|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images
Nov. 2012 (vol. 34 no. 11)
pp. 2233-2246
| ASCII Text | x | ||
| Yigang Peng, A. Ganesh, J. Wright, Wenli Xu, Yi Ma, "RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2233-2246, Nov., 2012. | |||
| BibTex | x | ||
| @article{ 10.1109/TPAMI.2011.282, author = { Yigang Peng and A. Ganesh and J. Wright and Wenli Xu and Yi Ma}, title = {RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {34}, number = {11}, issn = {0162-8828}, year = {2012}, pages = {2233-2246}, doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2011.282}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Pattern Analysis and Machine Intelligence TI - RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images IS - 11 SN - 0162-8828 SP2233 EP2246 EPD - 2233-2246 A1 - Yigang Peng, A1 - A. Ganesh, A1 - J. Wright, A1 - Wenli Xu, A1 - Yi Ma, PY - 2012 KW - sparse matrices KW - computer vision KW - convex programming KW - correlation methods KW - convex optimization techniques KW - RASL KW - robust alignment by sparse and low-rank decomposition KW - linearly correlated images KW - gross corruption KW - image domain transformations KW - transformed image matrix KW - error sparse matrix KW - recovered aligned image low-rank matrix KW - convex programs KW - ℓ<sup>1</sup>-norm KW - nuclear norm KW - component matrices KW - Robustness KW - Minimization KW - Algorithm design and analysis KW - Lighting KW - Optimization KW - Sparse matrices KW - Educational institutions KW - occlusion and corruption KW - Batch image alignment KW - low-rank matrix KW - sparse errors KW - robust principal component analysis VL - 34 JA - IEEE Transactions on Pattern Analysis and Machine Intelligence ER - | |||
This paper studies the problem of simultaneously aligning a batch of linearly correlated images despite gross corruption (such as occlusion). Our method seeks an optimal set of image domain transformations such that the matrix of transformed images can be decomposed as the sum of a sparse matrix of errors and a low-rank matrix of recovered aligned images. We reduce this extremely challenging optimization problem to a sequence of convex programs that minimize the sum of ℓ1-norm and nuclear norm of the two component matrices, which can be efficiently solved by scalable convex optimization techniques. We verify the efficacy of the proposed robust alignment algorithm with extensive experiments on both controlled and uncontrolled real data, demonstrating higher accuracy and efficiency than existing methods over a wide range of realistic misalignments and corruptions.
Index Terms:
sparse matrices,computer vision,convex programming,correlation methods,convex optimization techniques,RASL,robust alignment by sparse and low-rank decomposition,linearly correlated images,gross corruption,image domain transformations,transformed image matrix,error sparse matrix,recovered aligned image low-rank matrix,convex programs,ℓ<sup>1</sup>-norm,nuclear norm,component matrices,Robustness,Minimization,Algorithm design and analysis,Lighting,Optimization,Sparse matrices,Educational institutions,occlusion and corruption,Batch image alignment,low-rank matrix,sparse errors,robust principal component analysis
Citation:
Yigang Peng, A. Ganesh, J. Wright, Wenli Xu, Yi Ma, "RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2233-2246, Nov. 2012, doi:10.1109/TPAMI.2011.282
Usage of this product signifies your acceptance of the Terms of Use.