The objective is to recognize hand signs from video sequences. We develoepd
a prediction-and-verification segmentation scheme that uses attention images
from multiple fixations to segment hands of various shapes from complex
backgrounds. A major advantage of this scheme is that it can handle a large
number of different deformable objects presented in complex backgrounds.
The scheme is also relatively efficient since the segmentation is guided
by the past knowledge through a prediction-and-verification scheme. The
system has been tested to segment hands in the sequences of intensity images,
where each sequence represents a hand sign. After segmentation, a recursive
partition tree approximator is proposed to conduct hand sign classification.
This approach combines information in three key aspects of the hand signs,
the hand shape, the location, and the movement. The framework has been
tested to recognize various moving hand signs with hundreds of hand shapes.
Y. Cui and J. Weng, ``Appearance-Based
Hand Sign Recognition from Intensity Image Sequences,'' Computer Vision
and Image Understanding, vol. 78, pp. 157-176, 2000. Download
PostScript. Y. Cui and J. Weng, ``A Learning-based
prediction-and-verification segmentation scheme for hand sign image sequences,''
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21,
no. 8, pp. 798-804, August 1999. Download PostScript. Y. Cui and J. Weng, ``View-based hand
segmentation and hand-sequence recognition with complex backgrounds,''
in Proc. International Conference on Pattern Recognition, Vienna,
Austria, vol. III, pp. 617-621, Aug. 1996. Click here
to down load the paper (PostScript). Y. Cui and J. Weng, ``Hand segmentation
using learning-based prediction and verification for hand sign recognition,''
in Proc. IEEE Conference on Computer Vision and Pattern Recognition,
San Francisco, CA, pp. 88-93, June, 1996. Click here
to down load the paper (PostScript). Y. Cui, D. Swets and J. Weng, ``Learning-based
hand sign recognition using SHOSLIF-M,'' in Proc. Int'l Conf. Computer
Vision, MIT, MA, pp. 631-636, June 20-23, 1995. Y. Cui and J. Weng, ``Learning-based
hand sign recognition,'' in Proc. Int'l Workshop on Automatic Face-
and Gesture-Recognition, Zurich, Switzerland, pp. 201-206, June 26-28,
1995.
To Weng's Home Page: http://web.cps.msu.edu/~weng/