Slim-Trees: High Performance Metric Trees Minimizing Overlap between Nodes

Traina, Caetano; Traina, Agma J. M.; Seeger, Bernhard; Faloutsos, Christos

doi:10.1007/3-540-46439-5_4

Cited by 195 publications

(182 citation statements)

References 11 publications

Supporting

Mentioning

107

Contrasting

Unclassified

Order By: Relevance

“…The theoretical analysis of these structures can be quite difficult, so experimental validation becomes essential. There are some theoretically defined measures such as the fat and bloat factors and prunability of Traina Jr. et al [36,37], but even such properties are generally established empirically for a given structure. 48 Moret [38] gives some reasons why asymptotic analysis alone may not be enough for algorithm studies in general (the worst-case behavior may be restricted to a very small subset of instances and thus not be at all characteristic of instances encountered in practice, and even in the absence of these problems, deriving tight asymptotic bounds may be very difficult).…”

Section: Methods Qualitymentioning

confidence: 99%

See 1 more Smart Citation

The Basic Principles of Metric Indexing

Hetland

2009

Studies in Computational Intelligence

View full text Add to dashboard Cite

Summary. This chapter describes several methods of similarity search, based on metric indexing, in terms of their common, underlying principles. Several approaches to creating lower bounds using the metric axioms are discussed, such as pivoting and compact partitioning with metric ball regions and generalized hyperplanes. Finally, pointers are given for further exploration of the subject, including non-metric, approximate, and parallel methods.

show abstract

Section: Methods Qualitymentioning

confidence: 99%

“…12(a)). 36 This space bisection is used by the GH-tree, and the multiway equivalent is used by the structure called the Geometric Near-neighbor Access Tree, or simply GNAT (see Fig. 12(b)).…”

Section: Metric Planes and Dirichlet Domainsmentioning

confidence: 99%

The Basic Principles of Metric Indexing

Hetland

2009

Studies in Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…19,20 In an image database, a specific index tree is built for each type of feature vector and each comparative method. This mechanism allows Q2 A NEW FAMILY OF DISTANCE FUNCTIONS FOR PERCEPTUAL SIMILARITY for the effective retrieval of information from image databases, following user-defined parameters.…”

Section: Background On Distance Functionsmentioning

confidence: 99%

A New Family of Distance Functions for Perceptual Similarity Retrieval of Medical Images

Felipe

Traina

2008

J Digit Imaging

Self Cite

View full text Add to dashboard Cite

A long-standing challenge of content-based image retrieval (CBIR) systems is the definition of a suitable distance function to measure the similarity between images in an application context which complies with the human perception of similarity. In this paper, we present a new family of distance functions, called attribute concurrence influence distances (AID), which serve to retrieve images by similarity. These distances address an important aspect of the psychophysical notion of similarity in comparisons of images: the effect of concurrent variations in the values of different image attributes. The AID functions allow for comparisons of feature vectors by choosing one of two parameterized expressions: one targeting weak attribute concurrence influence and the other for strong concurrence influence. This paper presents the mathematical definition and implementation of the AID family for a two-dimensional feature space and its extension to any dimension. The composition of the AID family with L p distance family is considered to propose a procedure to determine the best distance for a specific application. Experimental results involving several sets of medical images demonstrate that, taking as reference the perception of the specialist in the field (radiologist), the AID functions perform better than the general distance functions commonly used in CBIR.KEY WORDS: Distance function, medical images, content-based image retrieval INTRODUCTION D igital images, which are present in the majority of medical systems, serve to support diagnostic activities. However, for the effective and suitable use of images, these systems must include tools for image management, including fast and effective comparison and retrieval. In the image analysis environment, the ability to compare images automatically is important because the number of stored images is usually very large, precluding a radiologist from making individual comparisons of the images in the entire database. Some groups of radiologists prefer to search in reference libraries, which are composed of sets of typical images. However, the possibility of retrieving images containing patient-related information from specific databases enables the analyst to make more in-depth analyses, for instance, to explore and study the patients from a particular geographic region.The core of content-based image retrieval (CBIR) is the use of intrinsic visual features, which are extracted automatically from the images to describe them while keeping their most relevant characteristics. Such features, usually consisting of numerical values obtained by image-processing algorithms, are used to compare and index images and are usually placed together in a feature vector. Each item of a feature vector is also called an image attribute. CBIR techniques take advantage of index structures that use the similarity of features to speed up the retrieval, doing this automatically. 1,2 In Figure 1, the user places a query, which is done typically by providing the system with an image (query image) ...

show abstract

“…Indexes based on clustering are better suited for high-dimensional metric spaces or larger query radii, that is, the cases where the problem is more difficult [2]. Some clustering-based indexes are the Voronoi tree [3], the GNAT [4], the M-tree [5], the Slim-tree [6], and the SAT [7].…”

Section: Introductionmentioning

confidence: 99%

Fully dynamic metric access methods based on hyperplane partitioning

Navarro

Uribe-Paredes

2011

Information Systems

View full text Add to dashboard Cite

Metric access methods based on hyperplane partitioning have the advantage, compared to the ballpartitioning-based ones, that regions do not overlap. The price is less flexibility for controlling the tree shape, especially in the dynamic scenario, that is, upon insertions and deletions of objects. In this paper we introduce a technique called ghost hyperplanes, which enables fully dynamic data structures based on hyperplane partitioning. We apply the technique to Brin's GNAT static index, obtaining a dynamic variant called EGNAT, which in addition we adapt to secondary memory. We show experimentally that the EGNAT is competitive with the M-tree, the baseline for this scenario. We also apply the ghost hyperplane technique to Voronoi trees, obtaining a competitive dynamic structure for main memory.

show abstract

Slim-Trees: High Performance Metric Trees Minimizing Overlap between Nodes

Cited by 195 publications

References 11 publications

The Basic Principles of Metric Indexing

The Basic Principles of Metric Indexing

A New Family of Distance Functions for Perceptual Similarity Retrieval of Medical Images

Fully dynamic metric access methods based on hyperplane partitioning

Contact Info

Product

Resources

About