Sign Language Detection "in the Wild" with Recurrent Neural Networks

Mark Borg; Kenneth P. Camilleri

ICASSP 2019accepted0 citations

Sign Language Detection "in the Wild" with Recurrent Neural Networks

Abstract

We propose a multi-layer RNN for sign language detection. The system uses features extracted automatically from a 2-stream convolutional neural network (CNN) that takes video image data and motion data as input. We also created a dataset of videos containing signing "in the wild" to be used for training and evaluation purposes. We compare our system against the state-of-the-art, and attain an improvement of around 18%, indicating that our network is able to leverage dynamic information of hand motion during detection.

BibTeX

@inproceedings{icassp2019_signlanguagedete,
  title = {Sign Language Detection "in the Wild" with Recurrent Neural Networks},
  author = {Mark Borg and Kenneth P. Camilleri},
  booktitle = {ICASSP 2019},
  year = {2019}
}