350 rub
Journal Science Intensive Technologies №9 for 2012 г.
Article in number:
Hybrid technologies on the basis of multidimensional spectral analysis and neural-net simulation for processing ophthamic eyeground images
Authors:
R.A. Tomakova, M.A. Efremov, A.A. Naser
Abstract:
Block diagram for segmentation of eyeground images, based on the use of hybrid technologies for information processing is considered in this article. There has been proposed the use of two-stage filtration in frequency region for automated analysis of eyeground images. There has been also given a block diagram for segmentation of eyeground image in frequency region. In order to be analyzed the initial image is divided into typical segments. Method of amplitude quantisation of modes of corresponding frequencies has been used to increase quality of obtained image. Proposed method for analysis of eyeground image has been realized in the problem of revealing druses of optical nerve disk. Non-linear filtration by means of one-layer neural network for two-dimentional spectrum has been realized in this work. There has been also fulfilled visualization of the segment to be found by means of discrete Fourier inversion.
Pages: 59-65
References
  1. Ильясова Н.Ю., Устинов А.В., Баранов В.Г. Экспертная компьютерная система диагностики глазных заболеваний по изображениям глазного дна // Компьютерная оптика. 1999. №19. С. 202-209.
  2. Пихлап С.В., Грахов А.А., Кузьмин А.А., Филист С.А. Использование метода адаптивного квантования мод при исследо­вании вейвлет-изображений электрокардиосигналов больных ишемической болезнью сердца // Известия ЮФУ. Технические науки. Тематический выпуск. «Медицинские информационные системы». Таганрог. 2008. №5(82). С. 76-79.
  3. Кацнельсон Л.А., Лысенко В.С., Балишанская Т.И. Клинический атлас патологии глазного дна. Издательство: ГЭОТАР-Медиа. 2008.
  4. Осовский С. Нейронные сети для обработки информации. М.: Финансы и статистика. 2002.