請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/44764完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 貝蘇章 | |
| dc.contributor.author | Yu-Ning Liu | en |
| dc.contributor.author | 劉祐寧 | zh_TW |
| dc.date.accessioned | 2021-06-15T03:54:25Z | - |
| dc.date.available | 2012-08-20 | |
| dc.date.copyright | 2011-08-20 | |
| dc.date.issued | 2011 | |
| dc.date.submitted | 2011-08-17 | |
| dc.identifier.citation | [1] Ferrari, V., Tuytelaars, T., and Van Gool, L. 2001. Simultaneous object recognition and segmentation by image exploration. In Proceedings European Conference on Computer Vision, Prague, Czech Republic, pp. 40–54.
[2] Hartley, R.I. and Zisserman, A. 2004. Multiple View Geometry in Computer Vision, 2nd edition, Cambridge University Press,ISBN: 0521540518 [3] Lowe, D. 1999. Object recognition from local scale-invariant features. In Proceedings of the 7th International Conference on Computer Vision, Kerkyra, Greece, pp. 1150–1157 [4] Lowe, D. 2004. Distinctive image features from scale-invariant keypoints. International Journal on Computer Vision 60(2):91–110. [5] Matas, J. Chum, O., Urban, M., and Pajdla, T. 2002. Robust wide-baseline stereo from maximally stable extremal regions. In Proceedings of the British Machine Vision Conference, Cardiff, UK, pp. 384–393. [6] Matas, J., Chum, O., Urban, M., and Pajdla, T. 2004. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing 22(10):761–767. [7] Obdrˇz’alek, ˆ S. and Matas, J. 2002. Object recognition using local affine frames on distinguished regions. In Proceedings of the British Machine Vision Conference, Cardiff, UK, pp. 113–122. [8] Tuytelaars, T. andVan Gool, L. 2000.Wide baseline stereo matching based on local, affinely invariant regions. In Proceedings of the 11th British Machine Vision Conference, Bristol, UK, pp. 412–425. [9] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L.V. Gool, “A Comparison of Affine Region Detectors,” accepted by Int'l J. Computer Vision. [10] P.-E. Forss’en and D. Lowe. Shape descriptors for maximally stable extremal regions. In IEEE International Conference on Computer Vision, volume CFP07198-CDR, Rio de Janeiro, Brazil, October 2007. IEEE Computer Society. [11] Mikolajczyk, K., Schmid, C.: Scale and Affine Invariant Interest Point Detectors. International Journal of Computer Vision. 60 (2004) 63–86 [12] ˇS. Obdrˇz’alek and J. Matas. Object recognition using local affine frames on maximally stable extremal regions. In J. Ponce, M. Hebert, C. Schmid, and A. Zisserman, editors, Toward Category-Level Object Recognition, LNCS, pages 83–104. Springer, 2006. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/44764 | - |
| dc.description.abstract | 在這篇論文裡，首先介紹了一種非常有用的區域特徵，稱為最穩定極值區域。這個特徵區域比同類的特徵子上絕大多數表現得很突出，並且有運算速度快的優點。爾後我們介紹了兩種不同的描述子去描述特徵區域，分別是利用共變矩陣正規化以及建立仿射不變特徵。仿射不變特徵是由特定的點所構成，比如說區域的幾何重心，對於凹面的切線，在凹面中對於切線最遠的點，在整個邊界中對於切點最遠的點。並且詳細了介紹凹面切點的演算法以及應用在最穩定極值區域的資料結構演算法。最後利用仿射不變特徵對於影像資料進行比對並評估效能。 | zh_TW |
| dc.description.abstract | At first, this paper introduced a powerful region feature – Maximally Stable Extremal Region (MSER), which has a better performance comparing to other region features. Then we use two different descriptors to describe the region, such as ellipse expression and local affine frame construction. Ellipses for each region are computed from covariant matrix and can be normalized to a circle. Local affine frame (LAF) is another description to feature region. In this paper we use several distinguished points, such as geometric center of the region, bi-tangent points of the region, the deepest points of the concavity and the farthest from the bi-tangent line. We also explain algorithms to MSER、LAF, including union-find and bin-sort for MSER detection and contour tracing, tangent from point to any polygon and steps to find bi-tangent points to construct LAF. Finally we compare the MSER to the other region detector and use MSER with LAF to match images from different deformation with image. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T03:54:25Z (GMT). No. of bitstreams: 1 ntu-100-R98942125-1.pdf: 5048570 bytes, checksum: e12b46142441c4b878a5d5e9c3151ff1 (MD5) Previous issue date: 2011 | en |
| dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 iii ABSTRACT v CONTENTS vii LIST OF FIGURES ix LIST OF TABLES xv Chapter 1 Introduction 1 Chapter 2 Maximally Stable Extremal Region 3 2.1 Stable Extremal Region 5 2.2 Detect Maximally Stable Extremal Region 6 2.3 Properties for MSER 7 2.3.1 Invariance to affine transformation of pixel continuity 7 2.3.2 Invariance to monotonic transformation 8 2.3.3 Stability 8 2.3.4 Multi-scale detection & Data-dependent shape 8 2.3.5 Fast and low complexity 8 2.4 Bin-sort and Union-Find algorithm 9 2.4.1 Bin-sort algorithm 9 2.4.2 Union-Find algorithm 10 2.5 An example to find MSER 13 Chapter 3 Affine Covariant Region Descriptors 17 3.1 Using Covariant Ellipse to Describe MSER 18 3.1.1 Covariance Matrix 18 3.2 Construction of Local Affine Frames (LAFs) 22 3.2.1 Contour Tracing Algorithm 22 3.2.2 Tangent Points to Polygon 25 3.3 Find the Bi-tangent Points in Arbitrary Polygon 28 3.4 Construction of Local Affine Frames 34 3.4.1 Affine coordinates 36 3.5 Normalization Using Local Affine Coordinates 38 3.5.1 Basis and Coordinates Transformation 39 Chapter 4 Simulation Result 47 4.1 Homography 47 4.2 Repeatability 50 4.2.1 The size of ellipse 52 4.3 Image Databases 53 4.4 Matching Result 54 4.4.1 Viewpoint change 55 4.4.2 Light change 57 4.4.3 JPEG compression 59 4.4.4 Image blur 61 4.4.5 Zoom + rotation 63 4.4.6 Scaling 65 Chapter 5 Conclusion and Future Work 67 REFERENCE 68 | |
| dc.language.iso | en | |
| dc.subject | 最穩定極值區域 | zh_TW |
| dc.subject | 仿射不變特徵 | zh_TW |
| dc.subject | 公切線 | zh_TW |
| dc.subject | 正規化 | zh_TW |
| dc.subject | 共變異矩陣 | zh_TW |
| dc.subject | Bi-tangent line | en |
| dc.subject | Normalization | en |
| dc.subject | Covariance Matrix | en |
| dc.subject | Local Affine Frames (LAF) | en |
| dc.subject | Maximally Stable Extremal Region | en |
| dc.title | 利用仿射不變特徵改進穩定極值區域之比對效能 | zh_TW |
| dc.title | Matching Performance Improvement of Maximally Stable Extremal Region with Local Affine Invariants | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 99-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 鐘國亮,祈忠勇 | |
| dc.subject.keyword | 最穩定極值區域,仿射不變特徵,共變異矩陣,正規化,公切線, | zh_TW |
| dc.subject.keyword | Maximally Stable Extremal Region,Local Affine Frames (LAF),Covariance Matrix,Normalization,Bi-tangent line, | en |
| dc.relation.page | 68 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2011-08-18 | |
| 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-100-1.pdf 未授權公開取用 | 4.93 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。