Distance transform based text-line extraction from unconstrained handwritten document images

作者：

Highlights：

• Uses mostly dynamic parameters compatible with any type of handwritten document.

• Deals with the non-uniform gaps between consecutive text-lines and words.

• Generates separation seams based on heuristics with empirically computed parameters.

• Handles complex situations; touching text-lines and overlapping characters easily.

• Outperforms state-of-the-art text-line extraction methods.

摘要

•Uses mostly dynamic parameters compatible with any type of handwritten document.•Deals with the non-uniform gaps between consecutive text-lines and words.•Generates separation seams based on heuristics with empirically computed parameters.•Handles complex situations; touching text-lines and overlapping characters easily.•Outperforms state-of-the-art text-line extraction methods.

论文关键词：Text-line extraction,Handwritten document image,Distance transform,Seam carving,HIT-MW,ICDAR

论文评审过程：Received 13 April 2020, Revised 22 January 2021, Accepted 23 July 2021, Available online 31 July 2021, Version of Record 10 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115666