Fluorosocopic sequence denoising using a motion compensated multi-scale temporal filtering

Autor:	Carole Amiot, Michel Desvignes, C. Girard, Jérémie Pescatore, Jocelyn Chanussot
Rok vydání:	2015
Předmět:	Motion compensation business.industry Noise reduction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Quarter-pixel motion Wavelet Match moving Filter (video) Motion estimation Computer vision Video denoising Artificial intelligence business Mathematics
Zdroj:	ICIP
DOI:	10.1109/icip.2015.7350887
Popis:	We propose a temporal motion-compensated filter operating on dual-tree complex wavelet coefficients to denoise low-dose X-ray sequences. This filter allows for a great noise reduction while preserving moving objects and structures. We take advantage of the properties of multi-scale spaces to perform a fast and robust motion tracking. The result of this step is then used in the temporal filter for denoising purpose. Quantitative and qualitative analysis on real fluoroscopic sequences show that our method outperforms state-of-the-art VBM3D method and allows for a dose reduction as high as 80%.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::1d95750d9416048935c04c8d61ae3c0e https://doi.org/10.1109/icip.2015.7350887 Zobrazit plný text záznamu