A Dempster–Shafer Theory based combination of handwriting recognition systems with multiple rejection strategies

作者：

Highlights：

• A two level handwritten word recognition system is proposed.

• Combining Hidden Markov models classifier based on Dempster–Shafer Theory.

• A post-processing module based on different DST based acceptance/rejection strategies.

• We improve the accuracy rate and the reliability of a Handwriting recognition system.

摘要

Highlights•A two level handwritten word recognition system is proposed.•Combining Hidden Markov models classifier based on Dempster–Shafer Theory.•A post-processing module based on different DST based acceptance/rejection strategies.•We improve the accuracy rate and the reliability of a Handwriting recognition system.

论文关键词：Handwriting recognition,Dempster–Shafer Theory,Ensemble classification,Rejection strategies,Representation of uncertainty,Imprecision

论文评审过程：Received 1 March 2014, Revised 12 August 2014, Accepted 13 August 2014, Available online 28 August 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.08.010