A novel finger and hand pose estimation technique for real-time hand gesture recognition

作者：

Highlights：

• A high-level hand feature extraction method for real-time gesture recognition.

• A novel algorithm is proposed to directly extract fingers from salient hand edges.

• A weighted radial projection algorithm is applied to locate each finger.

• The system can not only extract extensional fingers but also flexional fingers with high accuracy.

• It is robust to the hand rotation, finger side movement and disturbance of the arm area.

摘要

Highlights•A high-level hand feature extraction method for real-time gesture recognition.•A novel algorithm is proposed to directly extract fingers from salient hand edges.•A weighted radial projection algorithm is applied to locate each finger.•The system can not only extract extensional fingers but also flexional fingers with high accuracy.•It is robust to the hand rotation, finger side movement and disturbance of the arm area.

论文关键词：Computer vision,Finger modelling,Salient hand edge,Convolution operator,Real-time hand gesture recognition

论文评审过程：Received 17 March 2014, Revised 8 August 2014, Accepted 29 July 2015, Available online 8 August 2015, Version of Record 28 September 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.07.014