Abstract
A denoising algorithm for computed tomography images is proposed. The presented method of noise reduction uses Markov Random Field (MRF) model, Gaussian filter and adaptive Prewitt Mask, what gives better results than standard approach of using only the MRF. This implementation on Compute Unified Device Architecture is made, what makes this computationally complex denoising method faster.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cierniak, R.: X-Ray Computed Tomography in Biomedical Engineering. Springer, London (2011)
Weickert, J.: Anisotropic diffusion in image processing, vol. 1. Teubner, Stuttgart (1998)
Panjwani, D.K., Healey, G.: Markov random field mod-els for unsupervised segmentation of textured color images. IEEE Trans. on Pattern Analysis and Machine Intelligence 17(10), 939â954 (1995)
Yang, X.Y., Liu, J.: Unsupervised texture segmentation with one-stepmean shift and boundary Markov random fields. Pattern Recognition Letters 22(10), 1073â1081 (2001)
Kaushal, M., Singh, A., Singh, B., Kaushal, M.: Adaptive Thresholding for Edge Detection in Gray Scale Images. International Journal of Engineering Science and Technology 2 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Knas, M., Cierniak, R. (2015). Computed Tomography Images Denoising with Markov Random Field Model Parametrized by Prewitt Mask. In: ChoraĆ, R. (eds) Image Processing & Communications Challenges 6. Advances in Intelligent Systems and Computing, vol 313. Springer, Cham. https://doi.org/10.1007/978-3-319-10662-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-10662-5_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10661-8
Online ISBN: 978-3-319-10662-5
eBook Packages: EngineeringEngineering (R0)