Please use this identifier to cite or link to this item: http://gukir.inflibnet.ac.in:8080/jspui/handle/123456789/3673
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHiremath P.S
dc.contributor.authorAkkasaligar P.T
dc.contributor.authorBadiger S.
dc.date.accessioned2020-06-12T15:01:05Z-
dc.date.available2020-06-12T15:01:05Z-
dc.date.issued2009
dc.identifier.citationProceedings of the 4th Indian International Conference on Artificial Intelligence, IICAI 2009 , Vol. , , p. 1814 - 1827en_US
dc.identifier.urihttp://gukir.inflibnet.ac.in:8080/jspui/handle/123456789/3673-
dc.description.abstractThe narrowband ultrasound image suffers from a speckle noise. A novel method of medical ultrasound image despeckling using the contourlet transform is presented. The log transformed ultrasound image is contourlet transformed to obtain contourlet coefficients. The number of levels of Laplacian pyramidal decomposition, the number of directional decompositions to perform on each pyramidal level are determined. The transformed image is denoised by applying thresholding technique on individual bandpass subbands using a Bayes' shrinkage rule. The performance is measured in terms of variance, Mean Square Error (MSE), Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR) and Correlation Coefficient (CC). Finally, a comparison of performance of wavelet-based despeckling and contourlet based despeckling is provided. It is shown that the contourlet transform method has better performance than wavelet transform method. Despeckling is performed on medical ultrasound images to improve visual quality for better image analysis and diagnosis. Copyright © 2009 by IICAI.en_US
dc.subjectContourlet transform
dc.subjectDespeckling
dc.subjectDirectional filter bank
dc.subjectLaplacian pyramid transform
dc.subjectUltrasound image
dc.titleDespeckling medical ultrasound images using the contourlet transformen_US
dc.typeConference Paper
Appears in Collections:2. Conference Papers

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.