Software and tools

From ENFSI Monopoly Programme 2011: Project S-FIVE
Jump to: navigation, search



Contents


Items highlighted in red are still being investigated by the S-FIVE Project Team; please feel free to send in any updates or comments you may have.


Commercial FIVE hardware and software tools

This section provides an overview of the commercial tools that are most often cited when considering a Forensic Image and Video Enhancement workflow.

The companies or tools have been ordered alphabetically; i.e.:
The project team does not wish to promote nor endorse any specific (selection of the) tools listed here. Hence:

You are kindly invited to provide any additional links and references, or any other feedback that you may have (see "Contact Us" page).

Vendors that would wish to provide (additional) information may request to have one or two links included on this page. They are kindly requested to contact the project-team (see "Contact Us" page).


Tools with source code ("free" and "non-free")

For information about the references cited below, see the Scientific literature page.

  • Virtual Dub http://www.virtualdub.org/
  • excellent overview of reproducible research and data: http://reproducibleresearch.net/index.php/Super-resolution
  • matlab/c/MEX code for [Takeda:2009]. http://www.ece.lsu.edu/ipl/Software.html : see also [Gunturk:2004], [Gunturk:2005], and [Gunturk:2007]
    This method is also cited by the commercial Amped software package in its reporting facility.
    The tool includes:
    • Super-Resolution GUI: This is a super-resolution image restoration software developed in C. It includes an affine motion estimation module and a maximum a posteriori (MAP) image restoration module. The software uses the CImg C++ image processing library and the ImageMagick package.
    • Denoising: This is a Matlab implementation of the multi-resolution bilateral filter based image denoising algorithm.
    • Demosaicking: this is a Matlab implementation of the alternating projections demosaicking algorithm
  • Non-uniform Deblurring for Shaken Images: http://www.di.ens.fr/willow/research/deblurring/ ; see [Whyte:2010][Whyte:2011]
  • Robust And Fast Super Resolution http://www1.idc.ac.il/toky/videoproc-07/projects/superres/srproject.html ; it refers to/is mentioned as being based on [Farsiu:2003]
  • Elle Super-resolution code: http://www.robots.ox.ac.uk/~elle/SRcode/index.html. This code is based on [Pickup:2008]
  • EPFL Super-resolution tool: http://lcav.epfl.ch/software/superresolution/index.html ; Super-Resolution is a Matlab program with graphical user interface that implements several image registration and reconstruction algorithms for super-resolution imaging.
  • deblurring: http://ai.stanford.edu/~schuon/deblur.htm; this website mentions the following existing deblurring methods: Wiener Filter deconvwnr (IPT) , Regularized Filter deconvreg (IPT), Richardson-Lucy Deconvolution deconvlucy (IPT), Maximum Likelihood Estimation de-convblind (IPT), TU Berlin deconv_tuberlin, Sondhi deconv_sondhi, Advanced Landweber de-conv_alm; IPT is the Image Processing Toolbox by Mathworks. The last three algorithms are available for download.
  • Forevid http://sourceforge.net/projects/forevid/ (the main website http://www.forevid.org/ seems to have become unavailable) is "the world’s first free, open-source software for the forensic analysis of surveillance videos". It contains various (basic) filters; the main developer was a former member of the ENFSI DIWG group (Hi!)
  • Refocus-it: http://refocus-it.sourceforge.net/; deblur tool for GIMP http://www.gimp.org/; general OSS photo editing tool
  • a Matlab-based software package for resolution enhancement from video, developed at the Multi-Dimensional Signal Processing (MDSP) research lab at the University of California at Santa Cruz. The main objective of this software tool is the implementation of several superresolution techniques; http://users.soe.ucsc.edu/~milanfar/software/superresolution.html.
    This software is based on or related to: [Farsiu:2003], [Farsiu:2004], [Farsiu:2006]. Three software patents seem to cover these methods.
  • (link suggested by ZG): Matlab based super-resolution software and manual; http://decsai.ugr.es/pi/superresolution/software.html ; it implements:
    • S. Villena, M. Vega, D. Babacan, R. Molina, and A. Katsaggelos. "Bayesian combination of sparse and non sparse priors in image superresolution,"Digital Signal Processing, vol. 23, no. 2, 530-541, 2013.
    • S. Villena, M. Vega, R. Molina, and A. K. Katsaggelos, "Bayesian super-resolution image reconstruction using an l1 prior," in 6th International Symposium on Image and Signal Processing and Analysis (ISPA 2009) Best paper award, Image Processing and Analysis Track, 2009, pp. 152-157.
    • S. Villena, M. Vega, D. Babacan, R. Molina, and A. Katsaggelos. Using the Kullback-Leibler divergence to combine image priors in super-resolution image reconstruction. In IEEE International Conference on Image Processing, pages 809-812. Hong-Kong (China), September 2010.
    • S. D. Babacan, R. Molina, and A.K. Katsaggelos. Variational Bayesian super resolution. IEEE Transactions on Image Processing, 20(4):984-999, 2011.
    • and other common SR methods.
  • http://www.videocleaner.com/ all source code, along with their respective GPL license are in "Complete plugin zip folder.7z" located in the support folder of C:\VideoCleaner (updated post EAFS2015, source: e-mail DG).
  • ffmpeg: http://ffmpeg.org/ a complete, cross-platform solution to record, convert and stream audio and video


"Free trial" or "research only" executable tools


Back to the Central Repository page

Personal tools
Namespaces

Variants
Actions