Personal tools

From text detection to text segmentation: a unified evaluation scheme

From LRDE

Jump to: navigation, search

Abstract

Current text segmentation evaluation protocols are often incapable of properly handling different scenarios (broken/merged/partial characters). This leads to scores that incorrectly reflect the segmentation accuracy. In this article we propose a new evaluation scheme that overcomes most of the existent drawbacks by extending the EvaLTex protocol (initially designed to evaluate text detection at region level). This new unified platform has numerous advantages: it is able to evaluate a text understanding system at every detection stage and granularity level (paragraph/line/word and now character) by using the same metrics and matching rules; it is robust to all segmentation scenarios; it provides a qualitative and quantitative evaluation and a visual score representation that captures the whole behavior of a segmentation algorithm. Experimental results on nine segmentation algorithms using different evaluation frameworks are also provided to emphasize the interest of our method.

Documents

Bibtex (lrde.bib)

@InProceedings{	  calarasanu.16.iwrr,
  author	= {Stefania Calarasanu and Jonathan Fabrizio and S\'everine
		  Dubuisson},
  title		= {From text detection to text segmentation: a unified
		  evaluation scheme},
  booktitle	= {Proceedings of the 2nd International Workshop on Robust
		  Reading Conference (IWRR-ECCV)},
  address	= {Amsterdam, The Netherlands},
  month		= oct,
  year		= 2016,
  abstract	= {Current text segmentation evaluation protocols are often
		  incapable of properly handling different scenarios
		  (broken/merged/partial characters). This leads to scores
		  that incorrectly reflect the segmentation accuracy. In this
		  article we propose a new evaluation scheme that overcomes
		  most of the existent drawbacks by extending the EvaLTex
		  protocol (initially designed to evaluate text detection at
		  region level). This new unified platform has numerous
		  advantages: it is able to evaluate a text understanding
		  system at every detection stage and granularity level
		  (paragraph/line/word and now character) by using the same
		  metrics and matching rules; it is robust to all
		  segmentation scenarios; it provides a qualitative and
		  quantitative evaluation and a visual score representation
		  that captures the whole behavior of a segmentation
		  algorithm. Experimental results on nine segmentation
		  algorithms using different evaluation frameworks are also
		  provided to emphasize the interest of our method.}
}