Cross-language framework for word recognition and spotting of Indic scripts

作者：

Highlights：

• We introduce a cross-language-based text recognition and word spotting in handwritten recognition platform.

• A novel script similarity measure evaluation is proposed for selecting source script for better cross-language handwriting recognition.

• This cross-language text recognition paradigm will help for developing recognition and spotting approaches of low resource scripts.

摘要

•We introduce a cross-language-based text recognition and word spotting in handwritten recognition platform.•A novel script similarity measure evaluation is proposed for selecting source script for better cross-language handwriting recognition.•This cross-language text recognition paradigm will help for developing recognition and spotting approaches of low resource scripts.

论文关键词：Indic script recognition,Handwritten word recognition,Word spotting,Cross language recognition,Script similarity,Hidden Markov model

论文评审过程：Received 18 October 2016, Revised 31 December 2017, Accepted 28 January 2018, Available online 2 February 2018, Version of Record 10 February 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.01.034