Open AccessNOISE REDUCTION METHOD FOR OCT IMAGES BASED ON EMPIRICAL MODE DECOMPOSITION
Author(s) -
Oleg O. Myakinin,
Dmitriy V. Kornilin,
Ivan А. Bratchenko,
Valery P. Zakharov,
Alexander G. Khramov
Publication year - 2013
Publication title -
journal of innovative optical health sciences/journal of innovation in optical health science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.421
H-Index - 24
eISSN - 1793-5458
pISSN - 1793-7205
DOI - 10.1142/s1793545813500090
Subject(s) - hilbert–huang transform , reduction (mathematics) , noise reduction , computer science , noise (video) , artificial intelligence , process (computing) , computer vision , canny edge detector , decomposition , enhanced data rates for gsm evolution , segmentation , pattern recognition (psychology) , image processing , algorithm , edge detection , image (mathematics) , mathematics , ecology , geometry , filter (signal processing) , biology , operating system
In this paper, the new method for OCT images denoizing based on empirical mode decomposition (EMD) is proposed. The noise reduction is a very important process for following operations to analyze and recognition of tissue structure. Our method does not require any additional operations and hardware modifications. The basics of proposed method is described. Quality improvement of noise suppression on example of edge-detection procedure using the classical Canny's algorithm without any additional pre- and post-processing operations is demonstrated. Improvement of raw-segmentation in the automatic diagnostic process between a tissue and a mesh implant is shown