• Laser & Optoelectronics Progress
  • Vol. 58, Issue 2, 0210008 (2021)
Jincheng Li1, Xiaojuan Wang2, Weilan Wang1、*, Qiang Lin2, and Pengfei Hu2
Author Affiliations
  • 1Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu 730030, China
  • 2College of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu 730030, China
  • show less
    DOI: 10.3788/LOP202158.0210008 Cite this Article Set citation alerts
    Jincheng Li, Xiaojuan Wang, Weilan Wang, Qiang Lin, Pengfei Hu. Text Line Segmentation of Tibetan Historical Documents Based on Text Core Regions Combined with Expansion Growth[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0210008 Copy Citation Text show less
    Partial illustration of lines in ancient Tibetan texts. (a) Baseline and syllable points; (b) slanted text line; (c) distorted text line; (d) overlapping and adhesion of text lines
    Fig. 1. Partial illustration of lines in ancient Tibetan texts. (a) Baseline and syllable points; (b) slanted text line; (c) distorted text line; (d) overlapping and adhesion of text lines
    Flow chart of method
    Fig. 2. Flow chart of method
    Tibetan historical document image
    Fig. 3. Tibetan historical document image
    Syllable point detection of Tibetan historical document. (a) Binary map after layout processing (black background area is local binary map); (b) syllable point image
    Fig. 4. Syllable point detection of Tibetan historical document. (a) Binary map after layout processing (black background area is local binary map); (b) syllable point image
    Projection images. (a) Horizontal projection of syllable point image; (b) vertical projection of binary original image
    Fig. 5. Projection images. (a) Horizontal projection of syllable point image; (b) vertical projection of binary original image
    Formation of pseudo-text connected regions. (a) Image of text core area; (b) image of pseudo-text connected region
    Fig. 6. Formation of pseudo-text connected regions. (a) Image of text core area; (b) image of pseudo-text connected region
    Schematic of pixel point expansion growth process. (a) Pixel point without expansion; (b) pixel point during expansion; (c) pixel point after expansion
    Fig. 7. Schematic of pixel point expansion growth process. (a) Pixel point without expansion; (b) pixel point during expansion; (c) pixel point after expansion
    Line acquisition of pseudo text. (a) Expansion growth result; (b) pseudo-text lines
    Fig. 8. Line acquisition of pseudo text. (a) Expansion growth result; (b) pseudo-text lines
    Local diagram in attribution process of broken strokes. (a) Text lines to be split; (b) pseudo-text lines; (c) complete split lines
    Fig. 9. Local diagram in attribution process of broken strokes. (a) Text lines to be split; (b) pseudo-text lines; (c) complete split lines
    Final segmentation result of local image
    Fig. 10. Final segmentation result of local image
    Text lines and their segmentation results. (a)(c)(e) Original images; (b)(d)(f) segmentation results
    Fig. 11. Text lines and their segmentation results. (a)(c)(e) Original images; (b)(d)(f) segmentation results
    Segmentation effects of overlapped, adhered and broken strokes. (a)(b) Overlapped strokes; (c)(d) adhered strokes; (e)(f) broken strokes
    Fig. 12. Segmentation effects of overlapped, adhered and broken strokes. (a)(b) Overlapped strokes; (c)(d) adhered strokes; (e)(f) broken strokes
    Wrong segmentation and corresponding correct forms. (a)(c)(e)Wrong segmentation; (b)(d)(f)corresponding correct forms
    Fig. 13. Wrong segmentation and corresponding correct forms. (a)(c)(e)Wrong segmentation; (b)(d)(f)corresponding correct forms
    T1T2CTspaceRP /%
    5558080800.60.60.618202315141521151189.2689.6889.09
    5558080800.70.70.718202315241535151989.8590.5089.56
    1010101001001000.60.60.618202315091516150388.9789.3888.62
    1010101001001000.70.70.718202315261538152389.9790.6889.79
    Table 1. Text line segmentation results under different parameters
    Jincheng Li, Xiaojuan Wang, Weilan Wang, Qiang Lin, Pengfei Hu. Text Line Segmentation of Tibetan Historical Documents Based on Text Core Regions Combined with Expansion Growth[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0210008
    Download Citation