Recognizing hand gestures using the weighted elastic graph matching (WEGM) method

作者：

Highlights：

• The HEGM method for classifying hand postures with a hit rate of 97.08% on average over uniform and complex backgrounds.

• This method allows computing only features corresponding to highly discriminative nodes, thus decreasing computing time.

• A semi-automatic technique to annotate bunch graphs is described which is efficient and leads to faster graph creation.

摘要

•The HEGM method for classifying hand postures with a hit rate of 97.08% on average over uniform and complex backgrounds.•This method allows computing only features corresponding to highly discriminative nodes, thus decreasing computing time.•A semi-automatic technique to annotate bunch graphs is described which is efficient and leads to faster graph creation.

论文关键词：Elastic bunch graph,Graph matching,Feature weight,Hand gesture recognition

论文评审过程：Received 26 June 2012, Revised 24 March 2013, Accepted 19 June 2013, Available online 3 July 2013.

论文官网地址：https://doi.org/10.1016/j.imavis.2013.06.008