پایان نامه بهبود مدل سطوح فعال با استفاده از بهینه سازی توابع انرژی برای جزء بندی تصاویر سه بعدی

فهرست:

اول:مقدمه                                                                                                              1

          1-1-مقدمه                                                                                                           2 

          1-2-خلاصه مسئله                                                                                                   4

          1-3-سرفصل ها                                                                                                       4

فصل دوم:پیشینه تحقیق                                                                                                        6

          2-1-مقدمه                                                                                                             7

          2-2-مروری بر روش های قطعه بندی                                                                             7

                   2-2-1-روش های ساختاری                                                                              8

                   2-2-2-روش های آماری                                                                                12             

                   2-2-3-روش های ترکیبی                                                                              15

فصل سوم:مدل های قابل تغییر شکل                                                                                       18

          3-1-مقدمه                                                                                                           19

          3-2-مدل های قابل تغییر شکل پارامتری                                                                      20

                   3-2-1-بیان ریاضی مدل                                                                                20

                   3-2-2-انرژی داخلی مدل                                                                              21                                      

                   3-2-3-انرژی خارجی مدل                                                                             22

3-2-4-تکامل مدل قابل تغییر شکل پارامتری                                                      23

3-2-5-روش حل عددی                                                                                24

3-3-محدودیت های مدل های قابل تغییر شکل پارامتری                                                   24    

3-3-1-حساسیت به شرایط اولیه                                                                      25

3-3-2-حساسیت به حداقل های محلی                                                              25

3-3-3-حساسیت به انحنای زیاد                                                                      26

3-3-4-نیاز به تنظیم پارامترها                                                                         27

3-3-5-بار محاسباتی                                                                                    27

فصل چهارم:سطح فعال منفصل برای قطعه بندی تصاویر سه بعدی                                                   28

          4-1-مقدمه                                                                                                           29

          4-2-تعریف راس و سطح در مدل سطوح فعال منفصل                                                       30

          4-3-مرحله اول:تعیین سطح اندازه گیری شده                                                                 31

          4-4-مرحله دوم:تولید دانش پیشین غیرایستا در فضای سه بعدی                                          34

                   4-4-1-انحنا در فضای سه بعدی                                                                      34                       

                   4-4-2-نمونه برداری مجدد سطح بر مبنای انحنا                                                   35

          4-5-مرحله سوم:تخمین آماری                                                                                   39 

فصل پنجم:روش پیشنهادی                                                                                                  40

          5-1-مقدمه                                                                                                           41

          5-2-الگوریتم پیشنهادی                                                                                           41

5-2-1-تخمین کانتور فعال برای سطح اولیه                                                        42

5-2-2-روش جستجوی خطی                                                                         43

5-2-3-انتگرال انحنا به عنوان انرژی داخلی                                                         44

5-2-4-تبدیل ویولت برای تصاویر                                                                     45

5-2-5-وابستگی محلی فاز به عنوان انرژی خارجی                                                47

5-2-6-گرادیان تصویر حاصل از استخراج مرز توسط ویولت به عنوان انرژی خارجی         49

5-2-7-نمونه برداری براساس همسایگی                                                             51

5-2-8-بروز رسانی شبکه مثلثی براساس نزدیکترین همسایگی ها                              52     

5-2-9-تشریح روند کلی روش پیشنهادی                                                           53

فصل ششم:نتایج الگوریتم پیشنهادی و بررسی آنها                                                                       57

          6-1-مقدمه                                                                                                           58

          6-2-مغز                                                                                                              58

          6-3-ریه                                                                                                              59

          6-4-کبد                                                                                                             60

          6-5-پرتونگاری کامپیوتری                                                                                        61

6-5-1-تاریخچه سی تی اسکن                                                                        62

6-5-2-اجزای اصلی تشکیل دهنده دستگاه سی تی اسکن                                       62

          6-5-2-الف-لامپ اشعه ایکس                                                               63

          6-5-2-ب-دتکتورهای اشعه ایکس                                                         64

          6-5-2-پ-واحد جمع آوری اطلاعات                                                      64

          6-5-2-ت-واحد تولید ولتاژ بالا                                                             64

          6-5-2-ث-تخت بیمار                                                                        64

          6-5-2-ج-واحد بازسازی و تولید تصویر                                                   64

          6-5-2-چ-کنسول نمایش و واسط کاربر                                                   65

          6-5-ح-کامپیوتر کنترل کننده مرکزی                                                     65

6-5-3-نسل های مختلف دستگاه                                                                     65

          6-5-3-الف-نسل اول                                                                         65

          6-5-3-ب-نسل دوم                                                                          65

          6-5-3-پ-نسل سوم                                                                         65

          6-5-3-ت-نسل چهارم                                                                       66

          6-5-3-ث-نسل پنجم                                                                        66

          6-5-3-ج-نسل ششم                                                                         66

          6-5-3-چ-نسل هفتم                                                                         67

          6-6-مشخصات نتایج                                                                                               67

6-7-نتایج و تحلیل آنها                                                                                            67

6-7-1-مقایسه نتایج مدل سطح فعال منفصل با چند روش معمول                             67

6-7-2-مقایسه نتایج روش پیشنهادی و الگوریتم سطح فعال منفصل                          69

                   6-7-2-الف-ستاره سه بعدی ساختگی                                                     69

                   6-7-2-ب-تصاویر سی تی اسکن مغز                                                      70

                   6-7-2-پ-تصاویر سی تی اسکن ریه                                                       76

                   6-7-2-ت-تصاویر سی تی اسکن کبد                                                      81

                   6-7-2-ث-مقایسه سرعت همگرایی و بار محاسباتی                                     88

فصل هفتم:نتیجه گیری و کارهای آینده                                                                                   90

          7-1-نتیجه گیری                                                                                                   91

          7-2-کارهای آینده                                                                                                  92

فهرست منابع                                     

منبع:

[1] N. r.Pal and S. K.Pal, A review on image segmentation techniques, Pattern Recognition, Vol. 26, No.9, 1993, 1277-1294.

[2] D. L.Pham, C. Xu and J. L.Prince, A Survey of Current Methods in Medical Image Segmentation, Technical Report, Department of Electrical and Computer Engineering, the Johns Hopkins University, Baltimore, 2001.

[3] S. Lakare and A. Kaufman, 3D segmentation techniques for medical volumes, Technical Report, Center for Visual Computing, Department of Computer Science, State University of New York, 2000.

[4] M. Marsh, A. Literature Review of Image Segmentation Techniques and Matting for the Purpose of Implementing “Grab-Cut”, Grahamstown.

[5] X. Huang and G. Tsechpenakis, Medical Image Segmentation, Information Discovery on Electronic Health Records, 2009, 12-251.

[6] O. Wirjadi, Survey of 3D image segmentation methods, Fraunhofer Institute Techno-und Wirtschaftsmathematik, 2007.

[7] T. Uemura, G. Koutaki and K. Uchimura, Image Segmentation Based on edge Detection using Boundary Code, International Journal of Innovative Computing, Information and Control, Vol. 7, No. 10, 2011.

[8] L. Gui, R. Lisowski, T. Faundez, P. S. Huppi and F. Lazeyras, Morphology-driven automatic segmentation of MR images of the neonatal brain, Elsevier Journal on Medical Image Analysis, 2012, 1565-1579.

[9] T. Shen, H. Li, Z. Qian and X. Huang, Active Volume Models for 3D Medical Image Segmentation, IEEE conference on Computer Vision and Pattern Recognition, 2009, 707-714.

[10] E. Cuevas, D. Zaldivar and M. Perez-Cisneros, A Novel Multi-threshold Segmentation Approach based on Differential Evolution Optimization, Expert Systems with Application, Vol. 37, No. 7, 2010, 5265-5271.

[11] A. Mishra, P.W. Fieguth, D.A. Clausi, Decoupled Active Surface for Volumetric Image Segmentation, Canadian Conference on Computer and Robot Vision(CRV), 2010, 293-300.

[12] J. Olivier, J. Mille, R. Bone, J-J. Rousselle, Dynamic Neighborhoods in Active Surface for 3D Segmentation, International Journal for Computational Vision and Biomechanics, 2008, 173-180.

[13] N. barreira, M. G. Penedo, L. Cohen and M. Ortega, Topological active volumes: A topology-adaptive deformable model for volume segmentation, Elsevier Journal on Pattern Recognition 43, 2010, 255-266.

[14] J. Mille, Narrow band region-based active contours and surfaces for 2D and 3D segmentation, Computer Vision and Image Understanding, 2009, 946-965.

 [15] F. Heckel, O. Konrad, H. K. Hahn and H. Peitgen, Interactive 3D medical image segmentation with energy-minimizing implicit functions, Elsevier Journal on Computer and Graphics, 2011, 275-287.

[16] A. Mishra, Decoupled Deformable Model for 2D/3D Boundary Identification, A Thesis of Doctor of Philosophy in System Design Engineering presented to the University of Waterloo, 2010.

[17] J. Montagnat, H. Delingete and N. Ayache, A review of deformable surfaces: topology, geometry and deformation, Elsevier Journal on Image and Vision Computing, 2001, 1023-1040.

[18] L. D. Cohen and I. Cohen, Deformable models for 3D medical images using finite elements and balloons, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992, 592-598.

[19] L. D. Cohen, On active contour models and balloons, CVGIP: Image understanding, Vol. 53, No. 2, 1991, 211-218.

[20] C. Xu and J. L. Prince, Snakes, shapes, and gradient vector flow, IEEE Transactions on Image Processing, Vol. 7, No. 3, 1998, 359-369.

[21] B. Li and S.T. Acton, Active contour external force using vector field convolution for image segmentation, IEEE Transactions on Image Processing, Vol. 16, No. 8, 2007, 2096-2106.

[22] A. Blake and M. Isard, Active contours, London: Springer, Vol. 1, 1998.

[23] T. F. Cootes, C. J. Taylor, D. H. Cooper and J. Graham, Active shape models-their training and application, Computer vision and image understanding, Vol. 61, No. 1, 1995, 38-59.

[24] J. C. Nascimento and J. S. Marques, Robust shape tracking in the presence of cluttered background, IEEE Transactions on Multimedia, Vol. 6, No. 6, 2004, 852-861.

[25] J. C. Nascimento and J. S. Marques, Robust shape tracking with multiple models in ultrasound images, IEEE Transactions on Image Processing, Vol. 17, No. 3, 2008, 392-406.

[26] Y. Bar‐Shalom and T. E. Fortmann, Tracking and data association, Academic, New York, 1998.

[27] J. C. Nascimento and J. S. Marques, Adaptive snakes using the EM algorithm, IEEE Transactions on Image Processing, Vol. 14, No. 11, 2005, 1678-1686.

[28] L. D. Cohen and I. Cohen, Finite-element methods for active contour models and balloons for 2D and 3D images, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, No.11, 1993, 1131-1147.

[29] G. Sundaramoorthi, A. Yezzi and A. C. Mennucci, Coarse-to-fine segmentation and tracking using Sobolev Active Contours, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, No. 5, 2008, 851-864.

[30] G. Xu, E. Segawa and S. Tsuji, Robust active contours with insensitive parameters, Pattern Recognition, Vol. 27, No. 7, 1994, 879-884.

[31] G. Xu, E. Segawa and S. Tsuji, A robust active contour model with insensitive parameters, IEEE Fourth International Conference on Computer Vision, 1993, 562-566.

[32] A. K. Mishra, P. W. Fieguth and D. A. Clausi, From Active Contours to Active Surface, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, 2121 – 2128.

[33] T.F. Chan, B.Y. Sandberg, and L.A. Vese, Active contours without edges for vector-valued images, Journal of Visual Communication and Image Representation, 2000.

[34] T.F. Chan and L.A. Vese, Active contours without edges, IEEE Transactions on Image Processing, 2001.

[35] L. Bing and S.T. Scott, Automatic active model initialization via Poisson inverse gradient, IEEE Transactions on Image Processing, 2008.

[36] I. Sobol, Uniformly distributed sequences with an additional uniform property, USSR Computational Mathematics and Mathematical Physics 16, 1976, 236–242.

[37] A. K. Mishra, A. Wong, P. W. Fieguth and D. A. Clausi, Quasi-random nonlinear scale space, Pattern Recognition Letters 31, 2010, 1850 – 1859.

[38] L. MA, J. Tian, W. Yu, Visual Saliency Detection in Image using Ant Colony Optimization and Local Phase Coherence, IEEE Electronics Letters, Vol. 46, 2011, 1066-1068.

[39] R. Hassen, Z. Wang and M. Salama, No-Reference Image Sharpness Assessment based on Local Phase Coherence Measurement, IEEE International Conference on Acoustic, Speech and Signal Processing(ICASSP), 2010.

[40] R. Hassen, Z. Wang and M. Salama, Multifocus Image Fusion using Local Phase Coherence Measurement, International Conference on Image Analysis and Recognition(ICIAR), 2009.

[41] Z. Wang, E. P. Simoncelli, Local Phase Coherence and the Perception of Blur, Advances in Neural Information Processing Systems, Vol. 16, 2004.

[42] J. Cheng, Y. Liu, 3D Reconstruction of Medical Image using Wavelet Transform and Snake Model, Journal of Multimedia, vol. 4, 2009, 427-434.

[43] Y. Zhang, B. J. Matuszewski, L. Shark, and C. J. Moore, Medical image segmentation using new hybrid level-set method, Fifth International Conference on BioMedical Visualization, 2008, 71-76.