This Matlab library provides functions for the development of adaptive algorithms (primarily exemplar-based) for image restoration problems, such as denoising, deconvolution, superresolution, and inpainting. The current version provides functions for block-based processing of an image, and a demo script which utilizes these functions as part of a denoising algorithm. The aairpath function should be called to set up paths correctly before attempting to use the demo scripts.

Some library functionality and demonstration scripts in the demo directory depend on third-party software and data. Before using this library, please use the getcode.sh and getdata.sh scripts to download and install this software and test data respectively.

Please note: This release of the library has limited functionality, consisting primarily of the exemplar-based inpainting method reported at ICASSP 2009 (see directory demo/icassp2009) and published in IEEE Signal Processing Letters (see directory demo/spl2011):

• Brendt Wohlberg, "Inpainting with Sparse Linear Combinations of Exemplars", in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), (Taipei, Taiwan), pp. 689--692, Apr 2009
• Brendt Wohlberg, "Inpainting by Joint Optimization of Linear Combinations of Exemplars", IEEE Signal Processing Letters, vol. 18, no. 1, pp. 75--78, Jan 2011

Bug reports, comments, etc. are appreciated.

License

This library was developed at Los Alamos National Laboratory, and has been approved for public release under the approval number LA-CC-08-056. It is made available under the terms of the BSD License, full details of which may be found in the LICENSE file in the distribution.

Download

Download aair-0.02.1.tar.gz (gzipped tar file, 4M)