Comparative study of conventional time series matching techniques for word spotting
作者：
Highlights：
• Experimented 32 sequence matching techniques by following a simple and classical word spotting architecture.
• Many such techniques have never been experimented in the context of word spotting but shows interesting word spotting results.
• Each sequence matching technique is explained in a detailed manner to quickly understand the idea behind.
• Six historical datasets of different kinds (handwritten and printed) are experimented.
• Experimental results are explained, analyzed and important conclusions are drawn on which algorithms to be used in a given context.
摘要
•Experimented 32 sequence matching techniques by following a simple and classical word spotting architecture.•Many such techniques have never been experimented in the context of word spotting but shows interesting word spotting results.•Each sequence matching technique is explained in a detailed manner to quickly understand the idea behind.•Six historical datasets of different kinds (handwritten and printed) are experimented.•Experimental results are explained, analyzed and important conclusions are drawn on which algorithms to be used in a given context.
论文关键词：Word spotting,Degraded historical documents,Hand-written documents,George Washington dataset,Bentham dataset,Japanese handwriting recognition
论文评审过程：Received 7 February 2017, Revised 17 May 2017, Accepted 7 July 2017, Available online 25 July 2017, Version of Record 18 September 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.07.011
