Volume 23, Issue 1 (7-2004)
2004, 23(1): 33-48 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
H. Nezamabadi-Pour, E. Kabir and R. Azmi. A Modified Character Segmentation Algorithm for Farsi Printed Text Using Upper Contour Labelling. Computational Methods in Engineering 2004; 23 (1) :33-48
URL: http://jcme.iut.ac.ir/article-1-301-en.html
URL: http://jcme.iut.ac.ir/article-1-301-en.html
Abstract: (4255 Views)
In this paper, a modified segmentation algorithm for printed Farsi words is presented. This algorithm is based on a previous work by Azmi that uses the conditional labeling of the upper contour to find the segmentation points. The main objective is to improve the segmentation results for low quality prints. To achieve this, various modifications on local baseline detection, contour labeling and segmentation rules have been applied. In an experiment, the correct segmentation rate was 97%. Based on the results obtained, a detailed error analysis is presented which should be useful for furthur research on this topic.
Keywords: Character Segmentation, Farsi Printed text, Local baseline, Upper contour, Histogram, Segmental code, Labeling
