Performance Evaluation of Curled Textlines Segmentation Algorithms on CBDAR 2007 Dewarping Contest Dataset

Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel

In: International Conference on Image Processing. IEEE International Conference on Image Processing (ICIP-10) September 26-29 Hong Kong China IEEE 9/2010.


Camera-captured document images often contain curled textlines because of geometric and perspective distortions. Finding curled textlines, which is more difficult than straight textline detection, is a primary step in the processing of handheld camera-captured document images. Detected textlines results can be used for dewarping of warped images, layout analysis, etc. In this paper, we compare previously reported curled textline segmentation techniques by using the publicly available CBDAR 2007 dewarping contest dataset and vectorial performance evaluation metrics.


Bukhari-Curled-Textline-Segmentation-ICIP10.pdf (pdf, 384 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence