Отрывок: After removing hair to the image, a median filter with a dynamic window is applied to eliminate noise in the image. The size of the window is determined by the experimental formula. Next, the algorithm is applied to the image clustering (in terms of brightness) ISODATA (Iterative Self- Organizing Data Analysis Technique). The ISODATA algorithm is designed to divide a given set of images (in this case, two-dimensional space points) into subsets (clusters) bound by a cert...
Полная запись метаданных
Поле DC Значение Язык
dc.contributor.authorMelsitov, O.A.-
dc.contributor.authorSherendak, V.P.-
dc.contributor.authorKonovalov, S.G.-
dc.contributor.authorMyakinin, O.O.-
dc.date.accessioned2018-05-18 09:58:57-
dc.date.available2018-05-18 09:58:57-
dc.date.issued2018-
dc.identifierDspace\SGAU\20180513\69115ru
dc.identifierDspace\SGAU\20180516\69115ru
dc.identifier.citationMelsitov O.A. Automatic Malignant Melanoma recognition using a Dermatoscopy Imaging Tool / O.A. Melsitov, V.P. Sherendak, S.G. Konovalov, O.O. Myakinin // Сборник трудов IV международной конференции и молодежной школы «Информационные технологии и нанотехнологии» (ИТНТ-2018) - Самара: Новая техника, 2018. - С.925-929ru
dc.identifier.urihttp://repo.ssau.ru/handle/Informacionnye-tehnologii-i-nanotehnologii/Automatic-Malignant-Melanoma-recognition-using-a-Dermatoscopy-Imaging-Tool-69115-
dc.description.abstractIn this paper, we present the results of analysis of 56 in vivo multispectral dermatoscopy images of Malignant Melanoma and other benign and malignant skin tumors. The special own developed dermatoscopy tool analyzes pictures of suspicious skin areas and makes a decision using a special software based on texture and color analysis, which raise up the accuracy of diagnosis. Using our software, high accuracy (96% sensitivity and 89% specificity) in the personalized mode for melanoma has been achieved, which means a principal opportunity of effective excluding similar formations that are not melanoma. Additionally, considering to the high speed and accuracy of the automatic recognition, the proposed dermatoscopy tool can be used for screening procedures.ru
dc.description.sponsorshipThis research was supported by the Ministry of Education and Science of the Russian Federation.ru
dc.language.isoenru
dc.publisherНовая техникаru
dc.subjectMelanoma detectionru
dc.subjectdermatoscopyru
dc.subjectmelanoma recognitionru
dc.subjectimage analysisru
dc.titleAutomatic Malignant Melanoma recognition using a Dermatoscopy Imaging Toolru
dc.typeArticleru
dc.textpartAfter removing hair to the image, a median filter with a dynamic window is applied to eliminate noise in the image. The size of the window is determined by the experimental formula. Next, the algorithm is applied to the image clustering (in terms of brightness) ISODATA (Iterative Self- Organizing Data Analysis Technique). The ISODATA algorithm is designed to divide a given set of images (in this case, two-dimensional space points) into subsets (clusters) bound by a cert...-
Располагается в коллекциях: Информационные технологии и нанотехнологии

Файлы этого ресурса:
Файл Описание Размер Формат  
paper_125.pdfОсновная статья431.65 kBAdobe PDFПросмотреть/Открыть



Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.