Coupled grouping and matching for sign and gesture recognition
Computer Vision and Image Understanding
American sign language recognition with the kinect
ICMI '11 Proceedings of the 13th international conference on multimodal interfaces
Short communication: Selective Subsequence Time Series clustering
Knowledge-Based Systems
Robust hand tracking by integrating appearance, location and depth cues
Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Methodological foundation for sign language 3d motion trajectory analysis
IDA'12 Proceedings of the 11th international conference on Advances in Intelligent Data Analysis
Finding recurrent patterns from continuous sign language sentences for automated extraction of signs
The Journal of Machine Learning Research
Hi-index | 0.14 |
We consider two crucial problems in continuous sign language recognition from unaided video sequences. At the sentence level, we consider the movement epenthesis (me) problem and at the feature level, we consider the problem of hand segmentation and grouping. We construct a framework that can handle both of these problems based on an enhanced, nested version of the dynamic programming approach. To address movement epenthesis, a dynamic programming (DP) process employs a virtual me option that does not need explicit models. We call this the enhanced level building (eLB) algorithm. This formulation also allows the incorporation of grammar models. Nested within this eLB is another DP that handles the problem of selecting among multiple hand candidates. We demonstrate our ideas on four American Sign Language data sets with simple background, with the signer wearing short sleeves, with complex background, and across signers. We compared the performance with Conditional Random Fields (CRF) and Latent Dynamic-CRF-based approaches. The experiments show more than 40 percent improvement over CRF or LDCRF approaches in terms of the frame labeling rate. We show the flexibility of our approach when handling a changing context. We also find a 70 percent improvement in sign recognition rate over the unenhanced DP matching algorithm that does not accommodate the me effect.