From text detection to text segmentation: a unified evaluation scheme
From LRDE
- Authors
- Stefania Calarasanu, Jonathan Fabrizio, Séverine Dubuisson
- Where
- Proceedings of the 2nd International Workshop on Robust Reading Conference (IWRR-ECCV)
- Place
- Amsterdam, The Netherlands
- Type
- inproceedings
- Projects
- Olena
- Date
- 2016-10-01
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.} }