|
|
 Hand Detection Hand detection is to locate the positions and sizes of hands in images. It is an interesting computer vision problem and has many potential applications in Sign Language Recognition, Human Computer Interaction and many other fields. Despite the fact that skin color is a very discriminative feature to detect hands in color images, my research would focus on extracting salient and discriminating features that could identify hand shapes in still gray images. Related Works View/Pose-based Methods: Viola and Jones's framework, single view-based hand detector. Mathias Kolsch and Matthew Turk. UCSB, [Kolsch 04a][Kolsch 04b] Multiview hand detector, hand shapes are partitioned by shape context [Ong 04] Part-based Methods Deformable Hand Template [Coughlan 2000] A Geometric Prior an occlusion process an image model a dynamtic programming algorithm References [Kolsch 04a] Mathias Kolsch and Matthew Turk, Robust hand detection, International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, May 17-19, 2004 [Kolsch 04b]M.Kolsch, M.Turk,Analysis of rotational robustness of hand detection with a Viola-Jones detector, Proceedings of the 17th International Conference on Pattern Recognition, 2004
[Ong 04] Ong E, Bowden R, Detection and Segmentation of hand shapes using Boosted Classifiers, International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, May 17-19, 2004.
[Coughlan 2000] Coughlan, J.M., Snow, D., English, C. and Yuille, A.L. (2000). "Efficient Deformable Template Detection and Localization without User Initialization". Computer Vision and Image Understanding.78, pp 303-319.
[Grenander 1991] U.Urenander, Y.Chow and D.M.Keenan, Hands: a Pattern Theoretic Study of Biological Shapes, Springer-Verlag, 1991 |
|