Baseline detection based on local connection and evaluation for Tibetan historical document text line

Yiqun Wang; Weilan Wang; Zhengqi Cai

doi:10.1117/12.2662891

28 December 2022 Baseline detection based on local connection and evaluation for Tibetan historical document text line

Yiqun Wang, Weilan Wang, Zhengqi Cai

Author Affiliations +

Proceedings Volume 12506, Third International Conference on Computer Science and Communication Technology (ICCSCT 2022); 125066E (2022) https://doi.org/10.1117/12.2662891
Event: International Conference on Computer Science and Communication Technology (ICCSCT 2022), 2022, Beijing, China

Abstract

The baseline position is an important reference information of the text line in the document written by Uchen Script. In order to overcome the distortion of text line and obtain accurate baseline position, this paper proposes a baseline detection method based on lines connection local and global evaluation. First, the slanted document image is corrected and the number of text lines is determined by projection. Then the discrete lines are connected locally; Finally, the baseline of text lines is obtained by evaluating the combination of baselines. Experimental results show that the proposed method can effectively overcome document skew and text line distortion, and the baseline position detected is accurate.

Citation Download Citation

Yiqun Wang, Weilan Wang, and Zhengqi Cai "Baseline detection based on local connection and evaluation for Tibetan historical document text line", Proc. SPIE 12506, Third International Conference on Computer Science and Communication Technology (ICCSCT 2022), 125066E (28 December 2022); https://doi.org/10.1117/12.2662891

ACCESS THE FULL ARTICLE

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY