DocumentCode :
3228168
Title :
3D Multiresolution Analysis for reduced features segmentation of medical volumes using PCA
Author :
Zu´bi, S.A. ; Islam, Naveed ; Abbod, Maysam
Author_Institution :
Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK
fYear :
2010
fDate :
6-9 Dec. 2010
Firstpage :
604
Lastpage :
607
Abstract :
3D volume segmentation aims at partitioning the voxels into 3D objects (sub-volumes) which represent meaningful physical entities. Multi-resolution analysis (MRA) allows for the preservation of an image according to certain levels of resolution or blurring. The quality of this approach makes it useful in image compression, de-noising, and classification or segmentation. This paper focuses on the implementation of a medical volume segmentation technique using 3D Discrete Wavelet Transform (3D-DWT). Principle Component Analysis (PCA) has been presented to reduce the dimensionality of the 3D volume as a pre-processing step of 3D-DWT to accelerate the segmentation process.
Keywords :
data compression; feature extraction; image classification; image coding; image resolution; image restoration; image segmentation; medical image processing; principal component analysis; wavelet transforms; 3D discrete wavelet transform; 3D multiresolution analysis; 3D object; 3D volume segmentation; PCA; image blurring; image classification; image compression; image denoising; image resolution; medical volume segmentation technique; physical entity; principle component analysis; reduced feature segmentation; Biomedical imaging; Image segmentation; Multiresolution analysis; Principal component analysis; Three dimensional displays; Wavelet transforms; Feature Reduction; Medical images; PCA; Wavelet;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems (APCCAS), 2010 IEEE Asia Pacific Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4244-7454-7
Type :
conf
DOI :
10.1109/APCCAS.2010.5774847
Filename :
5774847
Link To Document :
بازگشت