COMPARATIVE ANALYSIS ON METRICS AND FILTERS TO REDUCE IMPULSIVE NOISE IN MEDICAL IMAGES USING GPU

M. Guadalupe Sánchez, Vicente Vidal, Jordi Bataller

Abstract

In many current applications of image processing, eliminating the noise is an important task in the pre-processing phase. In medicine, medical imaging obtained by X-ray and computed tomography, for example, mammograms, can have different types of noise, making it difficult to visually and to detect microcalcifications. We have adapted a noise reduction method for color images that gives good results for grayscale images. In the first step of the method, the corrupted pixels are detected using the concept of peer group with a metric and then is corrected by some kind of filter. This paper presents an algorithm with a very good balance between quality and computational cost to removing impulsive noise in mammography images. With regard to quality, we compared three metrics (two Fuzzy and one Euclidean) and two filters (Arithmetic Mean and Median). To reduce the computational cost, the method is parallelized on a Graphic Processing Unit. The quality results show that the metrics studied yield similar results, being the Euclidean metric less expensive computationally. On the other hand, the filter must be chosen depending on the density of noise in the input image.

References

  1. Bioucas, J. and Figueiredo, M. (2009). Total variation restoration of speckled images using a split-bregman algorithm. In Image Processing (ICIP).
  2. Camarena, J., Gregori, V., Morillas, S., and Sapena, A. (2008). Fast detection and removal of impulsive noise using peer group and fuzzy metrics. In Journal of Visual Communication and Image Representation 19.
  3. Camarena, J., Gregori, V., Morillas, S., and Sapena, A. (2010). Some improvements for image filtering using peer group techniques. In Image and Vision Computing 28.
  4. Database (2003). http://peipa.essex.ac.uk/info/mias.html. In The mini-MIAS database of mammograms.
  5. Gonzalez, R. and Woods, R. (1995). Digital Image Processing. Person International.
  6. Jin, L., Liu, H., Song, E., and Xu, X. (2010). Impulsive noise removal using switching scheme and adaptive weighted median filters. In Society of Photo-Optical Instrumentation Engineers 49.
  7. Jin, Z. and Yang, X. (2010). A variational model to remove the multiplicative noise in ultrasound images. In Journal of Mathematical Imaging and Vision.
  8. Kang, C. and Wang, J. (2009). Fuzzy reasoning-based directional median filter design. In Signal Processing.
  9. Lopez, A. (2010). Metricas fuzzy. aplicaciones al filtrado de imagenes en color. In Phd Thesis Universidad Politecnica de Valencia.
  10. Morillas, S., Gregori, V., Peris, G., and Latorre, P. (2005). A fast impulsive noise color image filter using fuzzy metric. In Real-Time Imaging 11.
  11. Nair, M. and Reji, J. (2011). An efficient directional weighted median switching filter for impulse noise removal in medical images. In Communications in Computer and Information Science 192.
  12. Padma, A., Sukanesh, R., and Vijayan, S. (2010). An efficient directional weighted median switching filter for impulse noise removal in medical images. In International Journal of Computer Applications.
  13. Sanchez, M., Vidal, V., and Bataller, J. (2011). Peer group and fuzzy metric to remove noise in images using heterogeneous computing. In HeteroPar.
  14. Sanchez, M., Vidal, V., Bataller, J., and Arnal, J. (2010). Implementig a gpu fuzzy filter for impulsive image noise correction. In CMMSE.
  15. Smolka, B. (2005). Fast detection and impulsive noise remolval in color images. In Real-Time Imaging 11.
  16. Toh, K. and Isa, N. (2010). Noise adaptive fuzzy switching median filter for salt-and-pepper noise reduction. In Signal Processing Letters, IEEE.
  17. Zhang, X. and Xiong, Y. (2009). Impulse noise removal using directional difference based noise detector and adaptive weighted mean filter. In Signal Processing Letters, IEEE.
Download


Paper Citation


in Harvard Style

Guadalupe Sánchez M., Vidal V. and Bataller J. (2012). COMPARATIVE ANALYSIS ON METRICS AND FILTERS TO REDUCE IMPULSIVE NOISE IN MEDICAL IMAGES USING GPU . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: MIAD, (BIOSTEC 2012) ISBN 978-989-8425-89-8, pages 534-539. DOI: 10.5220/0003892605340539


in Bibtex Style

@conference{miad12,
author={M. Guadalupe Sánchez and Vicente Vidal and Jordi Bataller},
title={COMPARATIVE ANALYSIS ON METRICS AND FILTERS TO REDUCE IMPULSIVE NOISE IN MEDICAL IMAGES USING GPU},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: MIAD, (BIOSTEC 2012)},
year={2012},
pages={534-539},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003892605340539},
isbn={978-989-8425-89-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: MIAD, (BIOSTEC 2012)
TI - COMPARATIVE ANALYSIS ON METRICS AND FILTERS TO REDUCE IMPULSIVE NOISE IN MEDICAL IMAGES USING GPU
SN - 978-989-8425-89-8
AU - Guadalupe Sánchez M.
AU - Vidal V.
AU - Bataller J.
PY - 2012
SP - 534
EP - 539
DO - 10.5220/0003892605340539