RWTH W2D - The RWTH Aachen Two-Dimensional Image Warping Software
RWTH W2D is a software package for two-dimensional image warping for
recognition. It has been developed by the Human Language Technology
and Pattern Recognition Group at the RWTH Aachen University. OCR,
image retrieval, and face recognition systems developed using this
framework have been applied successfully in several international
research projects and corresponding evaluations.
Different pixel deformation models are included:
- Zero-Order Warping (ZOW)
- Pseudo 2D Warping (P2DW)
- Pseudo 2D Warping with First-Order Strip Extension (P2DW-FOSE)
- Tree Serial Dynamic Programming (TSDP)
- Two-Level Dynamic Programming (2LDP)
- Image dependent warprange with Sliding-Window Zero Order Warping (SW-ZOW)
RWTH W2D is free software; it can be redistributed and/or modified under
the terms of the RWTH W2D License.
This license includes free usage for non-commercial purposes as long as
any changes made to the original software are published under the terms
of the same license. Other licenses can be requested.
Users must cite the authors of the Software upon publication of
results obtained through the use of original or modified versions
of the Software by refering to the following publication:
T. Gass, L. Pishchulin, P. Dreuw, and H. Ney: "Warp that Smile on your Face: Optimal and Smooth Deformations for Face Recognition". In IEEE International Conference Automatic Face and Gesture Recognition (FG), Santa Barbara, CA, USA, March 2011.
For usage of the Two-Level Dynamic Programming algorithm refer to:
H. Hanselmann, H. Ney, and P. Dreuw: "Pose-invariant Face Recognition with a Two-Level Dynamic Programming algorithm". In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), Madeira, Portugal, June 2013.
To download the W2D demo system, please fill out the form below. We will send you an email about how to proceed with the download.
L. Pishchulin, T. Gass, P. Dreuw, and H. Ney. The Fast and the Flexible: Extended Pseudo Two-Dimensional Warping for Face Recognition. In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), pages 49-57, Gran Canaria, Spain, June 2011.
T. Gass, L. Pishchulin, P. Dreuw, and H. Ney. Warp that Smile on your Face: Optimal and Smooth Deformations for Face Recognition. In IEEE International Conference on Automatic Face and Gesture Recognition (FG), pages 456-463, Santa Barbara, CA, USA, March 2011.
T. Gass, P. Dreuw, and H. Ney. Constrained Energy Minimisation for Matching-Based Image Recognition. In International Conference on Pattern Recognition (ICPR), pages 3304-3307, Istanbul, Turkey, August 2010.
L. Pishchulin. Matching Algorithms for Image Recognition. Master Thesis, Aachen, Germany, January 2010.
T. Gass, T. Deselaers, and H. Ney. Deformation-aware Log-Linear Models. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium (DAGM), pages 201-210, Jena, Germany, September 2009.
P. Dreuw, P. Steingrube, H. Hanselmann, and H. Ney. SURF-Face: Face Recognition Under Viewpoint Consistency Constraints . In British Machine Vision Conference (BMVC), pages 1-11, London, UK, September 2009.
T. Gass. Deformations and Discriminative Models for Image Recognition. Master Thesis, Aachen, Germany, July 2008.
D. Keysers, T. Deselaers, C. Gollan, and H. Ney. Deformation Models for Image Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 29, number 8, pages 1422-1435, August 2007.
P. Dreuw, T. Deselaers, D. Keysers, and H. Ney. Modeling Image Variability in Appearance-Based Gesture Recognition. In ECCV Workshop on Statistical Methods in Multi-Image and Video Processing (ECCV-SMVP), pages 7-18, Graz, Austria, May 2006.
D. Keysers, W. Macherey, H. Ney, and J. Dahmen. Adaptation in Statistical Pattern Recognition using Tangent Vectors. IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 26, number 2, pages 269-274, February 2004.
Older Software Versions
Note: an older release of this software is still available from our webpages.