ELM based two-handed dynamic Turkish Sign Language (TSL) word recognition

作者：

Highlights：

• Turkish Sign Language (TSL) recognition model was developed using Leap Motion.

• We present a methodology for feature selection and extraction in TSL.

• ELM learning based method was proposed for recognition 50 of dynamic words.

• Comparing the performance of classical and ELM based classifiers.

• A novel algorithm is introduced for feature selection.

摘要

•Turkish Sign Language (TSL) recognition model was developed using Leap Motion.•We present a methodology for feature selection and extraction in TSL.•ELM learning based method was proposed for recognition 50 of dynamic words.•Comparing the performance of classical and ELM based classifiers.•A novel algorithm is introduced for feature selection.

论文关键词：Sign language recognition,Hand gesture recognition,Dynamic word gestures,Leap Motion Controller (LMC),Extreme Learning Machine (ELM)

论文评审过程：Received 21 February 2021, Revised 13 May 2021, Accepted 13 May 2021, Available online 23 May 2021, Version of Record 26 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115213