /
• v.14 no.4
• /
• pp.339-345
• /
• 2010

So far, many researches have been done to index high-dimensional feature values for fast content-based image retrieval. Still, many existing indexing schemes are suffering from performance degradation due to the curse of dimensionality problem. As an alternative, heuristic algorithms have been proposed to calculate the result with 'high probability' at the cost of accuracy. In this paper, we propose a new extendible hash-based indexing scheme for high-dimensional feature values. Our indexing scheme provides several advantages compared to the traditional high-dimensional index structures in terms of search performance and accuracy preservation. Through extensive experiments, we show that our proposed indexing scheme achieves outstanding performance.

• Journal of KIISE:Databases
• /
• v.29 no.2
• /
• pp.128-137
• /
• 2002

In this paper, we propose the LPC+-file for efficient indexing of high-dimensional image data. With the proliferation of multimedia data, there Is an increasing need to support the indexing and retrieval of high-dimensional image data. Recently, the LPC-file (5) that based on vector approximation has been developed for indexing high-dimensional data. The LPC-file gives good performance especially when the dataset is uniformly distributed. However, compared with for the uniformly distributed dataset, its performance degrades when the dataset is clustered. We improve the performance of the LPC-file for the strongly clustered image dataset. The basic idea is to adaptively partition the data space to find subspaces with high-density clusters and to assign more bits to them than others to increase the discriminatory power of the approximation of vectors. The total number of bits used to represent vector approximations is rather less than that of the LPC-file since the partitioned cells in the LPC+-file share the bits. An empirical evaluation shows that the LPC+-file results in significant performance improvements for real image data sets which are strongly clustered.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.362-371
• /
• 2005

Similarity indexing and searching are well known to be difficult in high-dimensional applications such as multimedia databases. Especially, they become more difficult when multiple features have to be indexed together. In this paper, we propose a novel indexing method called the GB-index that is designed to efficiently handle complex similarity queries as well as relevance feedback in high-dimensional image databases. In order to provide the flexibility in controlling multiple features and query objects, the GB-index treats each dimension independently The efficiency of the GB-index is realized by specialized bitmap indexing that represents all objects in a database as a set of bitmaps. Main contributions of the GB-index are three-fold: (1) It provides a novel way to index high-dimensional data; (2) It efficiently handles complex similarity queries; and (3) Disjunctive queries driven by relevance feedback are efficiently treated. Empirical results demonstrate that the GB-index achieves great speedups over the sequential scan and the VA-file.

• Journal of KIISE:Databases
• /
• v.31 no.1
• /
• pp.13-22
• /
• 2004

With the proliferation of multimedia data, there is an increasing need to support the indexing and retrieval of high-dimensional image data. Although there have been many efforts, the performance of existing multidimensional indexing methods is not satisfactory in high dimensions. Thus the dimensionality reduction and the approximate solution methods were tried to deal with the so-called dimensionality curse. But these methods are inevitably accompanied by the loss of precision of query results. Therefore, recently, the vector approximation-based methods such as the VA- file and the LPC-file were developed to preserve the precision of query results. However, the performance of the vector approximation-based methods depend largely on the size of the approximation file and they lose the advantages of the multidimensional indexing methods that prune much search space. In this paper, we propose a new index structure called the GC-tree for efficient similarity search in image databases. The GC-tree is based on a special subspace partitioning strategy which is optimized for clustered high-dimensional images. It adaptively partitions the data space based on a density function and dynamically constructs an index structure. The resultant index structure adapts well to the strongly clustered distribution of high-dimensional images.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.6
• /
• pp.397-401
• /
• 2007

Recent applications on continuous queries on moving objects are extended quickly to various parts. These applications need not only 2-dimensional space data but also high-dimensional space data. If we use previous index for overlapped continuous range queries on high-dimensional space data, as the number of continuous range queries on a large number of moving objects becomes larger, their performance degrades significantly. We focus on stationary queries, non-exponential increase of storage cost and efficient processing time for large data sets. In this paper, to solve these problems, we present a novel query indexing method, denoted as PAB(Projected Attribute Bit)-based query index. We transfer information of high-dimensional continuous range query on each axis into one-dimensional bit lists by projecting technique. Also proposed query index supports incremental update for efficient query processing. Through various experiments, we show that our method outperforms the CES(containment-encoded squares)-based indexing method which is one of the most recent research.

• ETRI Journal
• /
• v.22 no.2
• /
• pp.32-42
• /
• 2000

The existing multi-dimensional index structures are not adequate for indexing higher-dimensional data sets. Although conceptually they can be extended to higher dimensionalities, they usually require time and space that grow exponentially with the dimensionality. In this paper, we analyze the existing index structures and derive some requirements of an index structure for content-based image retrieval. We also propose a new structure, for indexing large amount of point data in a high-dimensional space that satisfies the requirements. in order to justify the performance of the proposed structure, we compare the proposed structure with the existing index structures in various environments. We show, through experiments, that our proposed structure outperforms the existing structures in terms of retrieval time and storage overhead.

• Journal of Industrial Technology
• /
• v.20 no.B
• /
• pp.213-218
• /
• 2000

The nearest neighbor query is an important operation widely used in multimedia databases for finding the object that is most similar to a given query object. Most of techniques for processing nearest neighbor queries employ multidimensional indexes for effective indexing of objects. However, the performance of previous multidimensional indexes, which use N-dimensional rectangles or spheres for representing the capsule of the object cluster, deteriorates seriously as the number of dimensions gets higher. This paper proposes a new index structure based singular value decomposition resolving this problem and the query processing method using it. We also verify the superiority of our approach through performance evaluation by performing extensive experiments.

• Journal of KIISE:Databases
• /
• v.37 no.5
• /
• pp.228-237
• /
• 2010

Although conventional index structures provide various nearest-neighbor search algorithms for high-dimensional data, there are additional requirements to increase search performances as well as to support index scalability for large scale data. To support these requirements, we propose a distributed high-dimensional indexing structure based on cluster systems, called a Distributed Vector Approximation-tree (DVA-tree), which is a two-level structure consisting of a hybrid spill-tree and VA-files. We also describe the algorithms used for constructing the DVA-tree over multiple machines and performing distributed k-nearest neighbors (NN) searches. To evaluate the performance of the DVA-tree, we conduct an experimental study using both real and synthetic datasets. The results show that our proposed method contributes to significant performance advantages over existing index structures on difference kinds of datasets.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.88-102
• /
• 2006

In multimedia information retrieval, multimedia data are represented as vectors in high dimensional space. To search these vectors effectively, a variety of indexing methods have been proposed. However, the performance of these indexing methods degrades dramatically with increasing dimensionality, which is known as the dimensionality curse. To resolve the dimensionality curse, dimensionality reduction methods have been proposed. They map feature vectors in high dimensional space into the ones in low dimensional space before indexing the data. This paper proposes a method for dimensionality reduction based on a function approximating the Euclidean distance, which makes use of the norm and angle components of a vector. First, we identify the causes of the errors in angle estimation for approximating the Euclidean distance, and discuss basic directions to reduce those errors. Then, we propose a novel method for dimensionality reduction that composes a set of subvectors from a feature vector and maintains only the norm and the estimated angle for every subvector. The selection of a good reference vector is important for accurate estimation of the angle component. We present criteria for being a good reference vector, and propose a method that chooses a good reference vector by using Levenberg-Marquardt algorithm. Also, we define a novel distance function, and formally prove that the distance function lower-bounds the Euclidean distance. This implies that our approach does not incur any false dismissals in reducing the dimensionality effectively. Finally, we verify the superiority of the proposed method via performance evaluation with extensive experiments.