請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/31459
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 周瑞仁(Jui-Jen Chou) | |
dc.contributor.author | Yu-Chun Wang | en |
dc.contributor.author | 王友俊 | zh_TW |
dc.date.accessioned | 2021-06-13T03:13:17Z | - |
dc.date.available | 2011-08-30 | |
dc.date.copyright | 2006-08-30 | |
dc.date.issued | 2006 | |
dc.date.submitted | 2006-08-24 | |
dc.identifier.citation | Ballard, D. H., and C. M. Brown. 1982. Computer Vision. Prentice Hall, New Jersey.
Bennett, N., R. Burridge, and N. Saito. 1999. A method to detect and characterize ellipses using the hough transform. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(7): 652-657. Borgefors, G. 1984. Distance transform in arbitrary dimension. Comp. Vis. Graph. Imag. Proc. 27: 321-345. Burt, P. J., T. H. Hong, and A. Rosenfeld. 1981. Segmentation and estimation of image region properties through cooperative hierarchical computation. IEEE Trans. on Systems, Man, and Cybernetics 11:802-809. Canny, J. 1986. A Computational Approach to Edge Detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 8: 679-698. Chen, C. M., H. S. Lu, and Y. C. Lin. 2000. An early vision-based snake model for ultrasound image segmentation. Ultrasound in Medicine and Biology 26(2): 273-285. Chen, Y. C., and S. C. Lee. 1995. A new method for quadratic curve detection using K-RANSAC with acceleration techniques. Pattern Recognition 28(8): 663-682. Cheng, Y. 1995. Mean shift, mode seeking, and clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence 17(8): 790-798. Chien, C. F., and T. T. Lin. 2002. Leaf area measurement of selected vegetable seedlings using elliptical Hough transform. Transactions of the ASAE 45(5): 1669-1677. Christoudias, C. M., B. Georgescu, and P. Meer. 2002. Synergism in low level vision. 16th International Conference on Pattern Recognition 4:150-155. Quebec City, Canada. Cohen, L. D., and I. Cohen. 1993. Finit-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans. on Pattern Analysis and Machine Intelligence 15(11): 1131-1147. Comaniciu, D., V. Ramesh, and P. Meer. 2000. Real-time tracking of non-rigid objects using mean shift. IEEE Conference on Computer Vision and Pattern Recognition 2:142-149. Hilton Head, SC. Comaniciu, D., and P. Meer. 2002. Mean shift, a robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 24: 603-619. Comaniciu, D. 2003. An algorithm for data-driven bandwidth selection. IEEE Trans. on Pattern Analysis and Machine Intelligence 25(2): 281-288. Danielsson, P. E. 1980. Euclidean distance mapping. Comp. Graph. Imag. Proc. 14: 227-248. Fitzgibbon, A. W., M. Pilu, and R. B. Fischer. 1999. Direct least square fitting of ellipses. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(5): 476-480. Fu, K. S., and J. K. Mui. 1981. A Survey on Image Segmentation. Pattern Recognition 13: 3-16. Fukunaga, K., and L. D. Hostetler. 1975. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition. IEEE Trans. on Information Theory IT-21: 32-40. Gath, I., and D. Hoory. 1995. Fuzzy clustering of elliptic ring-shaped clusters. Pattern Recognition Letter 16: 727-741 Gonzalez, R. C., and P. Wintz. 1987. Digital Image Processing (2nd. Ed). Addison-Wesley Harlick, R. M. 1978. Zero-Crossing of Second Directional Derivative Edge Operator. IEEE Trans. on Pattern Analysis and Machine Intelligence 6:58-68. Hjelmas, E., and B. K. Low. 2001. Face Detection: A Survey. Computer Vision and Image Understanding 83: 236–274. Horn, B. K. P., and B. G. Schunck. 1981. Determining optical flow. Artificial intelligence 17: 185-203. Hough, P. V. C. 1962. Method and means for recognizing complex patterns. U.S. Pattern 3069654. Hueckel, M. F. 1971. An Operator Which Locates Edges in Digitised Pictures. Journal of the ACM 18: 113-125. Karaman, M., A. Kutay, and H. Bozdagi. 1995. An adaptive speckle suppression filter for medical ultrasonic imaging. IEEE Trans. on Medical Imaging 14(2):283-292. Kass, M., A. Witkin, and D. Terzoulos. 1988. Snake: Active contour models. International J. Computer Vision 1(4): 321-331. Kittler, J., and J. Illingworth. 1985. On threshold selection using clustering criteria. IEEE Trans. on Systems, Man, and Cybernetics 15:652-655. Kohler, R. A. 1981. A segmentation based on thresholding. Computer Vision, Graphics and Image Processing 15:319-338. Krishnapuram, R., H. Frigui, and O. Nasraoui. 1995. Fuzzy and possibilistic shell clustering algorithms and their application to boundary detection and surface approximation-Part I. IEEE Trans. on Fuzzy Systems 3(1): 29-43 Lefebvre, F., G. Berger, and P. Laugier. 1998. Automatic detection of the boundary of the calcaneus from ultrasound parametric images using an active contour model: Clinical assessment. IEEE Trans. on Medical Imaging 17(1): 45-52. Levine, M. D., and A. Nazif. 1984. An optimal set of image segmentation rules. Pattern Recognition Letters 1:417-422. Mallat, S. G. 1989. A Theory for Multiresolution Signal Decomposition: the Wavelet Representation. IEEE Trans. on Pattern Analysis and Machine Intelligence 11:674-693. Meer, P. and B. Georgescu. 2001. Edge detection with embedded confidence. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(12):1351-1365. Pal, N. R. and S. K. Pal. 1993. A review on image segmentation techniques. Pattern recognition 26(9): 1277-1294. Park, J., and J. M. Keller. 2001. Snake on the watershed. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(10): 1201-1205. Pratt, W. K. 1983. Digital Image Processing. Wiley, New York. Ridler, T. W., and S. Calvard. 1978. Picture thresholding using an iterative selection method. IEEE Trans. on Systems, Man, and Cybernetics SMC-8: 630-632. Sahoo, P. K., S. Soltani, A. K. C. Wong, and Y. C. Chen. 1988. A survey of thresholding techniques. Computer Vision, Graphics and Image Processing 41:233-260. Sapiro, G., and D. L. Ringach. 1996. Anisotropic Diffusion on Multivalued Images with Applications to Color Filtering. IEEE Trans. on Image Processing 5(11): 1582–1586. Shashidhar, N. S., D. S. Jayas, T. G. Crowe, and N. R. Bulley. 1997. Processing of digital image of touching kernels by ellipse fitting. Canadian Agric. Eng. 39(2): 139-142. Shatadal, P., D. S. Jayas, and N. R. Bulley. 1995. Digital image analysis for software separation and classification of touching grains: I. Disconnect algorithm. Transactions of the ASAE 38(2): 635-643. Spann, M., and R. G. Wilson. 1985. A Quad-Tree Approach to Image Segmentation Which Combines Statistical and Spatial Information. Pattern Recognition 18(3/4):257-269. Tsai, W. H. 1985. Moment-preserving thresholding: a new approach. Comput. Vision, Graphics. Image Processing 29: 377-393. Taxt, T., P. J. Flynn, and A. K. Jain. 1989. Segmentation of document images. IEEE Trans. on Pattern Analysis and Machine Intelligence 11:1322-1329. Vincent, L., and P. Soille. 1991. Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Trans. on Pattern Analysis and Machine Intelligence 13(6): 583-598. Visen, N. S., N. S. Shashidhar, J. Paliwal, and D. S. Jayas. 2001. Identification and segmentation of occluding groups of grain kernels in a grain sample image. J. Agric. Eng. Res. 79(2): 159-166. Wang, Y. C., and J. J. Chou. 2004. Automatic segmentation of touching rice kernels with active contour model. Transactions of the ASAE 47(5): 1803-1811. Wang, Y. C., and J. J. Chou. 2006. Segmentation of ellipse-like objects in an image with MFA approach. Journal of Agricultural Machinery 15(1): 15-24. (in Chinese) Wilson, R. G., and M. Spann. 1988. Image Segmentation and Uncertainty. Pattern Recognition and Image Processing Series. Research Studies Press Ltd. Xu, C., and J. L. Prince. 1998. Snakes, shapes, and gradient vector flow. IEEE Trans. on Image Processing 7(3): 359-363. Yang, F., and Tianzi Jiang. 2001. Cell image segmentation with kernel-based dynamic clustering and an ellipsoidal cell shape model. Journal of Biomedical Informatics. 34: 67-73 Yuen, H. K., J. Illingworth, and J. Kittler. 1989. Detecting partially occluded ellipses using the Hough transform. Image and Vision Computing 7(1): 31-37. Yuen, P. C., Y. Y. Wong, and C. S. Tong. 1996. Contour detection using enhanced snakes algorithm. Electronics Letters 32(3): 202-204. Yun, H. S., W. O. Lee, H. Chung, H. D. Lee, J. R. Son, K. H. Cho, and W. K. Park. 2002. A Computer Vision System for Rice Kernel Quality Evaluation. 2002 ASAE Annual Meeting. Paper number 023130. Zhu, S. C. and A. Yuille. 1996. Region growing: unifying snakes, region growing, and Bayes/MDL for Multiband image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(9): 884-900. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/31459 | - |
dc.description.abstract | 本論文發展一系列影像處理方法,使相互接觸之近似橢圓物件影像得以正確分割。主要方法包括:前置濾波器、分類、建立初始形變曲線與物件輪廓重建等。為了克服雜訊與被偵測物件具明顯紋理之干擾,提出結合Mean shift演算法與梯度向量場(gradient vector field, GVF)所設計之前置濾波器。經由此濾波器處理,可正確地擷取影像中物件之輪廓線。根據這些被偵測物件的輪廓線所產生之影像場,本研究發展出兩種不同的動態質點分類法,以正確獲得每一個物件之流場中心。此兩種分類法分別使用反向梯度向量場與距離轉換場配合Mean shift演算法發展出來。為了產生初始形變曲線,分別藉由蒙地卡羅觀念均勻放置動態質點法與使用Fitzgibbon最佳橢圓法,配合所提出兩種分類法。最後以主動輪廓模式(active contour model,ACM)重建近似橢圓物件之輪廓。實驗結果顯示,即使所偵測之物件輪廓線破碎不完整,但只要邊界輪廓線資訊比在50%以上,都能成功地重建出每一個物件的完整輪廓,其與人工分割米粒影像之相似度高達96%以上。當被偵測物件具明顯紋理或影像被雜訊干擾時,以Mean shift演算法與梯度向量場所設計之濾波器能有效抑制干擾,甚至當影像外加10%的點雜訊,所設計之濾波器仍能濾除此干擾,正確擷取物件輪廓線特徵,配合後續動態質點分類法(active points grouping approach)與主動輪廓模式,完成明顯紋理並相互接觸近似橢圓物件影像分割之目的。經由此方法所處理之物件影像,可依據其個別封閉輪廓線的取得,很容易求得影像中各物件之幾何、紋理或顏色之特徵,方便後續叢聚、分類與了解之目的。 | zh_TW |
dc.description.abstract | In this study, we developed a synergistic approach for the segmentation of touching ellipse-like objects with obvious texture and noises in an image. The proposed approach modifies and integrates several major image processing methods including pre-filtering, grouping, creating initial contours, and reconstructing contours. For de-noising, mean shift algorithm and Gradient Vector Field (GVF) are employed as a pre-filter. Through the filtering and edge detection, the processed image only preserves the boundaries of objects and rejects noise. With the edges, we developed two kinds of active point grouping approaches for generating the field center of each touching ellipse-like object. Inverse GVF (IGVF) field and mean shift algorithm with distance transform (DT) weight map are employed in the two grouping approaches, respectively. For creating initial deformable contour of each object, we designed two generation methods, the equally-spacing active points method inspired by Monte Carlo’s concept as well as Fitzgibbon’s optimal ellipses method. Finally, the complete contour of each object could be correctly reconstructed by Active Contour Model (ACM). The result shows that the algorithm could successfully reconstruct the whole contour as long as more than 50% of piecewise edge information remained in an image. Compared with the original contours, the ones generated in this study achieved more than 96% similarity. When the obvious textures or noises are filtered out by the mean shift algorithm with GVF weight map, it could effectively remain the edges of the detected objects. Even for an image polluted by 10% salt and pepper noises, the approach still can effectively and robustly eliminate the added noises. Therefore we can successfully cluster objects and reconstruct their corresponding contours by applying active contour model approach. The complete contours of touching objects could facilitate the subsequent image processing to obtain the geometric, texture, and color characteristics of objects in an image. These features might then be used for further clustering, classification, or image understanding. | en |
dc.description.provenance | Made available in DSpace on 2021-06-13T03:13:17Z (GMT). No. of bitstreams: 1 ntu-95-D88631003-1.pdf: 9792105 bytes, checksum: ea9d23e9595095e81774ae50ba8a5103 (MD5) Previous issue date: 2006 | en |
dc.description.tableofcontents | 誌謝 i
摘要 ii Abstract iv Content vi List of Figures ix List of Tables xi Chapter 1 Introduction 1 1.1 Purpose………………………………………………..………….........1 1.2 Contributions...………………….....….………………………….……2 1.3 Dissertation organization.……........….………………………….……3 Chapter 2 Literature Review 5 2.1 Region based segmentation methods.....….……………………..….…5 2.2 Boundary based segmentation methods.....….…………………..….…7 Chapter 3 Methods 11 3.1 Mean shift pre-filter…………………….....……...…..………..….…13 3.1.1 Density gradient estimate in mean shift........…..…….....………13 3.1.2 Mean shift for image segmentation....……..……………………17 3.1.3 Mean shift with weight map....……..…………...…….…...……18 3.2 Edge detection.....….………………..…………...……………..….…21 3.3 Formation of field center using active points………………………22 3.3.1 Potential field....................……..…………..…...…….……...…22 3.3.1.1 Gradient vector flow field…………….…………………23 3.3.1.2 Distance transform field…………………………………28 3.3.1.3 Example for field of ellipse contour………...…...………29 3.3.2 Active point grouping approach………………………………...31 3.3.2.1 Active points driven by IGVF field……………………31 3.3.2.2 Active points driven by mean shift algorithm with DT weight map…………………..…………………....…36 3.4 Automatic generation of initial deformable contours……...…………37 3.4.1 Generation based on Monte Carlo’s method....……..……...…37 3.4.2 Generation based on Fitzgibbon approach...……..……...…38 3.5 Contour reconstruction………….………………………....…………40 3.5.1 Contour reconstruction with active contour model........…...…40 3.5.2 Contour information ratio and similarity……………………...45 Chapter 4 Results and Discussions 46 4.1 Touching objects without noises and obvious textures…...…………46 4.1.1 Kernels with long touching border......................……..……...…54 4.1.2 A kernel closely surrounded by others.................…..……...…57 4.2 Touching objects with textures or light noises……………...………62 4.2.1 Touching kernel with Gaussian noise.....................…..……...…66 4.2.2 Touching kernel with different level of salt and pepper noise.…69 4.2.3 Touching kernel with clear textures……................…..……...…76 4.3 Touching objects with textures and higher level noises…..….........…80 4.3.1 Effectiveness of pre-filtering with different parameters and weighting………………………………………………………80 4.3.2 Different settings of minimum region pixels M…..……………84 4.3.3 Weighing with GVF……………………………………….……85 Chapter 5 Conclusions 108 References 110 Appendix Condensed Version in Chinese A-1 | |
dc.language.iso | en | |
dc.title | 以影像處理方法分割相互接觸之近似橢圓 | zh_TW |
dc.title | Image Processing Method for Segmentation of Touching Ellipse-like Objects | en |
dc.type | Thesis | |
dc.date.schoolyear | 94-2 | |
dc.description.degree | 博士 | |
dc.contributor.oralexamcommittee | 林達德,陳顯禎,賴坤財,艾群 | |
dc.subject.keyword | 主動輪廓模式,邊緣偵測,橢圓偵測,梯度向量場,影像處理,影像分割,機器視覺, | zh_TW |
dc.subject.keyword | Active contour model (ACM),Edge detection,Ellipse detection,Gradient vector flow (GVF),Image processing,Mean shift,Segmentation, | en |
dc.relation.page | 116 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2006-08-25 | |
dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
dc.contributor.author-dept | 生物產業機電工程學研究所 | zh_TW |
顯示於系所單位: | 生物機電工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-95-1.pdf 目前未授權公開取用 | 9.56 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。