Fingertip detection and tracking for recognition of air-writing in videos

作者：

Highlights：

• An expert system for the recognition of air-writing in web-cam videos is proposed.

• A new hand pose detection approach is proposed for initialization of air-writing.

• Robust fingertip detection and tracking is achieved using a new signature function.

• Fingertip velocity-based termination criterion is used as delimiter for air-writing.

• State-of-the-art results are obtained on a new air-writing dataset.

摘要

•An expert system for the recognition of air-writing in web-cam videos is proposed.•A new hand pose detection approach is proposed for initialization of air-writing.•Robust fingertip detection and tracking is achieved using a new signature function.•Fingertip velocity-based termination criterion is used as delimiter for air-writing.•State-of-the-art results are obtained on a new air-writing dataset.

论文关键词：Air-writing,Hand pose detection,Fingertip detection and tracking,Handwritten character recognition,Human-computer interaction (HCI)

论文评审过程：Received 9 September 2018, Revised 3 March 2019, Accepted 16 June 2019, Available online 17 June 2019, Version of Record 27 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.034