In this article image have been subject to segmentation using Matlab software, i.e. T1 in normal conditions, perfusion images and images after administering a contrast agent. The tumor in images made in normal conditions was difficult to identify. The images obtained after administering the contrast agent confirmed that the homogeneity criterion has been appropriately selected. In perfusion images the pixels of the background were added to the tumor. When the parameters were changed i.e. pixel counter or neighborhood type the method became more efficient; the tumor boundaries were outlined more precisely. The region growing method enables precise tumor detection; however, the selection of an appropriate homogeneity criterion is a prerequisite for correct segmentation.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The Biomedical Engineering appeared as an academic discipline at Polish universities five years ago. Since that time, many young people have chosen it as their future profession. A few hundreds have already received the engineer degree. Most of them decided to continue their education to become Master of Science in Biomedical Engineering. The Silesian University of Technology has been providing courses in Biomedical Engineering since 2007. Currently, on each of the four years of studies 60-100 students participate in various available courses. The education process started at the Faculty of Automatic Control, Electronics and Computer Science, and now continues within the new Faculty of Biomedical Engineering, the first and only in Poland at the moment. Knowledgeable and experienced professors, wide spectrum of cooperating medical, industrial and academical units and freshly equipped labs allow to provide the offer of modern studies in a challenging and interdisciplinary domain. The paper presents various aspects of biomedical engineering as it was in past and as it is today. A brief presentation of its history, educational offer, cooperating entities and infrastructural facilities as well as a summary of experiences after four years of studies and a short review of the research are included.
Praca przedstawia zastosowanie sumy gaussowskiej GMM do identyfikacji języka wypowiedzi. W trakcie badań sprawdzono wpływ długości wypowiedzi na stopę poprawnej identyfikacji. Badania przeprowadzono dla 15 języków zarówno europejskich jak i azjatyckich. Jako model języka wykorzystano sumę gaussowską GMM o pełnej macierzy kowariancji. Omówiono uzyskane rezultaty.
EN
The paper describes application of gaussian mixture models GMM to the task of spoken language identification.The influence of the length of the test utterances on identification error rate was examined. During identification procedure recordings for 15 languages were used, both European and Asian ones. As a language model GMM with full covariance matrix was applied. Obtained results of identification error rate were discussed.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.