# 臺灣博碩士論文加值系統

(3.236.110.106) 您好！臺灣時間：2021/07/25 23:17

:::

### 詳目顯示

:

• 被引用:0
• 點閱:183
• 評分:
• 下載:0
• 書目收藏:0
 圖像匹配是圖像處理的基礎組成部分，其作用是用來尋找兩個或兩個以上不同條件下獲得的圖像的匹配點。這些匹配點可以進一步用於一系列應用，例如圖像配準，圖像檢索等。一般來說，一個匹配算法有三個組成部分。第一是特征檢測，這個過程用於尋找一些特殊的點，這些點也被稱為角點，興趣點或特征點。第二是計算描述所選特征的特征描述符。第三是尋找匹配的方法，該方法將會尋找在前面的步驟中發現的特征點之間的匹配。本文將首先介紹一些早於 SIFT 特征檢測的算法，然後詳細介紹了 SIFT 特征檢測以及一些使得 SIFT匹配過程更有效的算法，例如基於 K-D 樹的搜索算法和空間檢測算法。最後基於以上介紹的算法提出了 SIFT 的應用，包括圖像拼接和圖像分類，在介紹 SIFT 應用的同時，也介紹了一些其他用到的算法，例如密集 SIFT 特征，金字塔空間匹配等。
 Image matching is one of the basic tasks in image processing. It is used to find matched points in two or more images captured under different conditions. These matches canbe further used to lots of applications such as image registration, image searching, image retrieving and so on. Generally,one matching algorithm has three components. One is featuredetector which is used to find some points. These points arealso called corner points, interesting points or feature points.The second one is feature descriptor which is used to describethe selected feature. The third part is matching metrics whichshows how to use the features found in previous steps to matchpoints. In this thesis we will first introduce some algorithmsprior to SIFT feature detection algorithm. Then the SIFT feature detector algorithm used in the thesis is introduced in detail. Some matching algorithms is further introduced to makethe SIFT based matching process more robust, such as K-d treebased searching algorithm and some spatial verification algorithm. Finally, some applications based on algorithms introduced above are proposed including image stitching and image classification.
 口試委員會審定書 iii誌謝 v摘要 viiAbstract ix1 Introduction 11.1 Background . . . . . . . . . . . . . . . . . . . . . . . . 11.2 Previous work . . . . . . . . . . . . . . . . . . . . . . 11.2.1 Moravec corner detector . . . . . . . . . . . . 21.2.2 Harris corner detector . . . . . . . . . . . . . . 31.2.3 Shi–Tomasi corner detector . . . . . . . . . . . 51.2.4 SUSAN corner detector . . . . . . . . . . . . . 51.3 Organization . . . . . . . . . . . . . . . . . . . . . . . 62 Scale Invariant Feature Transform 72.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . 72.2 Gaussian function . . . . . . . . . . . . . . . . . . . . 82.3 Detection of scale-space extrema . . . . . . . . . . . . 92.3.1 scale space . . . . . . . . . . . . . . . . . . . . 92.3.2 DoG and LoG . . . . . . . . . . . . . . . . . . 102.3.3 Detection of scale-space extrema . . . . . . . . 122.3.4 Octaves and scale space . . . . . . . . . . . . . 142.4 Accurate keypoint localization . . . . . . . . . . . . . 172.5 Orientation assignment . . . . . . . . . . . . . . . . . . 192.6 Local image descriptor . . . . . . . . . . . . . . . . . . 202.7 Further research . . . . . . . . . . . . . . . . . . . . . 232.7.1 PCA-SIFT and SURF . . . . . . . . . . . . . . 232.7.2 Other related algorithm . . . . . . . . . . . . . 243 Matching Method Based on SIFT 253.1 Basic method . . . . . . . . . . . . . . . . . . . . . . . 253.2 Advanced nearest neighbor algorithm . . . . . . . . . . 253.2.1 K-d tree . . . . . . . . . . . . . . . . . . . . . 263.2.2 Further tree-based NN algorithm . . . . . . . . 303.2.3 LSH . . . . . . . . . . . . . . . . . . . . . . . 313.3 Spatial Verifications . . . . . . . . . . . . . . . . . . . 323.3.1 RANSAC . . . . . . . . . . . . . . . . . . . . 333.3.2 Generalized Hough Transform . . . . . . . . . 343.3.3 Comparison of RANSAC and GHT . . . . . . 384 Applications Based On SIFT Algorithm 394.1 Image stitching . . . . . . . . . . . . . . . . . . . . . . 394.1.1 Introduction . . . . . . . . . . . . . . . . . . . 394.1.2 Image registration . . . . . . . . . . . . . . . . 394.1.3 Image blending . . . . . . . . . . . . . . . . . 414.1.4 Experiment . . . . . . . . . . . . . . . . . . . . 454.2 Image classification . . . . . . . . . . . . . . . . . . . 474.2.1 Introduction . . . . . . . . . . . . . . . . . . . 474.2.2 Bag of visual words . . . . . . . . . . . . . . . 474.2.3 Feature Extraction . . . . . . . . . . . . . . . . 494.2.4 Experiment about picture classification . . . . 524.2.5 Experiment about Chinese character classification 545 Conclusion 595.1 Summary . . . . . . . . . . . . . . . . . . . . . . . . . 595.2 Future work . . . . . . . . . . . . . . . . . . . . . . . . 60Bibliography 61
 [1] A. E. Abdel-Hakim and A. A. Farag. Csift: A sift descriptor withcolor invariant characteristics. In Computer Vision and PatternRecognition, 2006 IEEE Computer Society Conference on, volume 2, pages 1978–1983. IEEE, 2006.[2] A. Andoni and P. Indyk. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In Foundations ofComputer Science, 2006. FOCS’06. 47th Annual IEEE Symposiumon, pages 459–468. IEEE, 2006.[3] D. H. Ballard. Generalizing the hough transform to detect arbitraryshapes. Pattern recognition, 13(2):111–122, 1981.[4] H. Bay, T. Tuytelaars, and L. Van Gool. Surf: Speeded up robust features. In Computer Vision–ECCV 2006, pages 404–417.Springer, 2006.[5] J. S. Beis and D. G. Lowe. Shape indexing using approximatenearest-neighbour search in high-dimensional spaces. In ComputerVision and Pattern Recognition, 1997. Proceedings., 1997 IEEEComputer Society Conference on, pages 1000–1006. IEEE, 1997.[6] M. A. Brown. Multi-image matching using invariant features. PhDthesis, Citeseer, 2005.[7] P. J. Burt and E. H. Adelson. A multiresolution spline with application to image mosaics. ACM Transactions on Graphics (TOG),2(4):217–236, 1983.[8] L. Fei-Fei, R. Fergus, and P. Perona. Learning generative visual models from few training examples: An incremental bayesianapproach tested on 101 object categories. Computer Vision andImage Understanding, 106(1):59–70, 2007.[9] L. Fei-Fei and P. Perona. A bayesian hierarchical model for learning natural scene categories. In Computer Vision and PatternRecognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 2, pages 524–531. IEEE, 2005.[10] M. A. Fischler and R. C. Bolles. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM,24(6):381–395, 1981.[11] K. Grauman and T. Darrell. The pyramid match kernel: Discriminative classification with sets of image features. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on,volume 2, pages 1458–1465. IEEE, 2005.[12] C. Harris and M. Stephens. A combined corner and edge detector.In Alvey vision conference, volume 15, page 50. Manchester, UK,1988.[13] P. V. Hough. Method and means for recognizing complex patterns.Technical report, 1962.[14] L. Juan and O. Gwun. A comparison of sift, pca-sift and surf.International Journal of Image Processing (IJIP), 3(4):143–152,2009.[15] Y. Ke and R. Sukthankar. Pca-sift: A more distinctive representation for local image descriptors. In Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEEComputer Society Conference on, volume 2, pages II–506. IEEE,2004.[16] J. J. Koenderink. The structure of images. Biological cybernetics,50(5):363–370, 1984.[17] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories.In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, volume 2, pages 2169–2178. IEEE,2006.[18] T. Lindeberg. Scale-space theory: A basic tool for analysing structures at different scales. In Journal of applied statistics. Citeseer,1994.[19] D. G. Lowe. Object recognition from local scale-invariant features.In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, volume 2, pages 1150–1157. Ieee, 1999.[20] D. G. Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110,2004.[21] K. Mikolajczyk and C. Schmid. An affine invariant interest pointdetector. In Computer Vision — ECCV 2002, pages 128–142.Springer, 2002.[22] K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. Pattern Analysis and Machine Intelligence, IEEETransactions on, 27(10):1615–1630, 2005.[23] H. P. Moravec. Obstacle avoidance and navigation in the real worldby a seeing robot rover. Technical report, DTIC Document, 1980.[24] J.-M. Morel and G. Yu. Asift: A new framework for fully affineinvariant image comparison. SIAM Journal on Imaging Sciences,2(2):438–469, 2009.[25] M. Muja and D. Lowe. Scalable nearest neighbour algorithms forhigh dimensional data. 2014.[26] M. Muja and D. G. Lowe. Fast approximate nearest neighbors withautomatic algorithm configuration. In VISAPP (1), pages 331–340,2009.[27] J. Shi and C. Tomasi. Good features to track. In Computer Vision and Pattern Recognition, 1994. Proceedings CVPR’94., 1994IEEE Computer Society Conference on, pages 593–600. IEEE,1994.[28] C. Silpa-Anan and R. Hartley. Optimised kd-trees for fast imagedescriptor matching. In Computer Vision and Pattern Recognition,2008. CVPR 2008. IEEE Conference on, pages 1–8. IEEE, 2008.[29] J. Sivic and A. Zisserman. Video google: A text retrieval approachto object matching in videos. In Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, pages 1470–1477.IEEE, 2003.[30] S. M. Smith and J. M. Brady. Susan a new approach to low level image processing. International journal of computer vision,23(1):45–78, 1997.[31] M. J. Swain and D. H. Ballard. Color indexing. Internationaljournal of computer vision, 7(1):11–32, 1991.[32] P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE ComputerSociety Conference on, volume 1, pages I–511. IEEE, 2001.
 國圖紙本論文
 推文當script無法執行時可按︰推文 網路書籤當script無法執行時可按︰網路書籤 推薦當script無法執行時可按︰推薦 評分當script無法執行時可按︰評分 引用網址當script無法執行時可按︰引用網址 轉寄當script無法執行時可按︰轉寄

 1 空照彩色立體像對中人工建築物萃取之研究 2 基於光照條件變化下對影像色彩描述比對方法之評估 3 衛星影像幾何校正控制點自動萃取與匹配之研究 4 點特徵萃取方法於航照影像共軛點匹配之適用性研究 5 以多解析小波轉換為基礎的顯微影像接合系統 6 行走區域標示及危險狀況判別之盲人輔助系統 7 影像特徵點萃取與匹配應用於福衛二號影像幾何糾正 8 階層式區域二元影像圖形及比對應用 9 利用圖形處理器加速影像匹配獲取三維特徵點之研究 10 高效能影像描述法應用於影像比對之研究 11 尺度不變特徵與半色調視訊之安全議題 12 即時的視覺特徵運算之SIFT快速演算法暨硬體設計 13 利用配備GPS感測器之攝影機做戶外場景定位 14 結合靜態辨識與動態資訊之人體姿態辨識

 1 [2] 苗伯霖，「新型高性能超高強建築材料—活性粉混凝土」，營建知訊，162期，pp. 52-60, 1996。 2 [45] 邱宗炫、黃裕文、夏中和“光纖光柵應變感測器之溫度與膠合效應之研究”科儀新知第19卷1期, p21-23, 1997.

 無相關點閱論文

 簡易查詢 | 進階查詢 | 熱門排行 | 我的研究室