Документ взят из кэша поисковой машины. Адрес
оригинального документа
: http://imaging.cs.msu.ru/en/publication?id=288
Дата изменения: Sun Apr 10 03:41:44 2016
Дата индексирования: Sun Apr 10 03:41:44 2016
Кодировка: IBM-866
HeNLM-3D: A 3D Computer Tomography Image Denoising Algorithm
Publication type
Conference paper
Author(s)
N. Mamaev, A. Lukin, D. Yurin
Publication date
May 2014
Conference
The 12th International Conference on Pattern Recognition and Information Processing
Page(s)
176-180
Address
28тАУ30 May 2014, Minsk, Belarus
Publisher
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Abstract
A 3D filtering algorithm for CT images is proposed (HeNLM-3D). It is an extension of the known Local Jets method (LJNLM-LR) and our previous 2D algorithm (HeNLM). The proposed algorithm is based on the expansion of pixel neighborhoods into Hermite functions which form the orthonormal system. Tests on real CT images have shown that HeNLM-3D performs filtering better in high-detailed areas in comparison with LJNLM-LR and classical NLM method.