請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/67936完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 貝蘇章(Soo-Chang Pei) | |
| dc.contributor.author | Hsin-Ying Tsai | en |
| dc.contributor.author | 蔡馨瑩 | zh_TW |
| dc.date.accessioned | 2021-06-17T01:59:12Z | - |
| dc.date.available | 2020-08-02 | |
| dc.date.copyright | 2017-08-02 | |
| dc.date.issued | 2017 | |
| dc.date.submitted | 2017-07-19 | |
| dc.identifier.citation | [1] A. Gnutti, F. Guerrini and R. Leonardi, “Representation of signals by local symmetry decomposition,” in Proceedings of Signal Processing Conference (EUSIPCO), pp. 983-987, 2015.
[2] D. C. Hauagge and N. Snavely, “Image matching using local symmetry features,” in Proceedings of Computer Vision and Pattern Recognition Conference (CVPR), pp. 206-213, 2007. [3] D.K. Washburn and D.W. Crowe, Symmetries of Culture: Theory and Practice of Plane Pattern Analysis, University of Washington Press, 1991. [4] M. Leyton, Symmetry, Causality, Mind, The MIT Press, Cambridge, Massachusetts, 1992. [5] A.R. Rao and G.L. Lohse, “Identifying high level features of texture perception,” in CVGIP: Graphical Models and Image Processing, pp. 218-233, 1993. [6] A.D. Grossand and T.E. Boult, “Analyzing skewed symmetries,” in International Journal of Computer Vision, pp. 91-111, 1994. [7] G. Marola, “On the detection of the axes of symmetry of symmetric and almost symmetric planar images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 104-108, 1989. [8] J. Liu, J. Mundy, D. Forsyth, A. Zisserman, and C. Rothwell, “Ecient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders,” in Proceedings of Computer Vision and Pattern Recognition Conference (CVPR), pp. 123-128, 1993. [9] S.C. Peiand and L.G. Liou, “Automatic symmetry determination and normalization for rotationally symmetric 2d shapes and 3d solid objects,” in Pattern Recognition, pp. 1193-1208, 1994. [10] L.G.C. Hamey and T. Kanade, “Computer analysis of regular repetitive textures,” in Image Understanding Workshop, pp. 1076-1088, 1989. [11] A. Turina, T. Tuytelaars, and Luc VanGool, “Efficient grouping under perspective skew,” in Proceedings of Computer Vision and Pattern Recognition, 2001. [12] W. Miller, Symmetry Groups and Their Applications, Academic Press, New York, 1973. [13] Y. Liu and R. Popplestone, “A Group Theoretical Formalization of Surface Contact,” in International Journal of Robotics Research, pp. 148-161, 1994. [14] D. Schattschneider, The plane symmetry groups: their recognition and notation, pp. 439-450, 1978. [15] Y. Liu, R. T. Collins, and Y. Tsin, “A computational model for periodic pattern perception based on frieze and wallpaper groups,” IEEE transactions on pattern analysis and machine intelligence, pp. 354-371, 2004. [16] Y. Liu, R. T. Collins, “Skewed symmetry groups,” in Proceedings of Computer Vision and Pattern Recognition(CVPR), 2001. [17] G. Schindler, P. Krishnamurthy, R. Lublinerman, Y. Liu and F. Dellaert, “Detecting and matching repeated patterns for automatic geo-tagging in urban environments,” in Computer Vision and Pattern Recognition, 2008. [18] T. Leungand and J. Malik. Detecting, “localizing and grouping repeated scene elements,” in European Conference on Computer Vision, pp. 546-555, 1996. [19] F. Schaalitzky and A. Zisserman, “Geometric grouping of repeated elements within images,” in Shape, Contour and Grouping in Computer Vision, 1999. [20] H. C. Lin, L. L. Wang, and S. N. Yang, “Extracting periodicity of a regular texture based on autocorrelation functions,” Pattern Recognition Letters, pp. 433-443, 1997. [21] J. Russ, The Image Processing Hand book, second Edition, CRC Press, 1995. [22] S.W. Zucker and D. Terzopoulos, “Finding structure in co-occurrence matrices for texture analysis,” in Proceedings of Computer graphics and image processing (CGIP), pp.286-308, 1980. [23] V.V. Starovoitov, S.Y. Jeong, and R.H. Park, “Texture periodicity detection: Features, properties, and comparisons,” IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, pp. 839-848, 1998. [24] R.L.E. Schwarzenberger, “The seventeen plane symmetry groups,” in Mathematical Gazette, pp. 123-131, 1974. [25] T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman, and A. Y. Wu, “An efficient k-means clustering algorithm: Analysis and implementation,” IEEE transactions on pattern analysis and machine intelligence, pp. 881-892, 2002. [26] M. Park, K. Brocklehurst, R.T. Collins, and Y. Liu, “Deformed lattice detection in real-world images using mean-shift belief propagation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1804-1816, 2009. [27] K. Briechle and U. D. Hanebeck. “Template matching using fast normalized cross correlation,” in Proceedings of SPIE: Optical Pattern Recognition XII, pp. 95–102, 2001. [28] A. Torii, J. Sivic, T. Pajdla, and M. Okutomi, “Visual place recognition with repetitive structures,” IEEE transactions on computer vision and pattern recognition, pp. 883-890, 2013. [29] J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman, “Lost in quantization: Improving particular object retrieval in large scale image databases,” in Proceedings of Computer Vision and Pattern Recognition Conference (CVPR), 2008. [30] H. Jegou, M. Douze, and C. Schmid, “On the burstiness of visual elements,” in Proceedings of Computer Vision and Pattern Recognition Conference (CVPR), 2009. [31] G. Salton and C. Buckley, “Term-weighting approaches in automatic text retrieval,” Information Processing and Management, 1988. [32] J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman, “Object retrieval with large vocabularies and fast spatial matching,” in Proceedings of Computer Vision and Pattern Recognition Conference (CVPR), 2007. [33] J. Sivic and A. Zisserman, “Video Google: A text retrieval approach to object matching in videos,” in ICCV, 2003. [34] O. Chum, J. Philbin, J. Sivic, M. Isard, and A. Zisserman, “Total recall: Automatic query expansion with a generative feature model for object retrieval,” in ICCV, 2007. [35] A. Pothen and C.J. Fan, “Computing the block triangular form of a sparse matrix,” ACM Transactions on Mathematical Software, pp. 303–324, 1990. [36] Y. Liu, W. C. Lin, and J. Hays, “Near-regular texture analysis and manipulation,” in ACM Transactions on Graphics (TOG), pp. 368-376, 2004. [37] A. Efros and T. Leung, “Texture synthesis by non-parametric sampling,” in Proceedings of the Seventh IEEE International Conference, pp. 1033-1038, 1999. [38] Y. Tsin, Y. Liu and V. Ramesh, “Texture replacement in real images,” in Proceedings of Computer Vision and Pattern Recognition (CVPR), 2001. [39] D. Morrison, Multivariate Statistical Methods, McGraw Hill College Div, 1990. [40] M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of cognitive neuroscience, pp. 71-86, 1991. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/67936 | - |
| dc.description.abstract | 人們具有先天的能力來辨認一個影像的對稱性和規律性，但如何能透過電腦自動化地辨認影像，卻值得我們去深思，在我們的研究中，我們以奇偶對稱性，Wallpaper Groups以及規律性來進行辨認影像。
在第二章中，我們透過奇偶能量比將影像切割成許多未重疊的區塊，而在這些切割後的區塊具有強烈的對稱性。接著，透過影像的對稱性，區塊位置以及大小等特徵進行影像之壓縮，並且求得此種影像壓縮方法的峰值訊雜比和壓縮比。 在第三章中，我們基於Wallpaper Groups進行影像之辨認，產生以及分解等三項工作。而這些方法分別為以下三項，第一項是辨認任何一張影像的Wallpaper Groups，第二項是透過一個基本的Wallpaper圖像來產生一幅彩色的影像，最後一項是將一張影像依據Wallpaper色彩做分解。此外，我們對奇偶對稱性與Wallpaper Groups的關係做了進一步的研討。 在第四章中，我們針對具有以下共通點:即是針對規律與接近規律性的自然影像偵測的演算法進行探討。在自然影像中，有一些規律的影像常被破壞。因此，我們分別介紹兩種方式來克服此問題:第一個方法為聚類傳播算法而第二個方法為視覺環境辨識。由於接近規律的材質在自然影像中無所不在，因而在本文的最後我們介紹一個有關接近規律材質的分析和合成的計算模型，作為本論文的結尾。 | zh_TW |
| dc.description.abstract | Contrary to the inaccurately computer-automated characteristics recognition, humans have an innate ability to perceive symmetry. In order to quantize the detection model, we address a novel detection approach consisting of even or odd symmetry, wallpaper groups, and regularity extraction methods in three chapters respectively.
In Chapter 2, an image is segmented into the variable-sized blocks with strong symmetrical characteristics extracted through either even or odd energy portions by optimally placing the center of symmetry. The experimental result shows excellent performance of PSNR and compression ratio performance of the testing images. In Chapter 3, three kinds of distinct analyses are applied to examine the wallpaper group approach, including classification, generation, and decomposition. With these three kinds of analysis, we can identify any wallpaper by different wallpaper groups, generate a colorful wallpaper from basic patterns and decompose a wallpaper into the segmented wallpapers with different colors, accordingly. In addition, the relationship between the even or odd symmetry and wallpaper groups is investigated. The algorithm studied in Chapter 4 are to detect regular and near-regular patterns with a natural image. Due to the deformed regular patterns, two efficient methods are proposed to solve the above-mentioned problem: mean-shift belief propagation and visual place recognition way. There are near-regular textures in the natural world, so we addressed a model for realizing the near-regular texture analysis algorithms. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T01:59:12Z (GMT). No. of bitstreams: 1 ntu-106-R04942107-1.pdf: 6917637 bytes, checksum: 9032e7f712f540b2672e3dfce8df39f6 (MD5) Previous issue date: 2017 | en |
| dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vii LIST OF TABLES x Chapter 1 Introduction 1 Chapter 2 Even or Odd Symmetry Analysis 4 2.1 Related Work 4 2.1.1 Representation of Signals by Local Symmetry Decomposition 5 2.1.2 Image Matching Using Local Symmetry Features 7 2.2 Even or Odd Symmetry Definition 9 2.2.1 Basic Symmetry Types 9 2.2.2 New Symmetry Types 12 2.2.3 Relationship for Each Symmetry Type 13 2.3 Globally Optimal Discrete Symmetry 16 2.4 Locally Optimal Discrete Symmetry 17 2.4.1 Candidate Identification 18 2.4.2 Symmetry Block Detection 18 2.4.3 Overlap Management 21 2.5 Experimental Result 22 2.5.1 PSNR 25 2.5.2 Compression Ratio 25 Chapter 3 Wallpaper Groups Analysis 27 3.1 Related Work 27 3.1.1 A Computational Model for Periodic Pattern Perception Based on Frieze and Wallpaper Groups 29 3.1.2 Skewed Symmetry Groups 31 3.1.3 Detecting and Matching Repeated Patterns for Automatic Geo-tagging in Urban Environments 32 3.2 Wallpaper Groups 33 3.2.1 Seventeen Wallpaper Groups Definition 34 3.2.2 Seventeen Wallpaper Groups Characteristics 34 3.3 Wallpaper Classification 36 3.3.1 Lattice Detection 37 3.3.2 Wallpaper Groups Classification 39 3.3.3 MATLAB GUI for Wallpaper Classification 42 3.4 Wallpaper Generation 46 3.4.1 Binary Wallpaper Generation 46 3.4.2 Colorful Wallpaper Generation 49 3.5 Wallpaper Decomposition 52 3.5.1 Colorful Wallpaper Quantization 52 .3.5.1.1 Color Quantization by Hue Histogram 52 .3.5.1.2 Color Quantization by K-means Clustering 54 3.5.2 Colorful Wallpaper Decomposition 56 3.5.3 MATLAB GUI for Wallpaper Generation and Decomposition 61 3.6 Even or Odd Symmetry V.S. Wallpaper Groups 63 3.6.1 Generate Wallpaper Groups Based on Even or Odd Symmetry 63 3.6.2 Generate Even or Odd Symmetry Based on Wallpaper Groups 68 Chapter 4 Regularity Analysis 71 4.1 Regular Patterns Detection Using Mean-Shift Belief Propagation 71 4.1.1 Reference Tile Extraction 72 4.1.2 Lattice Extension 73 4.1.3 Mean-Shift Believe Propagation Algorithm 74 4.1.4 Lattice Warping 75 4.1.5 Experimental Result 76 4.2 Regular Structures Detection Using Visual Place Recognition 77 4.2.1 Visual Word Weighting Strategies 77 4.2.2 Regular Structures Detection 79 4.2.3 Regular Structures for Scalable Retrieval 80 4.2.4 Experimental Result 81 4.3 Near-Regular Texture Analysis and Manipulation 82 4.3.1 Near-Regular Texture Definition 82 4.3.2 Near-Regular Texture Algorithm 83 .4.3.2.1 Geometry Deformation 84 .4.3.2.2 Lighting Deformation 87 .4.3.2.3 Color Deformation 87 .4.3.2.4 Regularity Measurement 88 4.3.3 Texture Replacement 90 Chapter 5 Conclusion 91 REFERENCE 93 | |
| dc.language.iso | en | |
| dc.subject | 規律性 | zh_TW |
| dc.subject | 接近規律性 | zh_TW |
| dc.subject | Wallpaper Groups | zh_TW |
| dc.subject | 局部對稱性 | zh_TW |
| dc.subject | 對稱性 | zh_TW |
| dc.subject | Symmetry | en |
| dc.subject | Local Symmetry | en |
| dc.subject | Wallpaper Groups | en |
| dc.subject | Regularity | en |
| dc.subject | Near Regularity | en |
| dc.title | 適用於對稱和規律影像分析之計算模型 | zh_TW |
| dc.title | A Computational Model for Image Analysis Based on Symmetry and Regularity | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 105-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 祈忠勇(Chong-Yung Chi),吳家麟(Ja-Ling Wu),鍾國亮(Kuo-Liang Chung) | |
| dc.subject.keyword | 對稱性,局部對稱性,Wallpaper Groups,規律性,接近規律性, | zh_TW |
| dc.subject.keyword | Symmetry,Local Symmetry,Wallpaper Groups,Regularity,Near Regularity, | en |
| dc.relation.page | 97 | |
| dc.identifier.doi | 10.6342/NTU201701670 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2017-07-20 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-106-1.pdf 未授權公開取用 | 6.76 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。