IMTA 2010 Abstracts


Full Papers
Paper Nr: 1
Title:

Shadow Artifacts Correction on Fine Art Reproductions

Authors:

S. A. Bibikov, V. A. Fursov and A. V. Nikonorov

Abstract: The paper under consideration deals with information technology for correction of shadow artifacts on colour digital images obtained by taking photos of paintings with the purpose of their reproduction. Appearance of shadow artefacts is caused by different intensity of picture lighting. The problem of shadow detection and subsequent colour correction in this area is solved.

Paper Nr: 2
Title:

An Image Analysis Algorithm of Estimates Calculation on a Plane

Authors:

Valeriy Osipov

Abstract: An implementation of image recognition algorithms based on estimate calculation (2D AEC) with rectangular support sets is proposed. The article includes the sample. Let we have a photo of starry arch star map. The problem is to recognize stars on the photo. The algorithm calculates the array of estimates, and then we apply a decision rule.

Paper Nr: 4
Title:

Image Formalization via Descriptive Image Algebras

Authors:

Igor Gurevich and Vera Yashina

Abstract: In the framework of the Descriptive approach to image analysis and understanding, the concept of Image Formalization Space (IFS) is introduced. The elements of IFS are the different image representation forms through which a raw image passes while it is transformed into a recognizable form, i.e., into an image model. The structure and the main objects of the IFS are characterized and discussed. A system of concepts and a formal apparatus of descriptive image models are introduced to state the main axioms constituting the conceptual foundation for image formalization in image analysis and recognition. The topology of IFS is given by descriptive image algebra defining operations on pixels and their configurations, on pixel values, and on image states constructed using these operations.

Paper Nr: 5
Title:

The Technology of Dynamic Extension of Attribute Set for the Search of Satellite Images in a Database

Authors:

Yuri Maglinets, Eugene Maltsev, Ruslan Brejnev, Alexey Sosnin and Victor Kurnosov

Abstract: The structures of metafiles for describing satellite images of the Earth we analyze in this article. We describe the architecture of interaction among the satellite images database components at the automated registration of new-type sensors. We offer the technology of dynamic extension of the attribute set for the search of satellite images in a database.

Paper Nr: 8
Title:

Image Mining for Infomobility

Authors:

Massimo Magrini, Davide Moroni, Christian Nastasi, Paolo Pagano, Matteo Petracca, Gabriele Pieri, Claudio Salvadori and Ovidio Salvetti

Abstract: The wide availability of embedded sensor platforms and low-cost camera sensors – together with the developments in wireless communication – make it now possible the conception of pervasive intelligent systems based on vision. Such systems may be understood as distributed and collaborative sensor networks, able to produce, aggregate and process images in order to mine the observed scene and communicate the relevant information found about it. In this paper, we investigate the peculiarities of visual sensor networks with respect to standard vision systems and we identify possible strategies to tackle the image mining problem. We argue that multi-node processing methods may be envisaged to decompose a complex task into a hierarchy of computationally simpler problems to be solved over the nodes of the network. We illustrate these ideas by describing an application of visual sensor network to infomobility.

Paper Nr: 9
Title:

Detection of Iris in Image by Brightness Gradient Projections

Authors:

Ivan A. Matveev

Abstract: A method is proposed to detect a human iris location and size in digital image given some point lying inside the pupil. Method is based on construction of histogram projections of local brightness gradients and interrelating local maxima of these histograms as probable positions of pupil and iris borders. Method has low calculation cost.

Paper Nr: 10
Title:

On the Construction of Gestalt-Algebra Instances and a Measure for their Similarity

Authors:

Eckart Michaelsen

Abstract: Four construction principles that compose more complicated percep-tual gestalts from less complex ones are defined in detail: Mirror gestalts, lattice gestalts, rotational mandalas, and clusters, respectively. These can be encapsu-lated as constructions in a production system. Since any of the four constructions can work on any gestalt, a recursive and very expressive scheme is set up with many prospective applications in image mining. Of particular interest is such analysis for aerial and satellite images and for façade images of buildings.

Paper Nr: 11
Title:

An Image-based Framework for Intellectual Decision Making in Medical Research

Authors:

Sara Colantonio, Igor Gurevich, Ovidio Salvetti and Yulia Trusova

Abstract: Medical decisional problems strongly rely on the analysis and inter-pretation of diagnostic images acquired by different investigation techniques. Information extraction and correlation from these are usually demanding tasks that can burden the routine work of clinicians. In this paper, an image-based framework is presented which is devoted to the automated extraction of know-ledge and data from biomedical images used for intellectual decision making in clinical and medical research. An ontological approach is adopted for encoding different kind of knowledge required in problem solving. Modelling the pre-clinical stage of Parkinson's disease is presented as eligible case study.

Paper Nr: 12
Title:

Pattern Recognition Imaging for AFM Measurements

Authors:

Mario D’Acunto and Ovidio Salvetti

Abstract: The focus of this paper is on an algorithm for distortion corrections for atomic force microscope (AFM) recorded images. AFM is a fundamental tool for the investigation of a wide range of mechanical properties due to the contact interaction between the AFM tip and the sample surface. When a sequence to AFM images correspondent to the same area are recorded, it is common to observe convolution of thermal drift with surface modifications due to the AFM tip stresses. The surface modifications are material properties and add knowledge to the response of the materials on nanoscale. As a consequence, a suitable de-convolution of the thermal drifts on the recorded images need to be developed. In this paper, we present a method for correcting thermal drifts where the original images are corrected using a low-order polynomial mapping function. The precision achieved and the fast computation time required make our method particularly useful for image analysis in a wide range of applications.

Paper Nr: 13
Title:

Dynamical Segmentation of Images for the Problems of Medical Diagnostics

Authors:

Evgeny Maryaskin, Sergey A. Ivanovsky and Anatoly Nemirko

Abstract: This article describes software realized method, suggested for the analysis of medical data. The methods are illustrated by the examples in the fields of echocardiography and angiography. Dynamic scenes segmentation and motion detection, based on optical flow calculation underlie this method. The description is illustrated by model and real medical data examples. The results may be used in applied tasks of dynamic segmentation of medical images.

Paper Nr: 14
Title:

Automatic Determining of Vertebrae from CT Images

Authors:

B. A. Zalesky, A. M. Nedzved, S. V. Ablameiko and P. V. Lukashevich

Abstract: Position of the spinal column and vertebrae on the CT images is one of the main features to determine position of a patient and his organs. In this paper we propose the algorithm to extract the spinal column and vertebrae with ribs from CT images and to estimate their coordinates as well as coordinates of human body in the coordinate system of a CT scanner.

Paper Nr: 15
Title:

Novel Method of the Noise-Reduction in 3D X-Ray Computed Tomography

Authors:

N. S. Kulberg, T. V. Yakovleva, Yu. R. Kamalov, V. A. Sandrikov, L. V. Osipov and P. A. Belov

Abstract: There is described a novel technique of the noise suppression in X-Ray computed tomography (CT) images. At describing this technique a special attention is paid to the subsequent 3D reconstruction of the human body internal structures being investigated. The work has been implemented under the support of the Russian Foundation of Basic Research (RFBR), project Nº 08-01-12011-ofi.

Paper Nr: 18
Title:

Usage of Positional Representations in Tasks of Revealing Logical Regularities

Authors:

Yury Laptin, Alexander Vinogradov and Yury Zhuravlev

Abstract: A new approach to the problem of description of clusters in the form of sets of logical regularities is developed. Special attention is paid to detection of steady interrelations in data which are valid for considerable shares of the sample. The approach is based on usage of fast bit operations and positional method of data representation. New criterion of adjacency is proposed for high-level points of the representation, and it’s used further in the process of assembling such points in maximal hyper-parallelepipeds corresponding to the best regularities. The method can be used as preliminary step in various tasks related to the search of essential logical regularities and substantial interpretation of data.

Paper Nr: 19
Title:

An Algorithmic Scheme for Construction and Investigation of Parkinson’s Disease Model

Authors:

I. Gurevich, E. Kozina, A. Myagkov, H. Niemann, M. Ugrumov and V. Yashina

Abstract: This work continues the development of mathematical tools and information technology elements for automated extraction and characterization of objects in striatum section images. The latter are used to construct a Parkinson disease model at a preclinical stage. Previously an automatic segmentation method for extracting of objects from striatum section image was developed. Now it is enhanced and extended to a form of an algorithmic scheme. It allows reducing brain section images to a form appropriate for recognition. Experimental applications of the developed technique have confirmed its high efficiency and suitability for automated processing and analysis of brain section images (a 200 times increase in productivity and a 10 times decrease in the amount of animals and expendables).

Paper Nr: 20
Title:

Cavity Shape from Parallel Linear Shading: A Low-cost Technique to Collect Data for an Image Mining Oriented Geoprocessing System

Authors:

Edvar Ferreira da Rocha Júnior, Vanessa Gonçalves da Silva, Renato da Veiga Guadagnin, Levy Aniceto Santana, Rinaldo de Souza Neves and Jose Antonio Iturri de La Mata

Abstract: An Image Mining oriented Geoprocessing depends essentially on spatially defined information from images. So it is possible to support decisionmaking quite suitably in several areas, such as environment management, urban management and health care. When large-scale use of image capturing and interpretation devices becomes possible, it seems attractive to have low cost additional infrastructures. This paper discusses the extraction of geometric features of cavities, primarily motivated by the need for monitoring patients with wounds called pressure ulcers (PU). An image with linear shadows on the cavity of a model is generated in order to enable the measurement of its deformation caused by depth. This yields maximum depth and volume in an experimental model that are compared with measurements made previously in a conventional manner. Differences with conventional measurements are partially satisfactory and suggest further improvements in image capturing device and computational procedures.