Skip to main content
. Author manuscript; available in PMC: 2010 Nov 1.
Published in final edited form as: Image Vis Comput. 2009 Nov 1;27(12):1826–1844. doi: 10.1016/j.imavis.2009.02.005

Fig. 15.

Fig. 15

(a-b) The modelling results for the ASL signs “car” and “lousy.” In each sign, six example frames are shown. The 3D handshapes recovered by the proposed algorithm are shown in their 3D position and orientation with regard to the face coordinate system. The images with the corresponding reprojection of the reconstructed handshape using the 3D motion parameters recovered on top of the images are shown below each 3D display. (c) The handshape of the signs: “3.” (d-e) The motions of the signs. (f-g) The POAs of the signs.