Loading...

Rigid Registration using Sparse Representation Descriptor in MR Images

Ebrahim Abdollahian | 2014

1391 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 46069 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Manzuri-Shalmani, Mohammad Taghi
  7. Abstract:
  8. In recent years, sparse representation has had a variety of applications in computer vision such as noise reduction, image reconstruction, classification and dimension reduction. In this project, we aim to provide a method of matching the keypoints obtained from the Scale Invariant feature Transform (SIFT) algorithm. In this algorithm is used descriptor instead of intensity . The proposed method, first, extracts the salient points from the images and learns a dictionary-based descriptors corresponding to the points. Then, using the dictionary, it obtains the sparse coefficients for each salient point by which, it determines the correspondence of the salient points in the two images using SVD decomposition,then, it applies it on the proximity matrix, at the end rigid registration is done with corresponding points. Experimental results in data sets containing noise or changes in illumination demonstrates improvement in SIFT algorithm and this method in average improved precise of matching, 12 percent in noise condition and 1.3 percent in change of illumination and also in average decreased error of registration, 18 percent in noise condition and 1.4 in change of illumination
  9. Keywords:
  10. Sparse Representation ; Descriptor ; Denoising ; Image Registration ; Scale Invariant Feature Transform (SIFT)Algorithm

 Digital Object List

 Bookmark

...see more