Xaro Benavent

Multimedia Information Retrieval Based on Late Semantic Fusion Approaches: Experiments on a Wikipedia Image Collection

Main goal of this work is to show the improvement of using a textual pre-filtering combined with an image re-ranking in a Multimedia Information Retrieval task. The defined three step-based retrieval processes and a well-selected combination of visual and textual techniques help the developed Multimedia Information Retrieval System to overcome the semantic gap in a given query. In the paper, five different late semantic fusion approaches are discussed and experimented in a realistic scenario for multimedia retrieval like the one provided by the publicly available ImageCLEF Wikipedia Collection.

A relevance feedback CBIR algorithm based on fuzzy sets

CBIR (content-based image retrieval) systems attempt to allow users to perform searches in large picture repositories. In most existing CBIR systems, images are represented by vectors of low level features. Searches in these systems are usually based on distance measurements defined in terms of weighted combinations of the low level features. This paper presents a novel approach to combining features when using multi-image queries consisting of positive and negative selections. A fuzzy set is defined so that the degree of membership of each image in the repository to this fuzzy set is related to the users interest in that image. Positive and negative selections are then used to determine the degree of membership of each picture to this set. The system attempts to capture the meaning of a selection by modifying a series of parameters at each iteration to imitate user behavior, becoming more selective as the search progresses. The algorithm has been evaluated against four other representative relevance feedback approaches. Both the performance and usability of the five CBIR systems have been studied. The algorithm presented is easy to use and yields the highest performance in terms of the average number of iterations required to find a specific image. However, it is computationally more expensive and requires more memory than two of the other techniques.

A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval

Abstract This paper presents a texture descriptor based on wavelet frame transforms. At each position in the image, and for each resolution level, we consider both vertical and horizontal wavelet detail coefficients as the components of a bivariate random vector. The magnitudes and angles of these vectors are computed. At each level the empirical histogram of magnitudes is modeled by a Generalized Gamma distribution, and the empirical histogram of angles is modeled by a different version of the von Mises distribution that accounts for histograms with 2 modes. Each texture is characterized by few parameters. A new distance is presented (based on the Kullback–Leibler divergence) that allows giving relative importance to each model and to each resolution level. This distance is later conveniently adapted to provide for rotation invariance, by establishing equivalence classes over distributions of angles. Through a broad set of experiments on three different image databases, we demonstrate that our new descriptor and distance measure can be successfully applied in the context of texture retrieval. We compare our system to several relevant methods in this field in terms of retrieval performance and number of parameters used by each method. We also include some classification tests. In all the tests, we obtain superior retrieval rates for a set of fewer parameters involved.

Selecting the structuring element for morphological texture classification

This paper deals with a concrete aspect of texture classification: the choice of a good structuring element (SE) when the texture features used for classification are obtained from morphological granulometries. First, a granulometry is defined from the morphological opening of the texture using a convex and compact subset containing the origin as SE. Then, some usual distributional descriptors (mean, variance, skewness and kurtosis) of the granulometric size distribution are used as texture features. The main point of the paper is the choice of a good SE from the point of view of texture classification. A methodology is explained and software has been developed that helps in such a choice, for any given criterion for the quality of the classification.

A new wavelet-based texture descriptor for image retrieval

This paper presents a novel texture descriptor based on the wavelet transform. First, we will consider vertical and horizontal coefficients at the same position as the components of a bivariate random vector. The magnitud and angle of these vectors are computed and its histograms are analyzed. This empirical magnitud histogram is modelled by using a gamma distribution (pdf). As a result, the feature extraction step consists of estimating the gamma parameters using the maxima likelihood estimator and computing the circular histograms of angles. The similarity measurement step is done by means of the well-known Kullback-Leibler divergence. Finally, retrieval experiments are done using the Brodatz texture collection obtaining a good performance of this new texture descriptor. We compare two wavelet transforms, with and without downsampling, and show the advantage of the second one, which is translation invariant, for the construction of our texture descriptor.

Modeling user preferences in content-based image retrieval

This paper is concerned with content-based image retrieval from a stochastic point of view. The semantic gap problem is addressed in two ways. First, a dimensional reduction is applied using the (pre-calculated) distances among images. The dimension of the reduced vector is the number of preferences that we allow the user to choose from, in this case, three levels. Second, the conditional probability distribution of the random user preference, given this reduced feature vector, is modeled using a proportional odds model. A new model is fitted at each iteration. The score used to rank the image database is based on the estimated probability function of the random preference. Additionally, some memory is incorporated in the procedure by weighting the current and previous scores. Also, a novel evaluation procedure is proposed in this work based on the empirical commutative distribution functions of the relevant and non-relevant retrieved images. Good experimental results are achieved in very different experimental setups and tested in different databases. HighlightsA novel method for image retrieval have been proposed based on Generalized Linear Model.The model aims to bridge the semantic gap between low level features and user preferences.A drastic dimension reduction of feature vector is achieved by using a distance matrix.A broad set of experiments has been carried out for different databases.A new evaluation procedure has been proposed based on the empirical commutative distribution functions of the relevant and non-relevant retrieved images.

Wavelet-Based Texture Retrieval Modeling the Magnitudes of Wavelet Detail Coefficients with a Generalized Gamma Distribution

This paper presents a texture descriptor based on the fine detail coefficients at three resolution levels of a traslation invariant undecimated wavelet transform. First, we consider vertical and horizontal wavelet detail coefficients at the same position as the components of a bivariate random vector, and the magnitude and angle of these vectors are computed. The magnitudes are modeled by a Generalized Gamma distribution. Their parameters, together with the circular histograms of angles, are used to characterize each texture image of the database. The Kullback-Leibler divergence is used as the similarity measurement. Retrieval experiments, in which we compare two wavelet transforms, are carried out on the Brodatz texture collection. Results reveal the good performance of this wavelet-based texture descriptor obtained via the Generalized Gamma distribution.

Semi-automated evaluation tool for retinal vasculopathy

The ocular fundus is the only area of human body where vascular system is visible using relatively simple instrumentation. Furthermore, there is medical suggestive evidence of a direct relationship between certain measures of vascular characteristics in the ocular fundus (arteriolar and venular calibers and focal arteriolar narrowing) and cardiovascular diseases. In order to establish such relationship on sound statistical basis a method must be provided to measure the needed values in an easy, yet precise and repeatable way. This paper presents a system to assist physicians in signaling and storing the data associated to signs of vascular deterioration and vascular calibers in non-mydriatic ocular fundus images. The system is built around a graphical user interface that, even not fully automatic, guides the practitioner to mark certain anatomic visible features in an easy and precise way. The data are exported in common database formats for further processing and a statistical summary is also presented.

A novel dynamic multi-model relevance feedback procedure for content-based image retrieval

This paper deals with the problem of image retrieval in large databases with a big semantic gap by a relevance feedback procedure. We present a novel algorithm for modelling the userss preferences in the content-based image retrieval system.The proposed algorithm considers the probability of an image belonging to the set of those sought by the user, and estimates the parameters of several local logistic regression models whose inputs are the low-level image features. A Principal Component Analysis method is applied to the original vector to reduce its high dimensionality. The relevance probabilities predicted by these local models are combined by means of a weighted average. These weights are obtained according to the variance explained by the group of principal components used for each local model. These models are dynamically estimated in each iteration of the relevance feedback algorithm until the user is satisfied.This novel procedure has been tested in a collection with a large semantic gap, the Wikipedia collection. Two types of experiments have been performed, one with an automatic user and another with a typical user. The method is compared to some recent similar approaches in literature, obtaining very good performance in terms of the MAP evaluation measure.

Some results using different approaches to merge visual and text-based features in CLEF'08 photo collection

This paper describes the participation of the MIRACLE team at the ImageCLEF Photographic Retrieval task of CLEF 2008. We succeeded in submitting 41 runs. Obtained results from text-based retrieval are better than content-based as previous experiments in the MIRACLE team campaigns [5, 6] using different software. Our main aim was to experiment with several merging approaches to fuse text-based retrieval and content-based retrieval results, and it happened that we improve the text-based baseline when applying one of the three merging algorithms, although visual results are lower than textual ones.