Applying deep neural networks for the automatic recognition of sign language words: A communication aid to deaf agriculturists

作者：

Highlights：

• Hand gesture recognition for Indian sign language words in agriculture domain.

• CNN model for discriminative feature extraction from the frame sequences.

• Hybrid GoogleNet-BiLSTM model for improved gesture classification.

• Improved model performance on benchmarking hand gesture dataset.

摘要

•Hand gesture recognition for Indian sign language words in agriculture domain.•CNN model for discriminative feature extraction from the frame sequences.•Hybrid GoogleNet-BiLSTM model for improved gesture classification.•Improved model performance on benchmarking hand gesture dataset.

论文关键词：Sign language recognition,Indian sign language,Dynamic hand gestures,Agricultural words,Complex backgrounds,Deep learning

论文评审过程：Received 15 September 2020, Revised 6 July 2021, Accepted 11 July 2021, Available online 15 July 2021, Version of Record 20 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115601