Thesis

 

Links

Home

Publications

Gallery

 

 

 

Sparse Grouping and Invariant Representations for Estimation and Recognition

 

Guoshen Yu

 

Doctoral thesis

 

Ecole Polytechnique

Defended on June 30, 2009

 

Abstract: This thesis develops several contributions for signal and image processing as well as for computer vision. The first part includes a new audio denoising algorithm and a super-resolution algorithm for image zooming. These algorithms are based on some new sparse representations by blocks. A time-frequency block thresholding procedure is introduced for the audio denoising, which enables noise reduction without introducing artifacts, with the results superior to the state-of-the-art. This first part also develops a general approach to solve inverse problems with some piecewise linear sparser representations over the blocks. The application to the image super-resolution allows obtaining a fast algorithm, which clearly improves the PSNR relatively to the existing algorithms.

The second part of the thesis introduces an algorithm (ASIFT) of establishing correspondences between images, which is invariant to affine transforms. It is demonstrated that this algorithm satisfies the invariance constraints and it is able to make correspondences between objects observed under arbitrary angles. Its numeric complexity is of the same order as the most efficient algorithms, with a significantly higher robustness thanks to its affine invariance.

The third part of the thesis introduces a biologically plausible implementation of visual grouping. Inspired by the mechanism of neural synchronization in perceptual grouping, a general algorithm based on neural oscillators is proposed to make visual grouping. The same algorithm is shown to achieve promising results on several classical visual grouping problems, including point clustering, contour integration, and image segmentation.

 

 

Jury:

 
Emmanuel Bacry      Examiner, Ecole Polytechnique, France
Michael Elad      Reviewer, Technion, Israel
Henri Maître      Examiner, Telecom ParisTech, France
St└phane Mallat      Advisor, Ecole Polytechnique, France
Jean-Michel Morel      Examiner, ENS Cachan, France
Jean Ponce      Reviewer, ENS, France
Guillermo Sapiro      Examiner, University of Minnesota, USA
Jean-Jacques Slotine      Examiner, MIT, USA

 

Download (pdf, 7MB)