Bringing semantics into word image representation

作者：

Highlights：

• We propose a normalized word representation which is invariant to word form inflections.

• We introduce a novel semantic representation for word images which respects both its form and meaning, thereby reducing the vocabulary gap that exists between the query and its retrieved results.

• We demonstrate semantic word spotting task and evaluate the proposed representation on standard IR measures such word analogy and word similarity.

• The proposed representation is evaluated on both historical and modern document image collections in printed and handwritten domains across Latin and Indic scripts.

摘要

•We propose a normalized word representation which is invariant to word form inflections.•We introduce a novel semantic representation for word images which respects both its form and meaning, thereby reducing the vocabulary gap that exists between the query and its retrieved results.•We demonstrate semantic word spotting task and evaluate the proposed representation on standard IR measures such word analogy and word similarity.•The proposed representation is evaluated on both historical and modern document image collections in printed and handwritten domains across Latin and Indic scripts.

论文关键词：Word image embedding,Word spotting,Semantic spotting

论文评审过程：Received 6 April 2019, Revised 14 March 2020, Accepted 11 July 2020, Available online 12 July 2020, Version of Record 23 July 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107542