Convolutional sparse coding-based image decomposition

He Zhang, Vishal M. Patel

Research output: Contribution to conferencePaperpeer-review

20 Scopus citations


We propose a novel sparsity-based method for cartoon and texture decomposition based on Convolutional Sparse Coding (CSC). Our method first learns a set of generic filters that can sparsely represent cartoon and texture type images. Then using these learned filters, we propose a sparsity-based optimization framework to decompose a given image into cartoon and texture components. By working directly on the whole image, the proposed image separation algorithm does not need to divide the image into overlapping patches for leaning local dictionaries. Extensive experiments show that the proposed method performs favorably compared to state-of-the-art image separation methods.

Original languageEnglish (US)
StatePublished - 2016
Event27th British Machine Vision Conference, BMVC 2016 - York, United Kingdom
Duration: Sep 19 2016Sep 22 2016


Other27th British Machine Vision Conference, BMVC 2016
Country/TerritoryUnited Kingdom

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Convolutional sparse coding-based image decomposition'. Together they form a unique fingerprint.

Cite this