| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
A Statistical-Topological Feature Combination for Recognition of Isolated Hand Gestures from Kinect Based Depth Images
Abstract : Reliable hand gesture recognition is an important problem for automatic sign language recognition for the people with hearing and speech disabilities. In this paper, we create a new benchmark database of multi-oriented, isolated ASL numeric images using recently launched Kinect V2. Further, we design an effective statistical-topological feature combinations for recognition of the hand gestures using the available V1 sensor dataset and also over the new V2 dataset. For V1, our best accuracy is 98.4% which is comparable with the best one reported so far and for V2 we achieve an accuracy of 92.2% which is first of its kind.
Cited literature [21 references]
https://hal.inria.fr/hal-01517817
Contributor : Phuc Ngo <>
Submitted on : Wednesday, May 3, 2017 - 4:35:05 PM
Last modification on : Tuesday, April 13, 2021 - 3:29:51 AM
Long-term archiving on: : Friday, August 4, 2017 - 1:23:34 PM
Contributor : Phuc Ngo <>
Submitted on : Wednesday, May 3, 2017 - 4:35:05 PM
Last modification on : Tuesday, April 13, 2021 - 3:29:51 AM
Long-term archiving on: : Friday, August 4, 2017 - 1:23:34 PM
File
paper29.pdf
Files produced by the author(s)