Using histogram representation and Earth Mover's Distance as an evaluation tool for text detection
From LRDE
- Authors
- Stefania Calarasanu, Jonathan Fabrizio, Séverine Dubuisson
- Where
- Proceedings of the 13th IAPR International Conference on Document Analysis and Recognition (ICDAR)
- Place
- Nancy, France
- Type
- inproceedings
- Projects
- Olena
- Date
- 2015-08-01
Abstract
In the context of text detection evaluation, it is essential to use protocols that are capable of describing both the quality and the quantity aspects of detection results. In this paper we propose a novel visual representation and evaluation tool that captures the whole nature of a detector by using histograms. First, two histograms (coverage and accuracy) are generated to visualize the different characteristics of a detector. Secondly, we compare these two histograms to a so called optimal one to compute representative and comparable scores. To do so, we introduce the usage of the Earth Mover's Distance as a reliable evaluation tool to estimate recall and precision scores. Results obtained on the ICDAR 2013 dataset show that this method intuitively characterizes the accuracy of a text detector and gives at a glance various useful characteristics of the analyzed algorithm.
Documents
Bibtex (lrde.bib)
@InProceedings{ calarasanu.15.icdar, author = {Stefania Calarasanu and Jonathan Fabrizio and S\'everine Dubuisson}, title = {Using histogram representation and Earth Mover's Distance as an evaluation tool for text detection}, booktitle = {Proceedings of the 13th IAPR International Conference on Document Analysis and Recognition (ICDAR)}, address = {Nancy, France}, month = aug, year = 2015, pages = {221--225}, abstract = { In the context of text detection evaluation, it is essential to use protocols that are capable of describing both the quality and the quantity aspects of detection results. In this paper we propose a novel visual representation and evaluation tool that captures the whole nature of a detector by using histograms. First, two histograms (coverage and accuracy) are generated to visualize the different characteristics of a detector. Secondly, we compare these two histograms to a so called optimal one to compute representative and comparable scores. To do so, we introduce the usage of the Earth Mover's Distance as a reliable evaluation tool to estimate recall and precision scores. Results obtained on the ICDAR 2013 dataset show that this method intuitively characterizes the accuracy of a text detector and gives at a glance various useful characteristics of the analyzed algorithm.}, doi = {10.1109/ICDAR.2015.7333756} }