Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/7198
標題: 多重解析正交次空間投影技術於乾癬影像分割之研究
Applications of Multiresolution-Based Orthogonal Subspace Techniques to the Segmentation of Psoriasis Vulgaris Images
作者: 李國和
Lee, Gwo-Her
關鍵字: Fuzzy texture spectrum;模糊紋理光譜;image segmentation;signature subspace classifier;影像分割;信號次空間分類器
出版社: 電機工程學系所
引用: [1] T. P. Habif, Clinical Dermatology, The C.V. Mosby Company, 2nd ed., 1990. [2] J. S. Taur, C. W. Tao, C. C. Chen, and C. W. Yang, “Segmentation of psoriasis vulgaris images using orthogonal subspace techniques,” In Proceedings, The 7th Conference on Artificial Intelligence and Applications, pp. 667-671, Nov. 2002. [3] J. S. Taur,“Neural-fuzzy approach to the segmentation of psoriasis images,” Journal of VLSI Signal Processing, vol. 35, no.1, pp. 19-27, Feb. 2003. [4] J. S. Taur, G. H. Lee, C. W. Ta, C. C. Chen, and C. W. Yang, “Segmentation of psoriasis vulgaris images using multiresolution-based orthogonal subspace techniques,” IEEE Trans. On System, Man and Cybern. Part-B, vol. 36, no. 2, pp. 390-402, Apr. 2006. [5] R.M. Haralick and L.G. Shapiro, “Image segmentation techniques,” Comput. Vis. Graph. Im. Proc., vol. 29, pp.100-132, 1985. [6] N.R. Pal and S.K. Pal, “A review on image segmentation techniques,” Patt. Rec., vol. 26, no. 9, pp.1277-1294, 1993. [7] J.C. Bezdek, L.O. Hall, and L.P. Clarke, “Review of MR image segmentation techniques using pattern recognition,” Med. Phys., vol. 20, no. 4, pp. 1033-1048, Jul. 1993. [8] A.P. Zijdenbos and B.M. Dawant, “Brain segmentation and white matter lesion detection in MR images,” Critical Reviews in Biomedical Engineering, vol. 22, no. 5-6, pp. 401-465, 1994. [9] E.L. Chaney and S.M. Pizer, “Defining anatomical structures from medical images,” Seminars in Radiation Oncology, vol. 2, no.4, pp. 215-225, Oct. 1992. [10] D. L. Pham, C. Y. Xu, and J. L. Prince, “A survey of current methods in medical image segmentation,” Annu. Rev. Biomed. Eng., vol. 2, pp. 315-337, 2000. [11] J. Fan, D.K.Y. Yau, A.K. Elmagarmid, and W.G. Aref, “Automatic image segmentation by integrating color-edge extraction and seeded region growing,” IEEE Trans. Image Processing, vol. 10, no. 10, pp. 1454-1466, Oct. 2001. [12] Y. W. Lim and S. U. Lee, “On the color image segmentation algorithm based on the thresholding and the fuzzy C-means techniques,” Pattern Recognit., vol. 23, no. 9, pp. 935- 952, 1990. [13] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,” in Pros. 1st ICCV, pp. 259-267, 1987. [14] P. L. Palmer, H. Dabis, and J. Kittler, “A performance measure for boundary detection algorithms,” Comput. Vis. Image Understand., vol. 63, pp. 476-494, 1996. [15] R. Adams and L. Bischof, “Seeded region growing,” IEEE Trans. Pattern Anal. Machine Intell., vol. 16, pp. 641-647, 1994. [16] R. M. Haralick and L. G. Shapiro, “Survey: Image segmentation techniques,” Comput. Vis. Graph. Image Process., vol. 29, pp. 100-132, 1985. [17] Y. -L. Chang and X. Li, “Adaptive image region-growing,” IEEE Trans. Image Processing, vol. 3, pp. 868-872, 1994. [18] S. A. Hojjatoleslami and I. Kitter, “Region growing: A new approach,” IEEE Trans. Image Processing, vol. 7, pp. 1079-1084, 1998. [19] T. Pavlidis and Y. T. Liow, “Integrating region growing and edge detection,” IEEE Trans. Pattern Anal. Machine Intell., vol. 12, pp. 225-233, 1990. [20] J. Haddon and J. Boyce, “Image segmentation by unifying region and boundary information,” IEEE Trans. Pattern Anal. Machine Intell., vol. 12, pp. 929-948, 1990. [21] C. Chu and J. K. Aggarwal, “The integration of image segmentation maps using region and edge information,” IEEE Trans. Pattern Anal. Machine Intell., vol. 15, pp. 1241-1252, 1993. [22] G.B. Coleman and H.C. Andrews, “Image segmentation by clustering,” Proc. IEEE, vol. 5, pp. 773-785, 1979. [23] J.C. Dunn, “A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters,” Journal of Cybernetics, vol. 3, pp. 32-57, 1973. [24] J. Pauwels and G. Frederix, “Finding salient regions in images,” Computer Vision and Image Understanding, vol. 75, pp. 73-85, 1999. [25] L.O. Hall, A.M. Bensaid, L.P. Clarke, R.P. Velthuizen, M.S. Silbiger, and J.C. Bezdek, “A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain,” IEEE T. Neural Networks, vol. 3, pp. 672-682, 1992. [26] E. Gelenbe, Y. Feng, and K.R.R. Krishnan, “Neural network methods for volumetric magnetic resonance imaging of the human brain,” Proc. IEEE, vol. 84, pp.1488-1496, 1996. [27] W.E. Reddick, J.O. Glass, E.N. Cook, T.D. Elkin, and R.J. Deaton, “Automated segmentation and classification of multispectral magnetic resonance images of brain using artificial neural networks,” IEEE T. Med. Imag., vol. 16, pp. 911-918, 1997. [28] J.C. Harsanyi and C.I. Chang, “Hyperspectral image classification and dimensionality reduction: An orthogonal subspace projection approach,” IEEE Trans. Geosci. Remote Sensing, vol. 32, no. 4, pp. 779-784, Jul. 1994. [29] C. M. Wang, S. C. Yang, P. C. Chung, C. I. Chang, C. S. Lo, C. C. Chen, C. W. Yang, and C. H. Wen, “Orthogonal subspace projection-based approaches to classification of MR image sequences,” Computerized Medical Imaging and Graphics, vol. 25, no. 6, pp. 465-476, Dec. 2001. [30] T. M. Tu, C. H. Chen, and C. I. Chang, “A posteriori least squares orthogonal subspace projection approach to desired signature extraction and detection,” IEEE Trans. Geosci. Remote Sensing, vol. 35, no. 1, pp. 127-139, Jan. 1997. [31] C. I. Chang, X. L. Zhao, Mark L. G. Althouse, and J. J. Pan, “Least squares subspace projection to mixed pixel classification for hyperspectral images,” IEEE Trans. Geosci. Remote Sensing, vol. 36, no, 3, pp. 898-912, May 1998. [32] L. L. Scharf and B. Friedlander, “Matched subspace detectors,” IEEE Trans. Signal Process., vol. 42, no. 8, pp. 2146-2157, Aug. 1994. [33] H. Kwon and N. M. Nasrabadi, “Kernel matched signal detectors for hyperspectral target detection,” 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 3, pp. 20-26, Jun. 2005. [34] K.-R. Müller, S. Mika, G. Rätsch, K. Tsuda, and B. Schölkopf, “An introduction to kernel-based learning algorithm,” IEEE Trans. Neural Networks, vol. 12, no. 2, pp. 181-201, Mar. 2001. [35] C. Cortes and V. N. Vapnik, “Support vector networks,” Machine Learning, vol. 20, pp. 273-297, 1995. [36] V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995. [37] C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, 1998. [38] B. Schölkopf, C. Burges, and A. Smola, Advances in Kernel Methods: Support Vector Learning. Cambridge, MA: MIT Press, 1999. [39] S. Mika, G. Rätsch, J. Weston, B. Schölkopf, and K.-R. Müller, “Fisher discriminant analysis with kernels,” in Neural Networks for Signal Processing IX, Y.-H. Hu, J. Larsen, E. Wilson, and S. Douglas, Eds. Piscataway, NJ: IEEE, 1999, pp. 41-48. [40] S. Mika, G. Rätsch, J. Weston, B. Schölkopf, A. J. Smola, and K.-R. Müller, “Invariant feature extraction and classification in kernel spaces,” in Advances in Neural Information Processing Systems 12, S. A. Solla, T. K. Leen, and K.-R. Müller, Eds. Cambridge, MA: MIT Press, 2000, pp. 526-532. [41] V. Roth and V. Steinhage, “Nonlinear discriminant analysis using kernel functions,” in Advances in Neural Information Processing Systems 12, S. A. Solla, T. K. Leen, and K.-R. Müller, Eds. Cambridge, MA: MIT Press, 2000, pp. 568-574. [42] G. Baudat and F. Anouar, “Generalized discriminant analysis using a kernel approach,” Neural Comput., vol. 12, no. 10, pp. 2385-2404, 2000. [43] B. Schölkopf, A.J. Smola, and K.-R. Müller, “Kernel principal component analysis,” Neural Computation, No. 10, pp. 1299-1319, 1999. [44] B. Schölkopf, A. J. Smola, and K.-R. Müller, “Nonlinear component analysis as a kernel eigenvalue problem,” Neural Comput., vol. 10, pp. 1299-1319, 1998. [45] S. Mika, B. Schölkopf, A. J. Smola, K.-R. Müller, M. Scholz, and G. Rätsch, “Kernel PCA and de-noising in feature spaces,” in Advances in Neural Information Processing Systems 11, M. S. Kearns, S. A. Solla, and D. A. Cohn, Eds. Cambridge, MA: MIT Press, 1999, pp. 536-542. [46] B. Schölkopf, S. Mika, C. J. C. Burges, P. Knirsch, K.-R. Müller, G. Rätsch, and A. J. Smola, “Input space versus feature space in kernelbased methods,” IEEE Trans. Neural Networks, vol. 10, pp. 1000-1017, Sept. 1999. [47] S. Mukherjee, E. Osuna, and F. Girosi, “Nonlinear prediction of chaotic time series using a support vector machine,” in Neural Networks for Signal Processing VII—Proc. 1997 IEEE Workshop, J. Principe, L. Gile, N. Morgan, and E.Wilson, Eds. New York: IEEE, 1997, pp. 511-520. [48] D. Mattera and S. Haykin, “Support vector machines for dynamic reconstruction of a chaotic system,” in Advances in Kernel Methods—Support Vector Learning, B. Schölkopf, C. J. C. Burges, and A. J. Smola, Eds. Cambridge, MA: MIT Press, 1999, pp. 211-242. [49] V. Blanz, B. Schölkopf, H. Bülthoff, C. J. C. Burges,V. N. Vapnik, and T. Vetter, “Comparison of view-based object recognition algorithms using realistic 3-D models,” in Artificial Neural Networks—ICANN'96. ser. Springer Lecture Notes in Computer Science, C. von der Malsburg, W. von Seelen, J. C. Vorbrüggen, and B. Sendhoff, Eds. Berlin, Germany: Springer-Verlag, 1996, vol. 1112, pp. 251-256. [50] D. Roobaert and M. M. Van Hulle, “View-based 3d object recognition with support vector machines,” in Proc. IEEE Neural Networks Signal Processing Workshop 1999, 1999. [51] T. Joachims, “Text categorization with support vector machines: Learning with many relevant features,” in Proc. Europ. Conf. Machine Learning. Berlin, Germany: Springer-Verlag, 1998, pp. 137-142. [52] H. Drucker, D.Wu, and V. N. Vapnik, “Support vector machines for span categorization,” IEEE Trans. Neural Networks, vol. 10, pp. 1048-1054, 1999. [53] M. P. S. Brown, W. N. Grundy, D. Lin, N. Cristianini, C. Sugnet, T. S. Furey, M. Ares, and D. Haussler, “Knowledge-based analysis of microarray gene expression data using support vector machines,” Proc. Nat. Academy Sci., vol. 97, no. 1, pp. 262-267, 2000. [54] T. Furey, N. Cristianini, N. Duffy, D. Bednarski, M. Schummer, and D. Haussler, “Support vector machine classification and validation of cancer tissue samples using microarray expression data,” Bioinformatics, vol. 16, pp. 906-914, 2000. [55] H. Kwon and N. M. Nasrabadi, “Kernel orthogonal subspace projection for hyperspectral signal classification,” IEEE Trans. Geosci. Remote Sensing, vol. 43, no. 12, pp. 2952-2962, Dec. 2005. [56] H. Kwon and N. M. Nasrabadi, “Kernel matched subspace detectors for hyperspectral target detection,” IEEE Trans. Pattern Anal. Machine Intell., vol. 28, no. 2, pp. 178-194, Feb. 2006. [57] B. Schölkopf and A. Smola. Learning with Kernels, MIT Press, Cambridge, MA, 2002 [58] J.S. Taur and C.W. Tao, “Texture classification using a fuzzy texture spectrum and neural networks,” Journal of Electronic Imaging, vol. 7, no. 1, pp. 29-35, Jan. 1998. [59] W. K. Pratt, Digital Image Processing, Wiley, New York, 1991. [60] L. Shafarenko, M. Petrou, and J. Kittler, “Histogram-based segmentation in a perceptually uniform color space,” Pattern Recognition, vol. 33, no. 4, pp. 671-684, 2000. [61] G. Paschos and M. Petrou, “Histogram ratio features for color texture classification,” Pattern Recognition Letters, vol. 24, pp. 309-314, 2003. [62] J. Han and K.-K. Ma, “Fuzzy color histogram and its use in color image retrieval,” IEEE Trans. Image Processing, vol. 11, no. 8, pp. 944-952, Aug. 2002. [63] K.I. Diamantaras and S.Y. Kung. Principal Component Neural Network, Wiley, New York, 1996. [64] I. T. Jolliffe. Principal Component Analysis, Springer-Verlag, New York, 1986 [65] B. Schölkopf, A. Smola, and K.-R. Müller. “Nonlinear component analysis as a kernel eigenvalue problem,” Neural Computation, 10:1299-1319, 1998. [66] S.Y. Kung and J.S. Taur, “Decision-based neural networks with signal/image classification applications,” IEEE Trans. Neural Networks, vol. 6, no. 1, pp. 170-181, Jan. 1995. [67] S. Abe and R. Thawonmas, “A fuzzy classifier with ellipsoidal regions,” IEEE Trans. Fuzzy System, vol. 5, no. 3, Aug. 1997. [68] D. Driankov and H. Hellendoorn and M. Reinfrank, An Introduction to Fuzzy Control, Springer-Verlag, 1993. [69] D. Nauck, U. Nauck, and R. Kruse, “Generating classification rules with the neuro-fuzzy system NEFCLASS,” Proc. Biennial Conf. of the North American Fuzzy Information Processing Society, Berkeley, 1996. [70] S. Romdhani, S. Gong, and A. Psarrou. “A multi-view nonlinear active shape model using kernel PCA”. In T. Pridmore and D. Elliman, editors, Proceedings of the 10th British Machine Vision Conference (BMVC99), pp. 483-492, BMVA Press, 1999. [71] J. T. Kwok, B. Mak, and S. Ho. “Eigenvoice speaker adaptation via composite kernel principal component analysis,” in Advances in Neural Information Processing Systems 16, S. Thrun, L. Saul, and B. Schölkopf, Eds. MIT Press, Cambridge, MA, 2004. [72] A. J. Smola and B. Schölkopf, “Sparse greedy matrix approximation for machine learning,” in Proc. ICML'00, P. Langley, Ed. San Mateo: Morgan Kaufmann, 2000, pp. 911-918. [73] M. Tipping, “Sparse kernel principal component analysis,” in Advances in Neural Information Processing Systems 13. Cambridge, MA: MIT Press, 2001, to be published. [74] A. J. Smola, O. L. Mangasarian, and B. Schölkopf, “Sparse kernel feature analysis,” University of Wisconsin, Data Mining Institute, Madison, Tech. Rep. 99-04, 1999. [75] K.I. Kim, M.O. Franz, and B. Schölkopf, “Iterative kernel principal component analysis for image modeling,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 9, pp. 1351-1366, Sep. 2005. [76] J. C. Principe, “Information-Theoretic Learning,” in Unsupervised Adaptive Filtering, edit by S. Haykin, John Wiley and Sons, New York, 2000. [77] J.A.K. Suykens and J. Vandewalle, “Least squares support vector machine classifiers”, Neural Processing Letters, vol. 9, no. 3, pp. 293-300, 1999. [78] J.A.K. Suykens, T. Van Gestel, J. De Brabanter, B. De Moor, and J. Vandewalle, Least Squares Support Vector Machines, World Scientific, Singapore, 2002. [79] T. Van Gestel, J.A.K. Suykens, G. Lanckriet, A. Lambrechts, B. De Moor, and J. Vandewalle, “Bayesian framework for least squares support vector machine classifiers, gaussian processes and kernel fisher discriminant analysis,” Neural Computation, 15(5), 1115-1148, 2002. [80] C.K.I. Williams and M. Seeger, “Using the Nyström method to speed up kernel machines,” Advances in neural information processing systems, 13, 682-688, MIT Press, 2001. [81] T. Van Gestel, J. Suykens, B. Baesens, S. Viaene, J. Vanthienen, G. Dedene, B. De Moor, and J. Vandewalle, “Benchmarking least squares support vector machine classifiers,” Machine Learning, in press, 2001. [82] K. Pelckmans, J.A.K. Suykens, T. Van Gestel, J. De Brabanter, L. Lukas, B. Hamers, B. De Moor, and J. Vandewalle, “LS-SVMlab toolbox user's guide version 1.5,” K. U. Leuven, Technical Report ESAT-SCD-SISTA 02-145, Feb. 2003.
摘要: 
在本論文中,我們提出一種應用多重解析正交次空間投影技術的自動化方法於尋常性乾癬影像分割。由於尋常性乾癬是一種慢性疾病,因此,追蹤病人的病情並選擇適當的療法是很重要的。我們設計的影像分割系統可自動將乾癬影像分割成正常皮膚區域及乾癬區域,以估計某一病人在不同時間乾癬的面積,並提供一定量的治療進展量測。這些資訊可提供客觀的指標給醫生來選擇對某一病人最適當的治療方法,並可避免在評估過程中受到個人因素的影響。
此系統所需的主要的技術包含特徵抽取與影像分類(分割)的方法,我們首先採用模糊紋理光譜以及二維模糊色彩長條圖作為特徵向量來找出影像中的均勻區域,並用這些區域所獲得乾癬與正常皮膚的特徵向量來計算信號矩陣(signature matrix),以使得正交次空間技術能獲得較精確的分類結果。在本論文中,我採用信號次空間分類器(signature subspace classifier, SSC)、匹配次空間偵測器(matched subspace detector, MSD)、核化信號次空間分類器(kernel signature subspace classifier, KSSC) 及核化匹配次空間偵測器(kernel matched subspace detector, KMSD)四種多光譜影像處理技術來分割尋常性乾癬影像。
信號次空間分類器(SSC)是由估測非抑制最小平方的過程所推導求得,它不是先驗型(a priori model.)分類器,其信號可直接由觀測影像獲得。信號次空間分類器(SSC)首先將一觀測像素分解至信號次空間與雜訊空間,以大幅降低雜訊的影響。再使用非期望信號 (undesired signature) 消除器伴隨匹配濾波器來粹取出期望信號。匹配次空間偵測器(MSD)為另一廣泛被應用至超光譜影像偵測的技術,它可被描述成二位元測試問題的訊號偵測模型。
由於核化分類器可探測被傳統分類器忽略的非線性信號相關性,因此,藉由核化理論,我們將信號次空間分類器(SSC)擴展至對應的核化信號次空間分類器(KSSC)。採用核化技術,可避免在高維度的特徵空間中計算特徵向量的內積,並由核函式(kernel function)來取代。所求得的核化信號次空間分類器(KSSC)等效於在原始空間中的非線性信號次空間分類器(SSC),為進一步說明核化(kernel-based)分類器的優點,我們也在論文中討論核化匹配次空間偵測器(KMSD),它是一非線性版本的匹配次空間偵測器(MSD)。
在分類過程中,我們發展了多重解析SSC、MSD、KSSC及KMSD (MSSC、MMSD、MKSSC及MKMSD )以降低計算量。在實驗中,我們採用一相似性函式(similarity function)來執行量化評估,且與著名的LS-SVM方法比較。結果說明本論文所提的核化(kernel-based)技術能有效分割尋常性乾癬影像。

In this dissertation, an automatic method is proposed for the segmentation of psoriasis images using multiresolution-based orthogonal subspace techniques. Since psoriasis is a chronic disease, it is important to track the condition of the patient to select a proper treatment. In our design, the psoriasis images are segmented into normal regions and abnormal regions automatically. The areas of each kind of regions of a patient at different moments can then be estimated. The information can be used to give a quantitative measure of the treatment progress. The provided information can avoid the variation of the human factor in the evaluation procedure and offer an objective index for the doctor to select the most suitable treatment for the patient.
The essential techniques consist of feature extraction and image segmentation (classification) methods. In this approach, the fuzzy texture spectrum and the two-dimensional fuzzy color histogram in the hue-saturation space are first adopted as the feature vector to locate homogeneous regions in the image. Then these regions are used to compute the signature matrices for the orthogonal subspace techniques to obtain a more accurate segmentation. In this dissertation, we investigate the applications of four multispectral image processing techniques to segment psoriasis images. They are the signature subspace classifier (SSC), matched subspace detector (MSD), kernel signature subspace classifier (KSSC), and kernel matched subspace detector (KMSD).
The SSC is derived on the basis of an unconstrained least square estimation such that the signature abundances can be obtained from the observed data rather than assumed to be a priori model. It first decomposes an observed pixel into a signature space and a noise space so that noise effects can be greatly reduced, and then utilizes an undesired signature eliminator followed by a matched filter to extract the desired signature. The MSD is another approach which is widely used in hyperspectral image detection. It is formulated on the basis of a signal detection model that can be described by a binary hypothesis testing problem.
Since the kernel-based classifiers can exploit the nonlinear correlations of signatures that are ignored by the conventional classifiers, the SSC is extended to its corresponding kernel version, the kernel SSC (KSSC), by applying the idea of kernel-based learning theory. With the kernel-based technique, the explicit computation in high dimensional feature space can be avoided by replacing it with a kernel function. The obtained KSSC is equivalent to a nonlinear SSC in the input space. To further illustrate the advantage of kernel-based classifiers, the kernel MSD (KMSD), a nonlinear version of the MSD, is also discussed.
To reduce the computational requirement in segmentation, the multiresolution-based SSC, MSD, KSSC, and KMSD (MSSC, MMSD, MKSSC, and MKMSD) are developed. In the experiments, the proposed techniques is quantitatively evaluated by using a similarity function and compared with the well-known LS-SVM method. The results show that the proposed kernel-based techniques can effectively segment psoriasis images.
URI: http://hdl.handle.net/11455/7198
其他識別: U0005-0107200723220200
Appears in Collections:電機工程學系所

Show full item record
 

Google ScholarTM

Check


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