Ermir Qeli

Detecting Text in Videos Using Fuzzy Clustering Ensembles

Detection and localization of text in videos is an important task towards enabling automatic content-based retrieval of digital video databases. However, since text is often displayed against a complex background, its detection is a challenging problem. In this paper, a novel approach based on fuzzy cluster ensemble techniques to solve this problem is presented. The advantage of this approach is that the fuzzy clustering ensemble allows the incremental inclusion of temporal information regarding the appearance of static text in videos. Comparative experimental results for a test set of 10.92 minutes of video sequences have shown the very good performance of the proposed approach with an overall recall of 92.04% and a precision of 96.71%

Visualizing regulatory interactions in metabolic networks

BackgroundDirect visualization of data sets in the context of biochemical network drawings is one of the most appealing approaches in the field of data evaluation within systems biology. One important type of information that is very helpful in interpreting and understanding metabolic networks has been overlooked so far. Here we focus on the representation of this type of information given by the strength of regulatory interactions between metabolite pools and reaction steps.ResultsThe visualization of such interactions in a given metabolic network is based on a novel concept defining the regulatory strength (RS) of effectors regulating certain reaction steps. It is applicable to any mechanistic reaction kinetic formula. The RS values are measures for the strength of an up- or down-regulation of a reaction step compared with the completely non-inhibited or non-activated state, respectively. One numerical RS value is associated to any effector edge contained in the network. The RS is approximately interpretable on a percentage scale where 100% means the maximal possible inhibition or activation, respectively, and 0% means the absence of a regulatory interaction. If many effectors influence a certain reaction step, the respective percentages indicate the proportion in which the different effectors contribute to the total regulation of the reaction step. The benefits of the proposed method are demonstrated with a complex example system of a dynamic E. coli network.ConclusionThe presented visualization approach is suitable for an intuitive interpretation of simulation data of metabolic networks under dynamic as well as steady-state conditions. Huge amounts of simulation data can be analyzed in a quick and comprehensive way. An extended time-resolved graphical network presentation provides a series of information about regulatory interaction within the biological system under investigation.

Visualizing time-varying matrices using multidimensional scaling and reorderable matrices

We present a novel approach to visualize time-varying matrices. This approach is based on combining multidimensional scaling and the reorderable matrix method. An adapted version of multidimensional scaling which allows the construction of similarity plots for columns/rows of time-varying matrices is proposed. In addition, we have extended the reorderable matrix method to allow the visual exploration of time-varying matrix data in a tabular form for being able to verify the results of MDS and possibly discover new patterns in data. The benefits of our approach are illustrated by showing visualizations of sensitivity matrices generated during simulations of metabolic network models.

Visual exploration of time-varying matrices

In this paper, we present several extensions of our previous work on combining the multidimensional scaling technique and the reorderable matrix method to visualize time-varying matrices: (a) the Sammon mapping is employed as another dimension reduction technique that in contrast to multidimensional scaling pays more attention to small distances; (b) a novel method for the interactive colored visualization of covariances/correlations is presented; (c) the K-means clustering algorithm is used and its results are directly visualized in the mentioned dimension reduction plots; (d) a novel view, namely the visualization of the timely evolution of the cluster membership, is proposed. The latter is based on calculating accumulated adjacency matrix that gathers the information regarding membership of objects in clusters for each point of time. The color visualization of this matrix allows the investigation of changes in cluster memberships and possible outliers, i.e. objects that change clusters frequently. Results are presented by visualizing sensitivity matrices generated during the simulation of metabolic network models.

Visualizing regulatory interdependencies and parameter sensitivities in biochemical network models

For the evaluation of data from stimulus response experiments dynamic metabolic network models are generated. With an increase of reaction steps and regulatory interdependencies the amount of the simulation data becomes hard to handle. In this paper, we present the application and extension of methods combining visualization and animation of dynamic models to facilitate the analysis of the complex system behaviour. The dynamic changes of metabolite pools and fluxes are simultaneous visualized within the network structure. Depending on the scaling used, different focuses can be set, e.g. to observe local dynamics or global concentration balances. For the visualization of the present inhibition and activation state of certain reaction steps of a metabolic network model a novel quantification method is proposed. The sensitivity analysis of dynamic metabolic network models leads to high-dimensional sensitivity matrices that vary over time. To process the enormous amount of data we use a colour scale transformation and the reorderable matrix method for the visual exploration of the time-varying matrices. The benefits of our methods are illustrated with the help of a metabolic network model of the central carbon metabolism in Escherichia coli.

Customizable detection of changes for XML documents using XPath expressions

Change detection in XML documents is an important task in the context of query systems. In this paper, we present CustX- Diff, a customizable change detection approach for XML documents based on X-Diff [6]. CustX-Diff performs the change detection operation simultaneosly with the XPath based filtering of XML document parts. The class of XPath expressions used is the tree patterns subset of XPath. For the embedding of simple paths into XPath expressions during the difference operation, a dynamic programming approach is proposed. Comparative performance results with respect to the original X-Diff [6] approach demonstrate the efficiency of the proposed method.

The time-dependent reorderable matrix method for visualizing evolving tabular data

The reorderable matrix method is a convenient way of representing static tabular data (i.e. matrices) visually. In this paper, we present an approach to use the reorderable matrix method for visualizing time-varying matrix data. Solutions to the problems encountered during the adaptation of this visualization method for time-varying matrices and proposals to solve the problems related to the automatic reordering of static tabular data are discussed. The approach is illustrated by visualizing sensitivity matrices generated during the simulation of metabolic network models.

Filtering XML documents using XPath expressions and aspect-oriented programming

In this paper, we present the design and implementation of a filtering approach for XML documents which is based on XPath expressions and Aspect-Oriented Programming (AOP). The class of XPath expressions used allows for branching, wildcards and descendant relationships between nodes. For the embedding of simple paths into XPath expressions, a dynamic programming approach is proposed. The AOP paradigm, which provides a means for encapsulating crosscutting concerns in software, is introduced to integrate the filtering approach in the broader context of event-based parsing of XML documents using SAX.

Holistic Comparison of Text Images for Content-Based Retrieval

The accurate recognition of text that appears in images/videos using analytical character recognition methods is often very difficult, despite the fact that the text might be correctly localized, segmented and binarized. This is mainly due to changing features of the text such as various fonts, or noise factors embedded in the image which are inherited from the complex background. In this paper, we treat the problem of comparing text images for content-based retrieval purposes, by presenting a holistic approach to this issue. First, the shape of text is represented by estimating the salient points in the text image. Then, alignment shape methods are used to establish the correspondence of the salient points. Finally, a measure is suggested to compute the dissimilarity between two text images based on the generated correspondence. Empirical evaluation of the proposed holistic comparison method has demonstrated its very good performance