CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation
Historical document analysis systems gain importance with the increasing efforts in the digitalization of archives. Page segmentation and layout analysis are crucial steps for such systems. Errors in these steps will affect the outcome of handwritten text recognition and Optical Character Recognitio...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/6/5/32 |
| _version_ | 1797568010303569920 |
|---|---|
| author | Yekta Said Can M. Erdem Kabadayı |
| author_facet | Yekta Said Can M. Erdem Kabadayı |
| author_sort | Yekta Said Can |
| collection | DOAJ |
| description | Historical document analysis systems gain importance with the increasing efforts in the digitalization of archives. Page segmentation and layout analysis are crucial steps for such systems. Errors in these steps will affect the outcome of handwritten text recognition and Optical Character Recognition (OCR) methods, which increase the importance of the page segmentation and layout analysis. Degradation of documents, digitization errors, and varying layout styles are the issues that complicate the segmentation of historical documents. The properties of Arabic scripts such as connected letters, ligatures, diacritics, and different writing styles make it even more challenging to process Arabic script historical documents. In this study, we developed an automatic system for counting registered individuals and assigning them to populated places by using a CNN-based architecture. To evaluate the performance of our system, we created a labeled dataset of registers obtained from the first wave of population registers of the Ottoman Empire held between the 1840s and 1860s. We achieved promising results for classifying different types of objects and counting the individuals and assigning them to populated places. |
| first_indexed | 2024-03-10T19:50:19Z |
| format | Article |
| id | doaj.art-1feb16472d4c42baba96f75680802d28 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T19:50:19Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-1feb16472d4c42baba96f75680802d282023-11-20T00:25:59ZengMDPI AGJournal of Imaging2313-433X2020-05-01653210.3390/jimaging6050032CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival DocumentationYekta Said Can0M. Erdem Kabadayı1College of Social Sciences and Humanities, Koc University, Rumelifeneri Yolu, 34450 Sarıyer, Istanbul, TurkeyCollege of Social Sciences and Humanities, Koc University, Rumelifeneri Yolu, 34450 Sarıyer, Istanbul, TurkeyHistorical document analysis systems gain importance with the increasing efforts in the digitalization of archives. Page segmentation and layout analysis are crucial steps for such systems. Errors in these steps will affect the outcome of handwritten text recognition and Optical Character Recognition (OCR) methods, which increase the importance of the page segmentation and layout analysis. Degradation of documents, digitization errors, and varying layout styles are the issues that complicate the segmentation of historical documents. The properties of Arabic scripts such as connected letters, ligatures, diacritics, and different writing styles make it even more challenging to process Arabic script historical documents. In this study, we developed an automatic system for counting registered individuals and assigning them to populated places by using a CNN-based architecture. To evaluate the performance of our system, we created a labeled dataset of registers obtained from the first wave of population registers of the Ottoman Empire held between the 1840s and 1860s. We achieved promising results for classifying different types of objects and counting the individuals and assigning them to populated places.https://www.mdpi.com/2313-433X/6/5/32page segmentationhistorical document analysisconvolutional neural networksArabic script layout analysis |
| spellingShingle | Yekta Said Can M. Erdem Kabadayı CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation Journal of Imaging page segmentation historical document analysis convolutional neural networks Arabic script layout analysis |
| title | CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation |
| title_full | CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation |
| title_fullStr | CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation |
| title_full_unstemmed | CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation |
| title_short | CNN-Based Page Segmentation and Object Classification for Counting Population in Ottoman Archival Documentation |
| title_sort | cnn based page segmentation and object classification for counting population in ottoman archival documentation |
| topic | page segmentation historical document analysis convolutional neural networks Arabic script layout analysis |
| url | https://www.mdpi.com/2313-433X/6/5/32 |
| work_keys_str_mv | AT yektasaidcan cnnbasedpagesegmentationandobjectclassificationforcountingpopulationinottomanarchivaldocumentation AT merdemkabadayı cnnbasedpagesegmentationandobjectclassificationforcountingpopulationinottomanarchivaldocumentation |