Super resolution based on scale invariant feature transform

In this paper, SIFT (scale invariant feature transform) algorithm is used for the image registration of super resolution to ensure a more stable and accurate registration result, and thus improve the result of super-resolution which will be realized by least squares minimization. The advantage of this approach is that the super-resolution process will have a stable result even under severe transformation conditions. SIFT method is compared with Kerenpsilas method to prove its accuracy and robustness. Fine reconstruction results are also given to show the effectiveness of this approach. Simultaneous registration method can be introduced in future work to further improve the registration accuracy.

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

[2]  Manjunath V. Joshi,et al.  A learning-based method for image super-resolution from zoomed observations , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[4]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[5]  Jianya Gong,et al.  POCS Super-Resolution Sequence Image Reconstruction Based on Improvement Approach of Keren Registration Method , 2006, Sixth International Conference on Intelligent Systems Design and Applications.

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

[7]  B. S. Manjunath,et al.  A contour-based approach to multisensor image registration , 1995, IEEE Trans. Image Process..

[8]  Shmuel Peleg,et al.  Image sequence enhancement using sub-pixel displacements , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

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

[10]  Russell C. Hardie,et al.  Joint MAP registration and high-resolution image estimation using a sequence of undersampled images , 1997, IEEE Trans. Image Process..

[11]  Stephen J. Roberts,et al.  Overcoming Registration Uncertainty in Image Super-Resolution: Maximize or Marginalize? , 2007, EURASIP J. Adv. Signal Process..