Agma J. M. Traina

Similarity search without tears: the OMNI-family of all-purpose access methods

Designing a new access method inside a commercial DBMS is cumbersome and expensive. We propose a family of metric access methods that are fast and easy to implement on top of existing access methods, such as sequential scan, R-trees and Slim-trees. The idea is to elect a set of objects as foci, and gauge all other objects with their distances from this set. We show how to define the foci set cardinality, how to choose appropriate foci, and how to perform range and nearest-neighbor queries using them, without false dismissals. The foci increase the pruning of distance calculations during the query processing. Furthermore we index the distances from each object to the foci to reduce even triangular inequality comparisons. Experiments on real and synthetic datasets show that our methods match or outperform existing methods. They are up to 10 times faster, and perform up to 10 times fewer distance calculations and disk accesses. In addition, it scales up well, exhibiting sub-linear performance with growing database size.

An Efficient Algorithm for Fractal Analysis of Textures

In this paper we propose a new and efficient texture feature extraction method: the Segmentation-based Fractal Texture Analysis, or SFTA. The extraction algorithm consists in decomposing the input image into a set of binary images from which the fractal dimensions of the resulting regions are computed in order to describe segmented texture patterns. The decomposition of the input image is achieved by the Two-Threshold Binary Decomposition (TTBD) algorithm, which we also propose in this work. We evaluated SFTA for the tasks of content-based image retrieval (CBIR) and image classification, comparing its performance to that of other widely employed feature extraction methods such as Haralick and Gabor filter banks. SFTA achieved higher precision and accuracy for CBIR and image classification. Additionally, SFTA was at least 3.7 times faster than Gabor and 1.6 times faster than Haralick with respect to feature extraction time.

Retrieval by content of medical images using texture for tissue identification

This work aims at supporting the retrieval and indexing of medical images by extracting and organizing intrinsic features of them, more specifically texture attributes from images. A tool for obtaining the relevant textures was implemented This tool retrieves and classifies images using the extracted values, and allows the user to issue similarity queries. The application of the proposed method on images has given encouraging results that motivate to apply the method as a basis to more experiments, at diversified contexts. The accuracy degree obtained from the precision and recall plots was always over 90% for queries asking for similar images for up to 20% of the database.

Spatial join selectivity using power laws

We discovered a surprising law governing the spatial join selectivity across two sets of points. An example of such a spatial join is “find the libraries that are within 10 miles of schools”. Our law dictates that the number of such qualifying pairs follows a power law, whose exponent we call “pair-count exponent” (PC). We show that this law also holds for self-spatial-joins (“find schools within 5 miles of other schools”) in addition to the general case that the two point-sets are distinct. Our law holds for many real datasets, including diverse environments (geographic datasets, feature vectors from biology data, galaxy data from astronomy). In addition, we introduce the concept of the Box-Occupancy-Product-Sum (BOPS) plot, and we show that it can compute the pair-count exponent in a timely manner, reducing the run time by orders of magnitude, from quadratic to linear. Due to the pair-count exponent and our analysis (Law 1), we can achieve accurate selectivity estimates in constant time (O(1)) without the need for sampling or other expensive operations. The relative error in selectivity is about 30% with our fast BOPS method, and even better (about 10%), if we use the slower, quadratic method.

The Omni-family of all-purpose access methods: a simple and effective way to make similarity search more efficient

Similarity search operations require executing expensive algorithms, and although broadly useful in many new applications, they rely on specific structures not yet supported by commercial DBMS. In this paper we discuss the new Omni-technique, which allows to build a variety of dynamic Metric Access Methods based on a number of selected objects from the dataset, used as global reference objects. We call them as the Omni-family of metric access methods. This technique enables building similarity search operations on top of existing structures, significantly improving their performance, regarding the number of disk access and distance calculations. Additionally, our methods scale up well, exhibiting sub-linear behavior with growing database size.

Improving the ranking quality of medical image retrieval using a genetic feature selection method

In this paper, we take advantage of single-valued functions that evaluate rankings to develop a family of feature selection methods based on the genetic algorithm approach, tailored to improve the accuracy of content-based image retrieval systems. Experiments on three image datasets, comprising images of breast and lung nodules, showed that developing functions to evaluate the ranking quality allows improving retrieval performance. This approach produces significantly better results than those of other fitness function approaches, such as the traditional wrapper and than filter feature selection algorithms.

MultiWaveMed: a system for medical image retrieval through wavelets transformations

This paper presents the MultiWaveMed system, which is a new software allowing to index and retrieve medical images through the comparison of their texture features. The features are extracted by wavelet transforms, and are organized in feature vectors. The system extracts the image texture features, computes the distance between the query image to all images in the database, through the comparison of their features, and retrieve de n most similar images regarding this kind of feature. The proposed system has implemented both Daubechies and Gabor wavelets. The feature vectors extracted from the images are used to organize the images through access methods, which are the basis to perform the query-by-content operations over the images. The focus of this paper is to show the utility of the wavelet transforms on medical image characterization and their suitability for image indexing and retrieval.

An Association Rule-Based Method to Support Medical Image Diagnosis With Efficiency

In this paper, we propose a method based on association rule-mining to enhance the diagnosis of medical images (mammograms). It combines low-level features automatically extracted from images and high-level knowledge from specialists to search for patterns. Our method analyzes medical images and automatically generates suggestions of diagnoses employing mining of association rules. The suggestions of diagnosis are used to accelerate the image analysis performed by specialists as well as to provide them an alternative to work on. The proposed method uses two new algorithms, PreSAGe and HiCARe. The PreSAGe algorithm combines, in a single step, feature selection and discretization, and reduces the mining complexity. Experiments performed on PreSAGe show that this algorithm is highly suitable to perform feature selection and discretization in medical images. HiCARe is a new associative classifier. The HiCARe algorithm has an important property that makes it unique: it assigns multiple keywords per image to suggest a diagnosis with high values of accuracy. Our method was applied to real datasets, and the results show high sensitivity (up to 95%) and accuracy (up to 92%), allowing us to claim that the use of association rules is a powerful means to assist in the diagnosing task.

A fast and effective method to find correlations among attributes in databases

The problem of identifying meaningful patterns in a database lies at the very heart of data mining. A core objective of data mining processes is the recognition of inter-attribute correlations. Not only are correlations necessary for predictions and classifications – since rules would fail in the absence of pattern – but also the identification of groups of mutually correlated attributes expedites the selection of a representative subset of attributes, from which existing mappings allow others to be derived. In this paper, we describe a scalable, effective algorithm to identify groups of correlated attributes. This algorithm can handle non-linear correlations between attributes, and is not restricted to a specific family of mapping functions, such as the set of polynomials. We show the results of our evaluation of the algorithm applied to synthetic and real world datasets, and demonstrate that it is able to spot the correlated attributes. Moreover, the execution time of the proposed technique is linear on the number of elements and of correlations in the dataset.

Efficient Content-Based Image Retrieval through Metric Histograms

This paper presents a new and efficient method for content-based image retrieval employing the color distribution of images. This new method, called metric histogram, takes advantage of the correlation among adjacent bins of histograms, reducing the dimensionality of the feature vectors extracted from images, leading to faster and more flexible indexing and retrieval processes. The proposed technique works on each image independently from the others in the dataset, therefore there is no pre-defined number of color regions in the resulting histogram. Thus, it is not possible to use traditional comparison algorithms such as Euclidean or Manhattan distances. To allow the comparison of images through the new feature vectors given by metric histograms, a new metric distance function MHD( ) is also proposed. This paper shows the improvements in timing and retrieval discrimination obtained using metric histograms over traditional ones, even when using images with different spatial resolution or thumbnails. The experimental evaluation of the new method, for answering similarity queries over two representative image databases, shows that the metric histograms surpass the retrieval ability of traditional histograms because they are invariant on geometrical and brightness image transformations, and answer the queries up to 10 times faster than the traditional ones.