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

Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel
International Conference on Image Processing, Hong Kong, China, IEEE, 9/2010

Abstract:

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.

Files:

  Bukhari-Curled-Textline-Segmentation-ICIP10.pdf

BibTex:

@inproceedings{ BUKH2010,
	Title = {Performance Evaluation of Curled Textlines Segmentation Algorithms on CBDAR 2007 Dewarping Contest Dataset},
	Author = {Syed Saqib Bukhari and Faisal Shafait and Thomas M. Breuel},
	BookTitle = {International Conference on Image Processing},
	Month = {9},
	Year = {2010},
	Publisher = {IEEE}
}

     
Last modified:: 30.08.2016