Name
Abstract | ||
|---|---|---|
This paper introduces a model-based hand gesture recognition system, which consists of three phases: feature extraction, training, and recognition. In the feature extraction phase, a hybrid technique combines the spatial (edge) and the temporal (motion) information of each frame to extract the feature images. Then, in the training phase, we use the prin- cipal component analysis (PCA) to characterize spatial shape variations and the hidden Markov models (HMM) to de- scribe the temporal shape variations. A modified Hausdorff distance measurement is also applied to measure the sim- ilarity between the feature images and the pre-stored PCA models. The similarity measures are referred to as the pos- sible observations for each frame. Finally, in recognition phase, with the pre-trained PCA models and HMM, we can generate the observation patterns from the input sequences, and then apply the Viterbi algorithm to identify the gesture. In the experiments, we prove that our method can recognize 18 different continuous gestures effectively. |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1007/s001380050144 | Mach. Vis. Appl. |
Keywords | Field | DocType |
hand gesture recognition,hidden markov model hmm,principal compo- nent analysis pca,viterbi algorithm,hausdorff distance measurement,model-based hand gesture recognition,principal component analysis,hidden markov model,gesture recognition,hausdorff distance,hidden markov models,feature extraction | Pattern recognition,Gesture,Computer science,Gesture recognition,Feature extraction,Speech recognition,Artificial intelligence,Hausdorff distance,Hidden Markov model,Viterbi algorithm,Principal component analysis | Journal |
Volume | Issue | ISSN |
12 | 5 | 0932-8092 |
Citations | PageRank | References |
30 | 1.62 | 18 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chung-Lin Huang | 1 | 139 | 13.24 |
| Sheng-Hung Jeng | 2 | 36 | 2.12 |