基于廣義特征點(diǎn)匹配的全自動(dòng)圖像配準(zhǔn)
Automatic Image Registration Based on Matching of Feature Points in Broad Sense
-
摘要: 該文針對(duì)圖像配準(zhǔn)中用到的特征點(diǎn)提出了狹義特征點(diǎn)和廣義特征點(diǎn)兩個(gè)范疇。廣義特征點(diǎn)是針對(duì)區(qū)域特征定義的, 可以有各種不同的定義方法。該文建議了一種廣義特征點(diǎn)的定義和自動(dòng)提取算法。該算法以多尺度小波變換來定位圖像中的強(qiáng)棱邊點(diǎn),以局部區(qū)域的復(fù)雜性和非周期性約束最終檢測(cè)廣義特征點(diǎn)。該文采用兩個(gè)步驟建立廣義特征點(diǎn)之間的對(duì)應(yīng)關(guān)系。正確匹配的特征點(diǎn)對(duì)作為控制點(diǎn),以最小化控制點(diǎn)處的均方根誤差方法求得用于配準(zhǔn)圖像的仿射變換參數(shù)。用一個(gè)迭代機(jī)制進(jìn)一步修正控制點(diǎn)的位置,從而達(dá)到最佳的配準(zhǔn)精度。多種實(shí)驗(yàn)結(jié)果展示了該文方法的配準(zhǔn)效果。
-
關(guān)鍵詞:
- 圖像配準(zhǔn); 特征點(diǎn); 匹配準(zhǔn)則
Abstract: Feature points in images are commonly used for image registration. Feature points can be classified as in narrow sense and in broad sense. Feature Points in Broad Sense (FPBS) can be defined in different ways. A new definition of FPBS is proposed that is reasonable for image registration. The FPBS can be detected automatically by the use of multi-scale wavelet transform and a few additional restrictions that control the complexity and nonperiodicity of local regions. After feature point sets are extracted separately from the two images under consideration, the relation between them is then established by a two-stage matching algorithm. The registration transform is found by minimizing the Root Mean Square Error (RMSE) of the control points. An iterative optimization mechanism is used to refine the registration. Several experimental results of image registration can illustrate the performance of the method. -
Mehrotra R, Nichani S. Corner detection[J].Pattern Recognition.1990, 23(11):1223-[2]Liu S T, Tsai W H. Moment-preserving comer detection[J].Pattern Recognition.1990, 23(5):441-[3]Lee J S, Sun Y N, Chen C H, Tsai C T. Wavelet based comer detection[J].Pattern Recognition.1993, 26(6):853-[4]Rohr K. Localization properties of direct corner detectors[J].Journal of Mathematical Imaging and Vision.1994, 4(2):139-[5]Goshtasby A, Stockman G C, Page C V. A region-based approach to digital image registration with subpixel accuracy[J].IEEE Trans.on Geoscience andRemote Sensing.1986, 24(15):390-[6]Flusser J, Suk T. A moment-based approach to registration of images with affine geometric distortion[J].IEEE Trans. on Geoscience andRemote Sensing.1994, 32(2):382-[7]Holm M. Towards automatic rectification of satellite images using feature based matching. Proc. Intl. Geoscience and Remote Sensing Symposium IGARSS91, Espoo, Finland, 1991:2439-2442.[8]Mallat S, et al.. Singularity detection and processing with wavelets, IEEE Trans[J].on Information Theory.1992, 38(2):617-[9]Mallat S, et al.. Characterization of signals from multiscale edges[J].IEEE Trans. on Pattern Analysis and Machine Intelligence.1992,14(7):710-[10]王東峰,鄒謀炎.基于最大化對(duì)齊度的多模態(tài)圖像自動(dòng)配準(zhǔn)[J].電子與信息學(xué)報(bào).2003,25(6):755-762瀏覽 -
計(jì)量
- 文章訪問數(shù): 2625
- HTML全文瀏覽量: 84
- PDF下載量: 983
- 被引次數(shù): 0
下載:
