Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 25.90 MB
Add to list
  1. Search results
  2. Page boundary extraction of bound his...

Page boundary extraction of bound historical herbaria

Krishna Kumar Thirukokaranam Chandrasekar (UGent) and Steven Verstockt (UGent)
(2020) ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1. p.476-483
Author
Organization
Abstract
When digitizing bound historical collections such as herbaria it is important to extract the main page region so that it could be used for automated processing. The thickness of the herbaria books also gives rise to deformations during imaging which reduces the efficiency of automatic detection tasks. In this work we address these problems by proposing an automatic page detection algorithm that estimates all the boundaries of the page and performs morphological corrections in order to reduce deformations. The algorithm extracts features from Hue, Saturation and Value transformations of an RGB image to detect the main page polygon. The algorithm was evaluated on multiple textual and herbaria type historical collections and obtains over 94% mean intersection over union on all these datasets. Additionally, the algorithm was also subjected to an ablation test to demonstrate the importance of morphological corrections.
Keywords
Page Boundary Detection, Hinge Detection, Border Noise, Digitization, Historical Image Processing, Herbaria Books

Downloads

  • Download
    DS318 i.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 12.86 MB
  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 13.04 MB

Citation

Please use this url to cite or link to this publication:

MLA
Thirukokaranam Chandrasekar, Krishna Kumar, and Steven Verstockt. “Page Boundary Extraction of Bound Historical Herbaria.” ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1, edited by A. P. Rocha et al., 2020, pp. 476–83, doi:10.5220/0009154104760483.
APA
Thirukokaranam Chandrasekar, K. K., & Verstockt, S. (2020). Page boundary extraction of bound historical herbaria. In A. P. Rocha, L. Steels, & J. Van Den Herik (Eds.), ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1 (pp. 476–483). https://doi.org/10.5220/0009154104760483
Chicago author-date
Thirukokaranam Chandrasekar, Krishna Kumar, and Steven Verstockt. 2020. “Page Boundary Extraction of Bound Historical Herbaria.” In ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1, edited by A. P. Rocha, L. Steels, and J. Van Den Herik, 476–83. https://doi.org/10.5220/0009154104760483.
Chicago author-date (all authors)
Thirukokaranam Chandrasekar, Krishna Kumar, and Steven Verstockt. 2020. “Page Boundary Extraction of Bound Historical Herbaria.” In ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1, ed by. A. P. Rocha, L. Steels, and J. Van Den Herik, 476–483. doi:10.5220/0009154104760483.
Vancouver
1.
Thirukokaranam Chandrasekar KK, Verstockt S. Page boundary extraction of bound historical herbaria. In: Rocha AP, Steels L, Van Den Herik J, editors. ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1. 2020. p. 476–83.
IEEE
[1]
K. K. Thirukokaranam Chandrasekar and S. Verstockt, “Page boundary extraction of bound historical herbaria,” in ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1, Valletta, Malta, 2020, pp. 476–483.
@inproceedings{8654557,
  abstract     = {{When digitizing bound historical collections such as herbaria it is important to extract the main page region so that it could be used for automated processing. The thickness of the herbaria books also gives rise to deformations during imaging which reduces the efficiency of automatic detection tasks. In this work we address these problems by proposing an automatic page detection algorithm that estimates all the boundaries of the page and performs morphological corrections in order to reduce deformations. The algorithm extracts features from Hue, Saturation and Value transformations of an RGB image to detect the main page polygon. The algorithm was evaluated on multiple textual and herbaria type historical collections and obtains over 94% mean intersection over union on all these datasets. Additionally, the algorithm was also subjected to an ablation test to demonstrate the importance of morphological corrections.}},
  author       = {{Thirukokaranam Chandrasekar, Krishna Kumar and Verstockt, Steven}},
  booktitle    = {{ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1}},
  editor       = {{Rocha, A. P. and Steels, L. and Van Den Herik, J.}},
  isbn         = {{9789897583957}},
  keywords     = {{Page Boundary Detection,Hinge Detection,Border Noise,Digitization,Historical Image Processing,Herbaria Books}},
  language     = {{eng}},
  location     = {{Valletta, Malta}},
  pages        = {{476--483}},
  title        = {{Page boundary extraction of bound historical herbaria}},
  url          = {{http://doi.org/10.5220/0009154104760483}},
  year         = {{2020}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: