(54.80.183.100) 您好!臺灣時間:2018/05/24 07:58
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
本論文永久網址: 
line
研究生:李政道
論文名稱:特徵匹配於影像起始套合應用之研究
論文名稱(外文):Initialization for Image Registration Using Feature-Based Matching
指導教授:陳良健
指導教授(外文):Chen, L.C
學位類別:碩士
校院名稱:國立中央大學
系所名稱:土木工程研究所
學門:工程學門
學類:土木工程學類
論文出版年:1999
畢業學年度:87
語文別:中文
論文頁數:94
中文關鍵詞:不變的矩傅立葉描述子形狀矩陣特徵匹配套合影像參考影像
外文關鍵詞:Invariant MomentsFourier DescriptorsShape MatrixFeature-Based MatchingSensed ImageReference Image
相關次數:
  • 被引用被引用:11
  • 點閱點閱:490
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
本研究嘗試利用影像之區塊特徵,藉由各種區塊形狀之描述子,輔以特徵相似性的評估,進行特徵匹配,透過匹配之區塊自動化建立影像間的起始對應關係。一般自影像中萃取出來的區塊其輪廓為高低頻互見,且在自動化考量中高低頻之出現是無法預見的。因此;假設我們所萃取出的區塊包含上述兩種區塊形狀;且同時出現時,我們必須能有效率且迅速正確對於較高頻或低頻的形狀來描述,並且找出能同時考慮互補的形狀描述子。我們在此提出,利用不變的矩(Invariant Moments)、傅立葉描述子(Fourier Descriptors) 和形狀矩陣(Shape Matrix)作為描述元,並以此三者做為判斷相似性之指標,同時使用三種特徵描述的方法描述其形狀之相似性,並建立相似係數矩陣同時測試三個描述子對於不同區塊特徵所反映出之特性。
建立相似係數矩陣後,再藉由一對應篩選法則濾除特徵匹配中錯誤之對應。再由這些正確的對應區塊,以其重心位置為套合控制點,進行起始轉換係數求解,可找出並建立套合影像與參考影像間起始的相對坐標轉換關係。以此為出發點,可提供進一步套合控制點加密時,匹配位置之預估資訊。
This investigation uses feature matching which includes feature extraction , region descriptor and similarity assessment to initialize the correspondence for image registration. Shapes of the extracted regions appear to be in high frequency and low frequency in terms of irregularity. This irregularity ,in general ,is not predictable in the feature extraction stage Thus ,we consider both possibility and then strive to investigate the suitable matching strategy. We propose three descriptors to characterize the region shapes , namely invariant moments , Fourier descriptors ,and shape matrix.
According to the matching matrix designed in this study, we screen out the erroneous correspondence. Then for these determined conjugate regions, centroids are used as registration control point in the initial stage. Following a coordinate transformation as prediction , fine matching is applied to generate final registration control point pairs.
第一章 緒論
1.1研究動機與目的
1.2文獻回顧
1.2.1區域匹配
1.2.2特徵匹配
1.2.2.1特徵萃取
1.2.2.2特徵描述
1.2.2.3特徵匹配
1.3研究內容與文章架構
第二章 特徵萃取
2.1影像之前處理
2.1.1影像平滑
2.2紋理分析
2.3邊緣強度計算
2.4區塊萃取之整合
第三章 特徵的描述
3.1轉換參數化特徵描述元
3.1.1傅立葉描述子的原理
3.1.2傅立葉描述子之特性
3.2不變的矩
3.2.1不變的矩原理
3.2.2不變的矩之特性
3.3視覺化特徵描述元
3.3.1形狀矩陣的原理
3.3.3形狀矩陣之特性
第四章 相似性評估
4.1傅立葉描述子與不變的矩相似性評估
4.1.1傅立葉描述子之相似性評估
4.1.2不變的矩之相似性評估
4.2形狀矩陣之相似性評估
4.3相似性指標之組合
4.3綜合性討論
第五章 特徵匹配
5.1對應區塊的建立
5.2交集對應候選
5.3套合流程
第六章 實驗結果與分析
6.1 SPOT衛星影像套合
6.1.1測試影像資料介紹
6.1.2 特徵萃取
6.1.3 特徵區塊與編碼
6.1.4特徵匹配成果
6.1.5起始對應關係
6.1.6套合控制點的產生
6.1.7匹配點位檢核與精度評估
6.2空載多譜掃描儀影像與航空照片套合
6.2.1測試影像資料介紹
6.2.2特徵萃取
6.2.3特徵區塊與編碼
6.2.4特徵匹配成果
6.2.5起始對應關係
6.2.6套合控制點的產生
6.2.7匹配點位檢核與精度評估
第七章 結論與建議
李良輝,1991『計算視覺方法於SPOT衛星影像之幾何性分析』,博士論文,國立中央大學大氣物理研究所
黃智仁,1998『影像特徵萃取與立體匹配之結合於人工建物偵測之研究』,碩士論文,國立中央大學土木工程研究所
胡征懷,1992『以區塊匹配自動產生DEM資料及地表變遷偵測』,碩士論文,國立成功大學測量工程研究所
陳晉徹,1993『自動化數值影像索引鑲崁之研究』,碩士論文,國立成功大學測量工程研究所
湯凱佩,1997『匹配面圖元進行相對方位自動化之研究』,碩士論文,國立成功大學測量工程研究所
張宇洲,1993.『農田區域自動產生DEM資料之研究』,碩士論文,國立成功大學測量工程研究所
叢蕙滋,1997『特徵匹配與影像套合之應用』碩士論文,國立中央大學土木工程研究所
[Ackermann, 1984]Ackermann, F., 1984. Disital Image Correlation : Performance and Potential Application in Photogrammetry. Photogrammetric Record,11(64):429-439.
[Ballard and Brown, 1982]Ballard, D.h., and C.M., Brown, 1982. Computer Vision, Prenticehall, Englewood Cliffs, New Jersey.
[Canny, 1986]Canny, J.F., 1986. A computational approach to edge detection, IEEE Trans. On Pattern Anal. And Machine Intel., 8(6):679-698.
[Chandra, 1992]Chandra, D.V.S., 1992. Fast registration of multi-spectral image using orthogonal transform features, Proceedings of 35th Midwest Symposium on Circuits and systems, Washington, D.C., 1:703-706.
[Chen and Rau, 1993]Chen, L. C., and Rau, I.Y., 1993. “Geometric Correction of Airborne Scanner Imagery Using Orthophotos and Triangulated Feature Points”, International Journal of Remote Sensing. Vol.14. No.16. pp.3041-3059.
[Chen and Lee, 1992]Chen, L.C., and Lee, L.H., 1992. “Progressive Generation of Control Frameworks for Image Registration”, Photogrammetric Engineering and Remote Sensing, Vol.58, No.9. pp.1321-1328.
[Chui, 1992]Chui, C., 1992. An Introduction to Wavelets, (C. Chui, editor), Academic Press, New York.
[Cideciyan, Jacobson, Kemp, Knighton, and Nagel, 1992]Cideciyan, A.V., S.G. Jacobson, C.M. Kemp, R.W. Knighton, and J.H. Nagel, 1992. Registration of high resolution images of the retina, Proceedings of the SPIE-the International Society for Optical Engineering, Medical Imaging VI:Image Processing, 1652:310-322
[Huang, 1996]Dai-Hwa Huang, 1996 “Similar Shape Retrieval in Content-Based Image Retrieval System” Electrical Engineering Department National Tsing-Hua University
[Djamdji, Bijaoui and Maniere, 1993]Djamdji, J.P., A. Bijaoui, and R. Maniere, 1993. Geometrical registration of images: the multiresolution approach, PE&RS, 59(5):645-653.
[Flusser, 1992]Flusser, J., 1992. Invariant shape description and measure of object similarity. Proc. 4th Internat. Conf. Image Processing, Maastricht, The Netherlands, pp.139-142.
[Flusser and Suk, 1994]Flusser, J., and T. Suk, 1994. A momnet-based approach to registration of images with affine geometric distortion, IEEE Trans. On Geoscience and Remote Sensing, 32(2):382-387.
[Flusser, 1995]Flusser, J.,1995. Object matching by means of matching likelihood coefficients, Pattern Recognition Letters, vol 16, pp.893-900.
[Fonseca and Manjunath, 1996]Fonseca, L. M. G. and Manjunath, B. S., 1996. Registration Techniques for Multisensor Remotely Sensed Imagery. PE&RS, vol. 62, No. 9, September, pp1049-1056.
[Forstner and Guelch, 1987]Forstner, W., and Guelch, E., “A Fast Operator for Detection and Precise Location of Distinct Points, Corner and Centres of Circular Features”, ISPRS Intercommission Workshop, pp281-305, Interlaken, Switzerland, June, 1987.
[Gonzalez and Woods,1992] Digital Image Processing, Addison-Wesley Pub. Co., New York, 1992.
[Goshtasby, 1988]Goshtasby, A., 1988. Registration of Images with geometric distortions, IEEE Trans. On Geoscience and Remote Sensing, 26(1):60-64.
[Goshtasby and Stockman, 1985]Goshtasby, A., G.C. Stockman, 1985. Point pattern matching using convex hull edges, IEEE Trans. Syst. Man Cybernetics, 15(5):631-637.
[Goshtasby, Stocjman and Page, 1986]Goshtasby, A., G.C. Stocjman, and C.V. Page, 1986. A region-based approach to digital image registration with subpixel accuracy, IEEE Trans. On Geoscience and Remote Sensing, 24(3):390-399.
[Haralick and Shapiro, 1985]Haralick, R.M. and G.C. Stockman, 1985. Image segmentation techniques. Computer Vision, Graphics, abd Image Processing 29, pp.100-132.
[Hong, 1991]Hong, Z.Q., 1991. Algebraic feature extraction of image for recognition. Pattern Recognition 24, pp.211-219.
[Hu, 1962]Hu, M.K., 1962. Visual pattern recognition by moment invariants. IRE Trans. Inform. Theory 8, pp.179-187.
[Kiryati, 1988]Kiryati, N., 1988. Calculating geometric properties of objects represented by Fourier coefficients. Proc. CVPR ’88, Ann Arbor, MI, pp.641-646.
[Kher and Mitra, 1993]Kher, A., and S. Mitra, 1993. Registration of noisy SAR imagery using Morphological feature extractor and 2-d cepstrum, Proceedings of the SPIE- The International Society for Optical Engineering, Applications of Digital Image Processing XV, San Diego, California, 1771:281-291.
[Kuncheva, 1988]Kuncheva, R.A., 1988. Pattern recognition method using two-dimensional Hadamard transform. Proc, 7th Internat Conf. On Robot Vision Sensory Controls, Zurich, Switzerland, pp.231-236.
[Lin and Chellappa, 1987]Lin, C.C. and R. Chellappa, 1987. Classification of partial 2-D shapes using Fourier descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 9, pp.686-690.
[Le Moigen, 1994]Le Moigen, J., 1994. Parallel registration of multi-sensor remotely sensed imagery using wavelet coefficients, Proceedings of the SPIE- The International Society for Optical Engineering, Orlando, Florida, 2242:432-443.
[Lue, Y., 1988]Interest Operator and Fast Implementation, International Archives of Photogrammetry and Remote Sensing, Vol. 27-II,XVI ISPRS congress ,Kyoto, Japan, pp.491-500。
[Mallat, 1989]Mallat, S.G., 1989. Multifrequency channel decom-positions of images and wavelet models, IEEE Trans. On Acoustics, Speech, and Signal Processing, 37(12):2091-2110.
[Marr and Hildreth, 1980]Marr, D., and E. Hildreth, 1980. Theory of edge detection. Proceedings of Royal Society of London, B207:187-217.
[Peli, 1981]Peli, T., 1981. An algorithm for recognition and localization of rotated and scaled objects. Proc. IEEE 69, pp.483-485.
[Ranade and Rosenfeld, 1980]Ranade, S. and A. Rosenfeld , 1980. Point pattern matching by relaxation. Pattern Recognition 12, pp.269-275.
[Reiss, 1993]Reiss, T.H. 1993. Recognizing planar objects using invariant image features. Lecture Notes in computer Science 676. Springer, Berlin.
[Rignot, R.Kowk, Curlander and Pang, 1991]Rignot, E.J.M., R.Kowk, J.c. Curlander, and S.S. Pang, 1991. “Automated multisensor registration: Requir-ements and techniques”, PE&RS, 57(8):1029-1038.
[Rosenholm, 1985] Rosenholm, D., 1985, “Digital Matching of simulated SPOT Images”, Fotogrammetriska Meddelanden, Royal Institute of Technology, Sween, 58 pages.
[Tseng and Schenk 1992]Tseng,Y.H. and Schenk T.,1992. “A Least Squares Approach to Matching Lines with Fourier Descriptors”, International Archives of Photogrammetry and Remote Sensing,Vol.29,Part B2, Commission III,pp469-475
[Tseng,Tzen,Tang and Lin 1997]“Image-to-Image Registration by Matching Area Features Using Fourier Descriptors and Neural Networks”, PE&RS.
[Ton and Jain, 1989]Ton, J., and A.K. Jain, 1989. Registration Landsat images by point matching, IEEE Trans. On Geoscience and Remote Sensing, 27(5):642-651.
[Toth and Schenk, 1992]Toth, C.K., and T. Schenk, 1992. Feature-based matching for automatic image registration, ITC Journal, (1):40-46.
[Weiss, 1988]Weiss, I., 1988. Projective invariants of shapes. Proc. DARPA Image understanding Workshop, Cambridge, MA, pp.1125-1134.
[Werner, H.,1988]Automatic Gross Error Detection by Robst Estimators,ISPRS Congress,Commission III,Rio,de Janeiro,pp.197-219.
[William, K. Pratt]William, K. Pratt. 1991. Digital Image Processing. 2nd Ed.
[Zheng, and Chellappa, 1993]Zheng, Q., and R. Chellappa, 1993. A computational vision approach to image registration, IEEE Transactions on Image Processing, 2(3):311-326.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔