Presentation | 2005-05-19 Principle Component Analysis for Region-based Segmentation of MR Images Yuta IWASAKI, Yen Wei CHEN, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we proposed a robust segmentation method for MR images with noise by using region information. The feature vector is extracted from a 3x3 region. Compared with the conventional pixel-based method, the proposed region-based method is tolerant and robust to the noise, but the dimensionality of the feature vector is much larger than that of the conventional method. We also propose to use principle component analysis (PCA) as a preprocessing to reduce the large dimensionality. The experimental results show that the proposed method is superior to the conventional method with the same dimensionality of feature vector. In addition, the algorithm of K-means is used for un-supervised clustering. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Principle Component Analysis / MR image / robust segmentation / un-supervised clustering |
Paper # | PRMU2005-10,MI2005-10 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2005/5/12(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Principle Component Analysis for Region-based Segmentation of MR Images |
Sub Title (in English) | |
Keyword(1) | Principle Component Analysis |
Keyword(2) | MR image |
Keyword(3) | robust segmentation |
Keyword(4) | un-supervised clustering |
1st Author's Name | Yuta IWASAKI |
1st Author's Affiliation | Information Science and Systems Engineering, Graduate School of Science and Engineering, Ritsumeikan University() |
2nd Author's Name | Yen Wei CHEN |
2nd Author's Affiliation | Department of Media Technology, Callege of Information Science and Engineering, Ritsumeikan University |
Date | 2005-05-19 |
Paper # | PRMU2005-10,MI2005-10 |
Volume (vol) | vol.105 |
Number (no) | 62 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |