Java psychomorph webstart launch page

Click to launch java psychomorph (version 4).

You should be prompted to open with javaws, click OK and again when you get the security warning (or two) as it is a self-signed jar file.

Some example images to start playing with are available here images.zip

Help pages are provided on the wiki. Details of the API (e.g. for writing plugins) are available here.

Some other (possibly) useful data is available here extra.zip. This includes some masks, symmetry file and wavelet filters.

The current version has some improved computer vision tools, including face and feature detection and groupwise alignment. For the face and feature detection you will need the face detection data (this is generated by OpenCV but has the - stripped out of comments to keep Java happy), the PSM feature detection data and/or the ORASM feature detection data. You will need to unzip the data to your hard drive to use it. The PSM and ORASM data were trained on the BioID data set with some enrichement (+ or - 10 degree rotations). The ORASM data uses all the 20 points supplied with the BioID data, the PSM uses 5 points (points 0, 1, 14, 2 and 3 from the full set).

The previous version (version 3) is still available here.

References

Please reference at least one of the following papers in any published work using the software.

Feature detection

B. Tiddeman, Facial feature detection with 3D convex local models IEEE Conference on Face and Gesture Recognition, (to appear) 2011.

J. Chen and B. Tiddeman, Multi-Cue Facial Feature Detection and Tracking under Various Illuminations, International Journal of Robotics and Automation, Vol 25, No. 2, 2010.

M. Yu and B. Tiddeman, FACE DETECTION AND TRACKING WITH 3D PGA CLM, Int. Conf. on Computer Vision Theory and Applications (VISAPP), paper 111, 2010.

Texture transforming

B. Tiddeman, M. Stirrat and D. Perrett, Towards realism in facial transformation: results of a wavelet MRF method Computer Graphics Forum, Eurographics conference issue, Vol 24, No 1-5, Sept 2005.

Texture prototyping

B. Tiddeman, M. Stirrat and D. Perrett, Towards realism in facial prototyping: results of a wavelet MRF method, Theory and Practice of Computer Graphics, June 2005.

B. Tiddeman, D.M. Burt and D. Perrett, Computer Graphics in Facial Perception Research, IEEE Computer Graphics and Applications, Vol 21, No. 5, pp 42-50 Sept/Oct 2001.

Bernard Tiddeman Blending Textured Images using a Non-parametric Multiscale MRF Method 12th Int. Conf. in Central Europe on Computer Graphics, Visualization and Computer Vision 2004 (WSCG2004) 2-6 Feb 2004, University of West Bohemia, Plzen, Czech Republic

Moving Transforms

B.Tiddeman and D. Perrett, Moving Facial Image Transformations Based On Static 2D Prototypes, Proc. 9th Int. Conf. In Central Europe on Computer Graphics, Visualization and Computer Vision 2001, Pilsen, Czech Republic, Feb 5-9 2001.

B. Tiddeman and D. Perrett, Transformation of Dynamic Facial Image Sequences Using Static 2D Prototypes, The Visual Computer, Vol 18, No. 4, pp. 218-225, June 2002.

Good luck!