Wyniki wyszukiwania - BazTech

1

Problems of visualization of digital images for the blind persons with special attention paid to business graphics

Olejniczak M., Śmiałowski T., Chmielewski L., Orłowski A.

Information Systems in Management

|

2013

|

Vol. 2, No. 4

300--312

EN

Sight is the most important sense of a human. For the most of the society, the perception performed by the sight organ is perceived as something very natural. Reflection on life without the sight is not common, which slows down the technological development aiming at reducing the social exclusion of persons with sight disabilities. The dynamical development of advanced technologies does not provide solutions for all the cases of illness. However, many tools exist which allow people with visual disabilities to interact with the outside world. In most cases these tools allow only for the exchange of very basic information. We present some problems associated with the visualization of images for the blind, with the attention concentrated upon business graphics. We also give some propositions to enhance the level of non-visual perception of images with the use of specialized tactile equipment.

2

Wykorzystanie modeli ontologicznych na potrzeby budowy wspólnego obrazu pola walki

Chmielewski L.

Biuletyn Instytutu Systemów Informatycznych

|

2009

|

nr 3

19-28

PL

Fuzja danych i jej zastosowanie do konstrukcji wspólnego obrazu operacyjnego była traktowana jako poboczny element wykorzystywany w procedurach decyzyjnych. Praca ta prezentuje metodę integracji odrębnych obszarów danych pochodzących z pola walki z wykorzystaniem ontologii, mechanizmów wnioskujących. Opisywane podejście pozwala na organizację i filtrowanie danych bazujących na modelu semantycznym z wykorzystaniem predefiniowanych mechanizmów dedykowanych różnym poziomom dowodzenia oraz typom operacji. Połączenie reprezentacji semantycznej danych, mechanizmów języka zapytań SPARQL oraz środowiska GIS, pozwoliły na wytworzenie rozszerzalnych mechanizmów prezentacji informacji pola walki budujących jednolity obraz operacyjny pola walki (ang. Common Operational Picture). Publikowane w pracy wyniki uwzględniają analizę wojskowych standardów reprezentacji danych wykorzystywanych w badaniach. Bazując na przeglądzie dostępnych narzędzi i metod dedykowanych tej dziedzinie zaproponowana została bazowa ontologia wykorzystana do reprezentacji aktualnego scenariusza przestrzeni walki, wypełniona danymi geograficznymi oraz danymi dla algorytmów wspomagania dowodzenia. Artykuł zawiera opis wytworzonego podsystemu GIS wykorzystującego mechanizmy semantyczne wykorzystujące zewnętrzne heterogeniczne źródła Zautomatyzowanych Systemów Dowodzenia.

EN

This work concentrates mainly on methods of integrating several aspects of battlefield data using ontology models and presenting such data in rich GIS environment. Such approach allows to organize and filter data using predefined filters dedicated for various level of command and types of operations. Combining semantic data representation and semantic query languages like SPARQL allowed to produce extendable and rapid mechanism for information presentation which generates Common Operational Picture. Published results consist of analysis of known models representing different views on COP. Based on such study there have been proposed, a core ontology for representing current battlefield scenario filled with all geospatial information and data proposed by decision support algorithms and military domain analysis. This article describes designed layered architecture based on SOA and a proof-of-concept prototype demonstrating, a NEC integrated battlefield picture. The subsystem has been designed and prepared to be powered from external data sources such as heterogeneous C4I systems and other military-government data sources.

3

Assessment of the quality of radiotherapy with the use of portal and simulation images - the method and the software

Chmielewski L., Kukołowicz P., Gut P., Dąbrowski A.

Journal of Medical Informatics & Technologies

|

2002

|

Vol. 3

MI171--179

EN

Quality assessment in external beam radiotherapy necessitates for an efficient and robust tool for comparing the planned and realised geometry of the treatment. Such a tool using the modified Hausdorff distance measure has been developed and successfully introduced to clinical practice. The majority of steps of the method are automatic. The user specifies the share of edge data extracted from the images to be used in calculations, not before, but after these calculations are actually performed. Thus, the results of the choice can be seen immediately. This mechanism makes the method extremely robust against partially erroneous or missing data.

4

Morphological detection and feature-based classification of cracked regions in ferrites

Nieniewski M., Chmielewski L., Jóźwik A., Skłodowski M.

Machine Graphics and Vision

|

1999

|

Vol. 8, No. 4

699-712

EN

Automatic quality inspection of ferrite products is difficult as thier surfaces are dark and in many cases coverred with traces of grinding. A two-stage vision system for detection and measurement of crack regions was devised. In the first stage the regions with strong evidence for cracks are found using a morphological detector of irregular grightness changes with subsequent morphological reconstruction. In the second stage the feature-based k-Nearest Neighbors classifier analyzes the pixel indicated in the first stage. The classifier is optimized by using procedures of reclassification and replacement carried out on the reference set of pattern pixels to achieve a low error rate and a maximum speed of computation.

5

Interactive object detection using a fuzzy image segmentation approach

Mari M., Smits P. C., Kieś P., Chmielewski L.

Machine Graphics and Vision

|

1998

|

Vol. 7, No. 4

765-780

EN

In this paper the attention is focused on the processing of digital images, in particular on the segmentation of medical images. A new 3D fuzzy segmentation technique is presented to outline the adventages of a relatively simple software tool that may help the user to find contours of the objects of interest in images. The proposed technique is based on a seed growing approach, which takes into account both contextual and topological information in the image. The uncertainty of the image is considered through the use of fuzzy measures, well suited to represent the characteristics of a medical image. The result is a set of possible contours for the volume of interest at different certainty values. They mey be viewed as alternative comtours of the same object. If the method is used interactively, the user has the possibility to scroll very quickly through the different contours to select the most appropriate one for a specific application, according to his own knowledge.

6

A parallel net of (1-NN, K-NN) classifiers for optical inspection of surface defects in ferrites

Jóźwik A., Chmielewski L., Skłodowski M., Cudny W.

Machine Graphics and Vision

|

1998

|

Vol. 7, No. 1/2

99-112

EN

The challenging task of optical inspection of surface defects in ferrite cores has been successfully approached with a set of methods. In this paper the attention is paid to the k Nearest Neighbours classifier developed for the system. A parallel net of two-decision classifiers is presented. The combination of the 1-NN and k-NN rules reduces the training time. A great part of computations is restricted to the class overlap area. The classification quality is significantly improved if a separate feature selection for each of the component classifiers is done. A dramatic improvement of classification speed obtained by reference patterns sets reduction for component classifiers is vital, as in the considered task the classifier is used for recognition of pixels. The proposed modifications of the classifier are of general usefulness for pattern recognition. The presented quality inspection system can be applied to various defect detection tasks.