Automatic feature based image registration using SIFT algorithm

Image registration is the process of mapping and geometrically aligning the two or more images. The steps in image registrations include: feature detection, feature matching and image transformation, and resampling. The accuracy of a registration process is highly dependent on the feature detection and matching. In this paper, we use a SIFT (Scale Invariant Feature Transform) algorithm to detect features, which is invariant to rotation, scaling and noise. Then initial matching is computed using Euclidean distance, and mismatch features between point pairs are eliminated using RANSAC. The result shows that the automatic registration algorithm is correct and effective.

[1]  Emanuele Trucco,et al.  Geometric Invariance in Computer Vision , 1995 .

[2]  Peijun Du,et al.  Image registration based on corner detection and affine transformation , 2010, 2010 3rd International Congress on Image and Signal Processing.

[3]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[4]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[5]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[6]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Matthew A. Brown,et al.  Invariant Features from Interest Point Groups , 2002, BMVC.

[8]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[9]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[11]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.