Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/8577
標題: 以線性光譜之紋理分析作為腦部MR影像混合組織之分類
Texture Analysis for Linear Spectral Unmixing of Brain MR Image Classification
作者: 李宏哲
Li, Hung-Che
關鍵字: 線性頻譜混合分類法 (LSU)
full constraint least squares (FCLS)
灰階共現矩陣(GLCM)
特徵紋理分析
gray level co-occurrence matrix (GLCM)
texture analysis
linear spectral unmixing (LSU)
出版社: 電機工程學系所
引用: [1] P. Suete, ‘Fundamentals of Medical Imaging,' Cambridge University Press, New York, 99 -118, 2002. [2] C. I. Chang, “Hyperspectral Imaging, Techniques for Spectral Detection and Classification”, Kluwer Academic/Plenum Publishers, New York, 40-41, 2003. [3] J. C. Harsanyi, and C. I. Chang, “Hyperspectral image classification and dimensionality reduction: and orthogonal subspace projection approach,” IEEE Trans. on Geoscience and Remote Sensing, 32(4), 779-785, 1994. [4] T. M. Tu, C. H. Chen and C. I. Chang, “A posteriori least squares orthogonal subspace projection approach to weak signature extraction and detection,” IEEE Trans. on Geoscience and Remote Sensing, 35(1), 127-139, 1997. [5] R. M. Harakick, R. Shanmugan and L. Dinstein, “Texture features for image classification” IEEE Trans. Syst. Man. Cyb., vol. SMC-3, no. 6, pp.610-216,1973. [6] J. C. Harsanyi and C. I. Chang, “Hyperspectral image classification and dimensionality reduction: An orthogonal subspace projection,” IEEE Trans. Geosci. Remote Sens., vol. 32, no. 4, pp. 779-785, Jul. 1994. [7] C. I. Chang, and Heinz, D. C., “Constrained Subpixel Target Detection for Remotely Sensed Imagery,” IEEE Transactions on Geoscience and Remote Sensing, 38(3), 1144-1159, 2000. [8] J. J. Settle and N. A. Drake, “linear mixing and estimation of ground cover proportions” Int. J. Remote Sensing, vol.14, no.6, pp.1159-1177, 1993. [9] D. Henz, C. I. Chang, and M. L. G. Althouse, “Fully constraint least squares-based linear unmixing”. [10] E. L. Wong and C. I. Chang, “Linear spectral unmixing approaches to magnetic resonance image analysis,” SPIE Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIV, March 16-20, Orlando, Florida, 2008. E. L. Wong, “Linear spectral unmixing approaches to magnetic resonance classification” M.S. 2008. [11] D. Heinz, C. I. Chang, and M. L. G. Althouse, “Fully constrained least square-based linear unmixing, ” in Int. Geoscience and Remote Sensing Symp.'99, Hamburg, Germany, pp. 1401-1403, June 28-July 2 1999. [12] H. Ren, and C. I. Chang, “A generalized orthogonal subspace projection approach to unsupervised multispectral image classification,” IEEE Trans. on Geoscience and Remote Sensing, 38(6), 2515-2528, 2000. [13] Y. C. Ouyang, H. Chen, J. Chai, C. Chen, S. Poon, C. Yang, S. Lee, “Independent component analysis for magnetic resonance image analysis,” EURASIP Adv. Signal Process, 2008. [14] Y. C. Ouyang, H. M. Chen, J. W. Chai, C. C. C. Chen, S. K. Poon, C. W. Yang, S. K. Lee and C. I. Chang, “Band expansion-based over-complete independent component analysis for magnetic resonance image analysis,” IEEE Trans. Biomedical Engineering, 2008. [15] Y. C. Ouyang, H. M. Chen, J. W. Chai, C.C.C. Chen, S. K. Poon, C. W. Yang, S .K. Lee “Independent component analysis for magnetic resonance image analysis,” EURASIP Advances in Signal Processing, 2008. [16] R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for classification,” IEEE Trans. Syst. Man, Cybern, vol. SMC-3, pp.610-621.Now, 1973. [17] C. I. Chang, Senior Member, IEEE “Linear spectral unmixing-based texture analysis for hyperspecral image classification. [18] D. Heinz and C. Chang “Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery,” IEEE Trans. Geosci. Remote Sensing, vol. 39, pp. 529-545, Mar. 2001. [19] L. K. Soh and C. Tsatsoulis “Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 37, No. 2, pp. 780-795, 1999. [20] M. H. Horng, “Texture feature coding method for texture classification, “Opt. Eng., Vol 42 (1), pp. 228-238, 2003. [21] D. C. He and L. Wang, ‘Texture classification using texture spectrum,” Pattern Recognition, vol. 23, pp905-910, 1990. [22] http://www.bic.mni.mcgill.ca/brainweb, first date: May, 1997; last modified date: Jun, 2006.
摘要: 最近幾年線性頻譜混合分類法Linear spectral unmixing (LSU) 應用在腦部核磁共振影像分類並且展現出在分類表現上潛在的能力。過去的分類方式主要強調於影像內部(Inter)像素的關係,LSU分類方法則是強調頻譜與頻譜之間的特性探究頻譜像素與頻譜像素之間(Intra)的關係,因此,LSU主要的能力處理混合像素的分類以預測分類項目組織的部份以一個像素來表示,像素將提供給我們資訊 讓我們知道預測的分類組織該被分到哪一個特別的類別。因為LSU是利用影像intra-pixel的關係,沒有利用到傳統影像分類方法的inter-pixel關係,所以LSU方法無法跟傳統方法一樣進行單純像素分類必須藉由硬的決策取代軟的決策才能將混合的像素以單純像素呈現,為了要讓LSU方法可以進行單純像素分類,我們進行以特徵紋理方法為主要的後處理結合LSU方法進行頻譜與空間性的分析。具體來說,後處理主要利用灰階共現矩陣Gray level co-occurrence matrix (GLCM) 找到不同的紋理特徵 這些紋理特徵值將被當作倒傳遞類神經網路Back propagation neural network 的訓練樣本,讓倒傳遞類神經網路幫助我們做分類。為了要驗證我們特徵紋理基於線性頻譜混合分類法所要達到的表現,我們利用實驗來推導和分析運算的結果。
Linear spectral unmixing (LSU) has recently applied to MR image classification and shown potential in MR image classification. Unlike the traditional classification which is mainly focused on inter-pixel correlation among data samples the LSU explores intra-pixel correlation to characterize spectral properties for classification. As a result, a major strength of the LSU is to perform mixed pixel classification by estimating abundance fraction of each tissue substance present in a pixel to provide the likelihood of each tissue substance to be classified in one particular class. This task cannot be accomplished by classical spatial domain-based classification techniques which perform pure-pixel classification by confusion matrices that involve hard decisions instead of soft decisions made by mixed pixel classification. Since the LSU is an intra-pixel-based technique and does not take advantage of inter-pixel correlation as the traditional image processing techniques do. In order for the LSU to be able to do so, texture analysis is included as a post-processing technique that can be used in conjunction with LSU to perform both spectral/spatial (i.e., intra-pixel and inter-pixel) analysis. Specifically, the gray level co-occurrence matrix (GLCM) is used as a base to generate various texture features to be used as training samples for a follow-up back propagation-based neural network for classification. To demonstrate the performance of our texture-based LSU approach, experiments are conducted for performance analysis and evaluation.
URI: http://hdl.handle.net/11455/8577
其他識別: U0005-1908200912394900
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1908200912394900
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



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