臺灣博碩士論文加值系統

色析法是一種將物體分離出來的一種技術，它廣泛的應用在分析蛋白質的研究上。一種新的分析方法用來量測色析法顆粒內部擴散情形，它提供了顆粒內部的擴散係數。在實驗過程中，色析法顆粒會隨著時間移動而改變了它顆粒內部的影像強度。要手動的移動每張影像到參考的影像空間是沒有效率而且不夠精準。因此藉由影像套合的技術，我們可以自動地將影像序列對齊好。在本篇論文中，我們比較了兩種影像套合的方法來對齊在視訊流中的最大的色析法顆粒。我們也利用了區域填補的方法來增加套合的準確度。
第一種套合方法是以強度為基礎的，它只用到2張影像的強度的資訊來對齊。它比較了轉換過後的移動影像跟固定影像的強度差。因此選擇一個適當的強度相似標準是一個重要的步驟。如果利用平方差總和的估測，對影像亮度的變化效果較差。我們選擇正規化相似標準來解決這樣的問題。
第二種套合方法是以影像上的特徵為基礎。影像上的特徵提供了空間上的位置。利用這些位置來找到相對應特徵點的關係來算出它們之間的轉換方程式。我們在影像上擷取邊的特徵來當作套合的特徵。對於影像是空心的話，我們利用區域填補的方法來填滿它進而增加套合的精準度。我們也修改了廣義的雙靴反覆最近點的演算法當作我們的以特徵套合的方法。修改過的部份包括了初始化，特徵擷取跟套合引擎。
我們總共套合了926張的影像對。在比較這兩種套合方法後，以特徵為基礎的套合方法提供了比較小的對齊誤差。而且特徵為基礎的套合方法也提供了滿意的結果。
在未來的研究方向，我們將利用結合特徵擷取跟一些影像形態學處理技巧來達到追蹤在視訊流中色析法影像的最大顆粒。

Chromatographic technique is one kind of chemical analysis for a sample-filtering application. It is widely used in protein research. A new approach for measure of intraparticle protein diffusion, it provides the intraparticle diffusion coefficients. In the experiment, the chromatographic particles not only move with time change but also alter its intensity. If it is not consistent with reference space of the biggest particle, researchers would get errors during the diffusion process. Manually shifting the particle for each frame is neither robust nor efficient. Therefore, we utilize the image registration technique to align the image sequence automatically. In this thesis, we compare two kinds of registration method applying to align the biggest chromatographic particles in a video stream. We also utilize the region filling technique to improve the feature-based registration accuracy.
The first registration method is intensity-based. It uses the image information to align images. This method compares the intensity difference of transformed moving image and fixed image. Therefore, selecting a suitable intensity measure metric is an essential step. If we use the sum of squared errors (SSD) measure, it is sensitive to illumination change. We select a Normalized Correlation metric to solve this problem.
The second registration method is feature-based. Image features provide the location of its space. This method uses the relationship of feature’s location to find the correspond point. It uses a set of correspondences of salient features to establish the transformation. We extract points on the edges as features for registration. If the image is hollow, we fill the region to improve the registration accuracy. We modify the GDBICP (Generalized Dual-Bootstrap Iterative Closest Point) algorithm as our proposed feature-based registration method. We modify the part of GDBICP algorithm including initialization, feature extraction and the registration engine.
We totally align 926 image pairs. After we compare these two kinds of registration method, the feature-based registration method provides the less alignment error than intensity-based method. The feature-based method also provides satisfactory results for all cases.
In the future, we will utilize feature extraction and some morphological technique to track the biggest chromatographic particles in a video stream.

中文摘要 ……………………………………………………………………………...i
ABSTRACT iii
List of Figures vii
List of Tables x
Chapter 1
Introduction 1
1.1 Background 1
1.2 Problem definition 5
1.3 Study of related work 6
1.4 Intensity-based and feature-based registration 7
1.5 Summary of our approach 9
Chapter 2
Intensity-Based Image Registration 11
2.1 Mathematical Background 12
2.2 ITK framework 17
Chapter 3
Feature-Based Registration 19
3.1 Mathematical Background 20
3.2 RGRL framework 22
Chapter 4
Proposed Image Registration System 28
4.1 Feature extraction 31
4.2 Finding the reference frame 32
4.3 Judgment of region filling 33
4.4 Region Filling 36
4.5 Transform images to reference space 45
Chapter 5
Experiment and Discussion 47
5.1 Experimental Results 47
5.2 Discussion 56
Chapter 6
Conclusions and Future Work 61
References 64

[1] N. Sehat, M. P. Yurawecz, J. A. Roach, M. M. Mossoba, J. K. Kramer, and Y. Ku, "Silver-ion high-performance liquid chromatographic separation and identification of conjugated linoleic acid isomers.," Lipids, vol. 33, no. 2, pp. 217-21, Feb.1998.
[2] S. Magnus, L. Eric, and J. Hubbuch, "Direct Quantification of Intraparticle Protein Diffusion in Chromatographic Media," J. Phys. Chem, vol. 110, pp. 1429-1436, 2005.
[3] N. Bonnet, "Some trends in microscope image processing," Micron, vol. 35, pp. 635-653, 2004.
[4] M. Stewart, "Introduction to the computer image processing of electron micrographs of two-dimensionally ordered biological structures," J. Elec. Microsc. Tech. 9, pp. 301-324, 1998.
[5] P. Geladi, "Some special topics in multivariate image analysis," Chemom. Intell. Lab. Syst. 14, pp. 375-390, 1992.
[6] K. Rodenacher, M. Aubele, P. Hutzler, and U. Adiga, "Groping for quantitative digital 3D image analysis: an approach to quantitative fluorescence in situ hybridization in thick tissue sections of prostate carcinoma," Anal. Cell. Pathol. 15, pp. 19-29, 1997.
[7] P. B. Hojte and X. Wang, "Registering electrophoresis images for bioinformatics study of protein," In Proc. ICME, vol. 3, pp. 465-468, 2003.
[8] M. Rogers, J. Graham, and R. P. Tonge, "2-D Electrophoresis Gel Registration Using Feature Matching," In Proceedings of IEEE International Symposium on Biomedical Imaging, pp. 1436-1439, 2004.
[9] C. O. S. Sorzano, P. Thevenaz, and M. Unser, "Elastic Registration of Biological Images Using Vector-Spline Regularization," IEEE Trans. Bio. Imaging, vol. 52, no. 4, pp. 652-663, 2005.
[10] M. Tichem and M. S. Cohen, "Submm registration of fiducial marks using machine vision," IEEE Trans. on PAMI, vol. 16, no. 8, pp. 791-794, 1994.
[11] E. Meijering, I. Smal, and G. Danuser, "Tracking in Molecular Bioimaging," IEEE Signal Processing Magazine, vol. 23, no. 3, pp. 46-53, 2006.
[12] C. Zimmer, B. Zhang, A. Defour, A. Thebaud, S. Berlemont, V. Meas-Yedid, and J.-C. O. Marin, "On the digital trail of mobile cells," IEEE Signal Processing Mag, vol. 23, no. 3, pp. 54-62, 2006.
[13] Szymon Rusinkiewicz and Marc Levoy, "Efficient variants of the ICP algorithm," In Proceedingsof the Third International Conference on 3-D Digital Imaging and Modeling, pp. 224-231, 2001.
[14] B. Zitova and J. Flusser, "Image registration methods: a survey," Image and Vision Computing, vol. 21, pp. 977-1000, 2003.
[15] D. L. Hill, P. G. Batchelor, M. Holden, and D. J. Hawkes, "Medical image registration," Phys. Med. Biol., vol. 46, no. 3, pp. R1-45, Mar.2001.
[16] J. B. A. Maintz and M. A. Viergever, "A survey of medical image registration," Medical Image Analysis, pp. 1-36, 1998.
[17] M. Pilu, "On using raw MPEG motion vectors to determine global camera motion," Pilu Digital Media Department HP Laboratories Bristol, pp. HPL-97-102, Aug.1997.
[18] J. I. Igbokwe, "Geometrical processing of multisensoral multi-temporal satellite images for change detection studies," International Journal ofRemote Sensing, vol. 20, no. 6, pp. 1141-1148, 1999.
[19] J. K. Seo, G. Sharp, and S. W. Lee, "Range Data Registration Using Photometric Features," In Proc. CVPR, vol. 2, pp. 1140-1145, 2006.
[20] Y. Zhang, J. Paik, A. Koschan, and M. Abidi, "3-D Object Representation from Multi-view Range Data Applying Deformable Superquadrics," In. Conf. Pattern Recognition, vol. III, pp. 273-276, 2002.
[21] L. G. Brown, "A survey of image registration techniques," ACM Computing Surveys, vol. 24, no. 4, pp. 325-376, Dec.1992.
[22] H. Chen, P. K. Varshney, and M. K. Arora, "A Study of Joint Histogram Estimation Methods to Register Multi-Sensor Remote Sensing Images Using Mutual Information," in proceedings of International Geoscience & Remote Sensing Sysposium, pp. 4035-4037, 2003.
[23] J. P. W. Pluim, J. B. A. Maintz, and M. A. Viergever, "Mutual-information-based registration of medical images: a survey," IEEE Trans. Med. Imaging, vol. 22, no. 8, pp. 986-1004, 2003.
[24] F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, "Multimodality image registration by maximization of mutual information," IEEE Trans. Med. Imaging, vol. 16, no. 2, pp. 187-198, 1997.
[25] A. Bartoli and A. Zisserman, "Direct Estimation of Non-Rigid Registrations," In Proc. BMVC, vol. II, pp. 899-908, Sept.2004.
[26] H. J. Johnson and G. E. Christensen, "Consistent Landmark and Intensity-Based Image Registration," IEEE Trans. Med. Imaging, vol. 21, no. 5, pp. 450-461, May2002.
[27] J. Feldmar, G. Malandain, J. Declerck, and N. Ayache, "Extension of the ICP Algorithm to Non-Rigid Intensity-Based Registration of 3D Volumes," In Proc. MMBIA, p. 84, 1996.
[28] C. Shekhar, V. Govindu, and R. Chellappa, "Multisensor image registration by feature consensus," Tech. Rep. , University of Maryland, Computer Vision Laboratory, Center for Automation Research, Aug.1996.
[29] C. Stewart, C.-L. Tsai, and B. Roysam, "The dual bootstrap iterative closest point algorithm with application to retinal image registration," IEEE Trans. Med. Imaging, vol. 22, no. 11, pp. 1379-1394, Nov.2003.
[30] M. Brown and D. G. Lowe, "Invariant features from interest point groups," In Proceedings of British Machine Vision Conference, pp. 656-665, 2002.
[31] A. C. Shastry and R. A. Schowengerdt, "Airborne video registration and traffic-flow parameter estimation," IEEE Trans. Intell. Trans. Sys, vol. 6, no. 4, pp. 391-405, Dec.2005.
[32] S. K. Sun, Z. Chen, and T. L. Chia, "Image registration using only two Gabor feature points with their principal orientations for computational complexity reduction," In Proc. 2002 Conference on Computer Vision, Graphics, and Image Processing, pp. 25-27, Aug.2002.
[33] B. S. e. al. Manjunath, "A new approach to image feature detection with applications," Pattern Recognition, vol. 29, no. 4, pp. 627-640, 1996.
[34] K. Mikolajczyk and C. Schmid, "Scale and affine invariant interest point detectors," IJCV, vol. 60, pp. 63-86, 2004.
[35] M. Brown, R. Szeliski, and S. Winder, "Multi-Image Matching using Multi-Scale Oriented Patches," In Proc. CVPR., pp. 510-517, 2005.
[36] P. Besl and N. McKay, "A method for registration of 3-d shapes," IEEE Trans. on PAMI, vol. 14, no. 2, pp. 239-256, 1992.
[37] C. Stewart, C.-L. Tsai, and B. Roysam, "The dual bootstrap iterative closest point algorithm with application to retinal image registration," IEEE Trans. Med. Imaging, vol. 22, no. 11, pp. 1379-1394, Nov.2003.
[38] C. V. Stewart and B. Roysam, "RIVERS: Retinal Image Vessel Extraction and Registration System," http://sgilinux4. aisl. rpi. edu/retina/, 2006.
[39] G. Yang, C. V. Stewart, M. Sofka, and C.-L. Tsai, "Alignment of challenging image pairs: Refinement and region growing starting from a single keypoint correspondence," IEEE T. Pattern Anal, 2005.
[40] C. V. Stewart, Y.-L. Lee, and C.-L. Tsai, "An uncertainty-driven hybrid of intensity-based and feature-based registration with application to retinal and lung CT images," In Proc. 7th MICCAI, Saint-Malo, France, 2004.
[41] W. Grimson, T. Lozano-Perez, W. Wells, G. Ettinger, and, and S. White, "An automatic registration method for frameless stereotaxy, image, guided surgery and enhanced reality visualization," In Proc. CVPR, pp. 430-436, 1994.
[42] C. V. Stewart, "Robust parameter estimation in computer vision.," SIAM Reviews, vol. 41, no. 3, pp. 513-537, 1999.
[43] P. Anandan, "A computational framework and an algorithm for the measurement of visual motion," IJCV, vol. 2, no. 3, pp. 283-310, 1989.
[44] Yao Jianchao, "Image Registration Based on Both Feature and Intensity Matching," In Proc. ICASSP, vol. 3, pp. 1693-1696, 2001.
[45] L. Zollei, E. Grimson, A. Norbash, and W. ells, "2D-3D rigid registration of X-ray fluoroscopy and CT images using mutual information and sparsely sampled histogram estimators," In Proc. CVPR, vol. 2, no. 2, pp. 696-703, 2001.
[46] W. Wein, B. Roper, and N. Navab, "2D/3D Registration Based on Volume Gradients," SPIE Medical Imaging, pp. 12-17, Feb.2005.
[47] J. e. al. West, "Comparison and evaluation of retrospective intermodality brain image registration techniques," Journal of Computer Assisted Tomography, vol. 21, pp. 554-566, 1997.
[48] A. Roche, X. Pennec, G. Malandain, and N. Ayache, "Rigid Registration of 3D Ultrasound with MR Images: a New Approach Combining Intensity and Gradient Information," IEEE Trans. Med. Imaging, vol. 20, no. 10, pp. 1038-1049, Oct.2001.
[49] R. Z. Shekhar, V, "Mutual information-based rigid and nonrigid registration of ultrasound volumes," IEEE Trans. Med. Imaging, vol. 21, no. 1, pp. 9-22, Jan.2002.
[50] A. Yezzi, L. Zollei, and T. Kapur, "A Variational Framework for Joint Segmentation and Registration," IEEE Trans. Bio. Imaging Anal, pp. 44-51, 2001.
[51] H. Livyatan, Z. Yaniv, and L. Joskowicz, "Gradient-Based 2-D/3-D Rigid Registration of Fluoroscopic X-Ray to CT," IEEE Trans. Med. Imaging, vol. 22, no. 11, pp. 1395-1406, Nov.2003.
[52] G. P. Penney, J. Weese, J. A. J. A. Little, P. Desmedt, D. L. O. Hill, and D. J. Hawkes, "A comparison of similarity measures for use in 2-D-3-D medical image registration," IEEE Trans. Med. Imaging, vol. 17, no. 4, pp. 586-595, 1998.
[53] R. P. Woods, J. C. Mazziotta, and S. R. Cherry, "MRI-PET Registration with Automated Algorithm," Journal ofComputer Assisted Tomography, vol. 17, no. 4, pp. 536-546, 1993.
[54] T. Lehmann, C. Gonner, and K. Spitzer, "Survey: interpolation method in medical imaging," IEEE Trans. Med. Imaging, vol. 18, no. 11, pp. 1049-1075, 1999.
[55] W. CRUM, T. HARTKENS, and D. HILL, "Non-rigid image registration: theory and practice," The British Journal of Radiology, pp. 140-153, 2004.
[56] L. Ibanez, W. Schroeder, L. Ng, and J. Cates, "The ITK Software Guide," Insight Software Consortium, 2005.
[57] L. Ibanez, W. Schroeder, L. Ng, and J. Cates, The ITK Software Guide: The Insight Segmentation and Registration Toolkit. Kitware Inc., 2003.
[58] L. Ibanez, L. Ng, J. Gee, and S. Aylward, "Registration patterns: the generic framework for image registration of the insight toolkit," Biomedical Imaging, 2002. Proceedings. 2002 IEEE International Symposium, pp. 345-348, 2002.
[59] W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, "Numerical recipes in C: the art of scientific computing," Cambridge University Press., 1992.
[60] C. V. Stewart, C.-L. Tsai, and B. Roysam, "The dual-bootstrap iterative closest point algorithm with application to retinal image registration," IEEE Trans. Med. Imaging., vol. 22, no. 11, pp. 1379-1394, 2003.
[61] T. Tommasini, A. Fusiello, E. Trucco, and V. Roberto, "Making Good Features Track Better," In Proc. CVPR, pp. 178-184, 1998.
[62] P. R. Beaudet, "Rotationally invariant image operators," In Proc. ICPR, pp. 579-583, 1978.
[63] B. S. Manjunath, "A new approach to image feature detection with applications," Pattern Recognition, vol. 29, no. 4, pp. 627-640, 1996.
[64] A. C. Shastry and R. A. Schowengerdt, "Airborne video registration and traffic-flow parameter estimation," IEEE Trans. Intell. Trans. Sys, vol. 6, no. 4, pp. 391-405, Dec.2005.
[65] K. Mikolajczyk and C. Schmid, "Scale & Affine Invariant Interest Point Detectors," International Journal ofComputer Vision, vol. 60(1), pp. 63-86, 2004.
[66] D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, vol. 60(2), pp. 91-110, 2004.
[67] V. Gor, M. Elowitz, T. Bacarian, and E. Mjolsness, "Tracking Cell Signals in Fluorescent Images," In Proc. CVPR, pp. 142-151, July2005.
[68] A. E. Beaton and J. W. and Tukey, "The fitting of power series, meaning polynomials, illustrated on band-spectroscopic data," Technometrics, p. 16:147-185, 1974.
[69] P. W. Holland and R. E. Welsch, "Robust regression using iteratively reweighted least squares," Commun. Statist. -Theor. Meth., vol. A6, pp. 813-827, 1977.
[70] The TargetJr Consortium., The VXL Book. 2000.
[71] J. Miller, V and C. V. Stewart, "MUSE: Robust surface fitting using unbiased scale estimates," IEEE Trans. on PAMI., pp. 300-306, 1996.
[72] C. V. Stewart, C.-L. Tsai, and A. Perera, "A View-Based Approach to Registration: Theory and Application to Vascular Image Registration," In Proc. IPMI, Ambleside, UK, 20-25, July2003.
[73] D. Shen and C. D. Hammer, "Hierarchical attribute matching mechanism for elastic registration," IEEE Trans. Med. Imaging., vol. 22, no. 11, pp. 1421-1439, 2002.
[74] R. C. Gonzalez and R. E. Woods, "Digital Image Processing," Prentice-Hall, Upper Saddle River, NJ, 2002.
[75] R. A. Fisher, "Applications of 'Student's' Distribution," Metron 5, pp. 3-17, 1925.
[76] T. George, T. Rick, and I. Clare, "A new spreadsheet method for the analysis of bivariate flow cytometric data," BMC Cell Biology, vol. 5, no. 1 Mar.2004.
[77] J.-P. Thirion, "Non-rigid matching using demons," In Proc. CVPR, pp. 245-251, June1996.
[78] J.-P. Thirion, "Image matching as a diffusion process: an analogy with Maxwell's demons," Med. Image Anal, vol. 2, no. 3, pp. 243-260, 1998.
[79] B. K. P. Horn and B. G. Schunck, "Determining optical flow," AI Memo 572. Massachusetts Institue of Technology, 1980.