Visual recognition of continuous hand postures
Tóm tắt
This paper describes GREFIT (Gesture REcognition based on FInger Tips), a neural network-based system which recognizes continuous hand postures from gray-level video images (posture capturing). Our approach yields a full identification of all finger joint angles (making, however, some assumptions about joint couplings to simplify computations). This allows a full reconstruction of the three-dimensional (3-D) hand shape, using an articulated hand model with 16 segments and 20 joint angles. GREFIT uses a two-stage approach to solve this task. In the first stage, a hierarchical system of artificial neural networks (ANNs) combined with a priori knowledge locates the two-dimensional (2-D) positions of the finger tips in the image. In the second stage, the 2-D position information is transformed by an ANN into an estimate of the 3-D configuration of an articulated hand model, which is also used for visualization. This model is designed according to the dimensions and movement possibilities of a natural human hand. The virtual hand imitates the user's hand to an remarkable accuracy and can follow postures from gray scale images at a frame rate of 10 Hz.
Từ khóa
#Fingers #Image recognition #Artificial neural networks #Neural networks #Image reconstruction #Shape #Image segmentation #Hierarchical systems #Two dimensional displays #VisualizationTài liệu tham khảo
10.1007/BFb0028333
10.1109/38.403831
millar, 1996, a mathematical model for hand-shape analysis, Progress in Gestural Interaction— Proc Gesture Workshop 96, 235
10.1109/AFGR.1996.557255
shimada, 1996, 3-d hand pose estimation and shape model refinement from a monocular image sequence, Proc VSMM 96 GIFU, 423
10.1109/AFGR.1998.670960
ouhaddi, 1999, 3d hand gesture tracking by model registration, Proceedings of the International Workshop Synthetic-Natural Hybrid Coding and Three Dimensional Imaging IWSNHC3-DI 97, 74
jones, 1987, an evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex, J Neurophysiol, 58, 1233, 10.1152/jn.1987.58.6.1233
ritter, 1991, learning with the self-organizing map, Artificial Neural Networks, 379
kohonen, 1997, Self-Organizing Maps, 10.1007/978-3-642-97966-8
10.1016/S0926-6410(98)00025-1
nölker, 0, GREFIT website
poizner, 1981, perception of american sign language in dynamic point-light displays, J Experimental Psychol Human Performance Perception, 7, 432, 10.1037/0096-1523.7.2.430
10.1109/ICCV.1995.466882
10.1109/ICPR.1996.546107
10.1109/IJCNN.1992.227306
10.1109/AFGR.2000.840675
pavlović, 1997, visual interpretation of hand gestures for human–computer interaction: a review, IEEE Trans Pattern Anal Machine Intelll, 19, 677, 10.1109/34.598226
10.1007/BF00849076
10.1109/38.250916
martin, 1997, an appearance-based approach to gesture-recognition, Proc 9th Int Conf Image Anal Processing, 1311, 10.1007/3-540-63508-4_141
10.1007/978-1-4471-2063-6_159
kapandji, 1982, The Physiology of the Joints Upper Limbs
walter, 1996, Rapid Learning in Robotics
ritter, 1992, Neural Computation and Self-Organizing Maps
10.1109/5.58325
10.1016/0925-2312(95)00117-4