International Journal of Computer Vision

, Volume 114, Issue 2–3, pp 137–167

Structured Overcomplete Sparsifying Transform Learning with Convergence Guarantees and Applications


DOI: 10.1007/s11263-014-0761-1

Cite this article as:
Wen, B., Ravishankar, S. & Bresler, Y. Int J Comput Vis (2015) 114: 137. doi:10.1007/s11263-014-0761-1


In recent years, sparse signal modeling, especially using the synthesis model has been popular. Sparse coding in the synthesis model is however, NP-hard. Recently, interest has turned to the sparsifying transform model, for which sparse coding is cheap. However, natural images typically contain diverse textures that cannot be sparsified well by a single transform. Hence, in this work, we propose a union of sparsifying transforms model. Sparse coding in this model reduces to a form of clustering. The proposed model is also equivalent to a structured overcomplete sparsifying transform model with block cosparsity, dubbed OCTOBOS. The alternating algorithm introduced for learning such transforms involves simple closed-form solutions. A theoretical analysis provides a convergence guarantee for this algorithm. It is shown to be globally convergent to the set of partial minimizers of the non-convex learning problem. We also show that under certain conditions, the algorithm converges to the set of stationary points of the overall objective. When applied to images, the algorithm learns a collection of well-conditioned square transforms, and a good clustering of patches or textures. The resulting sparse representations for the images are much better than those obtained with a single learned transform, or with analytical transforms. We show the promising performance of the proposed approach in image denoising, which compares quite favorably with approaches involving a single learned square transform or an overcomplete synthesis dictionary, or gaussian mixture models. The proposed denoising method is also faster than the synthesis dictionary based approach.


Sparsifying transform learning Dictionary learning  Convergence guarantees Overcomplete representation Clustering Image representation Sparse representation Image denoising Machine learning 

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Bihan Wen
    • 1
  • Saiprasad Ravishankar
    • 1
  • Yoram Bresler
    • 1
  1. 1.Department of Electrical and Computer Engineering and the Coordinated Science LaboratoryUniversity of IllinoisUrbana-ChampaignUSA

Personalised recommendations