This article discusses the quality assessment of binary images. The customary, ground truth based methodology, used in the literature is shown to be problematic due to its subjective nature. Several previously suggested alternatives are surveyed and are also found to be inadequate in certain scenarios. A new approach, quantifying the adherence of a binarization to its document image is proposed and tested using six different measures of accuracy. The measures are evaluated experimentally based on datasets from DIBCO and H-DIBCO competitions, with respect to different kinds of binarization degradations.
|Title of host publication||Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Pages||495 - 500|
|Number of pages||6|
|State||Published - 2016|
|Event||15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016 - Shenzhen, China|
Duration: 23 Oct 2016 → 26 Oct 2016
|Name||2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), Frontiers in Handwriting Recognition (ICFHR), 2016 15th International Conference on, ICFHR|
|Conference||15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016|
|Period||23/10/16 → 26/10/16|
Bibliographical noteFunding Information:
The research reported here received initial funding from the Israel Science Foundation - F.I.R.S.T. (Bikura) Individual Grant no. 644/08, as well as the Israel Science Foundation Grant no. 1457/13. The research was also funded the European Research Council under the European Community's Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no. 229418, and by an Early Israel grant (New Horizons project), Tel Aviv University.
© 2016 IEEE.
- Computing and Processing
- Extraterrestrial measurements
- Quality assessment
- quality measure
- ground truth