Libraries and archives throughout the world keep a great number of historical documents. Many of them are handwritten ones. In many cases they are hardly available. Digitization of such artifacts can make them accessible to the community. But even digitized, they remain unsearchable so the important task is to draw the contents in the computer readable form. One of the first steps on this way is segmentation of the document into the lines. Artificial Intelligence algorithms can be used to solve this problem. In the current paper the projection–based algorithm is presented. Our algorithm finds lines in the left and the right part of the page independently and then associates both sets. Thanks to this, our method can recognize skewed lines better then the algorithms that use global projection. The performance of the algorithm is evaluated on the data-set and with the procedure proposed by the organizers of the ICDAR2009 competition.
CITATION STYLE
Babczyński, T., & Ptak, R. (2020). Handwritten Text Lines Segmentation Using Two Column Projection. In Advances in Intelligent Systems and Computing (Vol. 1173 AISC, pp. 11–20). Springer. https://doi.org/10.1007/978-3-030-48256-5_2
Mendeley helps you to discover research relevant for your work.