Static hand gesture recognition in sign language based on convolutional neural network with feature extraction method using ORB descriptor and Gabor filter

作者：

Highlights：

• A novel hand gesture identification is proposed using CNN, ORB and Gabor filter.

• It can be used as a pre-trained structure for any type of the hand gesture dataset.

• Remarkable results are obtained on the famous databases.

• Less computational intricacy in the hardware implementation and online application.

摘要

•A novel hand gesture identification is proposed using CNN, ORB and Gabor filter.•It can be used as a pre-trained structure for any type of the hand gesture dataset.•Remarkable results are obtained on the famous databases.•Less computational intricacy in the hardware implementation and online application.

论文关键词：Static hand gesture,CNN,ORB feature descriptor and Transfer learning technique

论文评审过程：Received 7 May 2022, Revised 23 July 2022, Accepted 12 August 2022, Available online 23 August 2022, Version of Record 30 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118559