Bahadar Ali
Shah Khusro
ABSTRACT
Document tables are a rich source of implicit semantics hidden in documents which could be exploited for better searching and ranking. However, a central problem in document table processing systems is the segmentation of impure and incomplete table segments. Many existing methods are limited to basic table segments of limited table layout complexity. These methods are passing through the stage of very low level segmentation thus missing many physical and logical structures of tables producing erroneous results. However, these structures have significant impact on the overall table interpretation. In order to gain the full strength of table information reusability, a deep segmentation with a layout independent representation of tables is needed. This paper propose an algorithm which performs divide and merge tasks in different phases of segmentation using matrix as intermediate model. The algorithm covers maximum layout complexity and extracts table schema, data and the set of reading paths which are then represented in a layout independent notation. We evaluated our results using standard measures and open data sets.
- Babatunde, F.F. et al. 2015. Automatic Table Recognition and Extraction from Heterogeneous Documents. Journal of Computer and Communications. 03, 12 (2015), 100--110. DOI= http://dx.doi.org/10.4236/jcc.2015.312009.Google Scholar
Cross Ref
- Bansal, A. et al. Table Extraction from Document Images using Fixed Point Model. In Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (Bangalore, India, December 14-18, 2014), ACM, New York, NY, 1--8. DOI= http://dx.doi.org/10.1145/2683483.2685503. Google ScholarDigital Library
- Crestan, E. and Pantel, P. 2011. Web-scale table census and classification. In Proceedings of the Forth International Conference on Web Search and Web Data Mining (Hong Kong, China, February 9-12, 2011), ACM, New York, NY, 545--554. DOI= http://doi.acm.org/10.1145/1935826.1935904. Google ScholarDigital Library
- e Silva, A.C. et al. 2006. Design of an end-to-end method to extract information from tables. International Journal of Document Analysis and Recognition (IJDAR). 8, 2-3 (Feb. 2006), 144--171. DOI= http://dx.doi.org/10.1007/s10032-005-0001-x.Google ScholarCross Ref
- Embley, D.W. et al. 2006. Table-processing paradigms: A research survey. International Journal of Document Analysis and Recognition (IJDAR). 8, 2-3 (2006), 66--86. DOI= http://dx.doi.org/10.1007/s10032-006-0017-x.Google ScholarCross Ref
- Fang, J. et al. 2012. Table Header Detection and Classification. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence (Toronto, Ontario, Canada, July 22-26, 2012), 599--605. Google ScholarDigital Library
- Hurst, M. 2006. Towards a theory of tables. International Journal on Document Analysis and Recognition (IJDAR). 8, 2-3 (2006), 123--131. DOI= http://dx.doi.org/10.1007/s10032-006-0016-y.Google ScholarCross Ref
- Jha, P. and Nagy, G. 2008. Wang Notation Tool: Layout independent representation of tables. In 19th International ICPR Conference on Pattern Recognition (Tampa, Florida, USA, December 8-11, 2008), IEEE, 1--4. DOI= http://dx.doi.org/10.1109/ICPR.2008.4761550.Google Scholar
- Khusro, S. et al. 2014. On Methods and Tools of Table Detection, Extraction and Annotation in PDF Documents. Journal of Information Science (JIS). 41, 1 (2014), 41--57. DOI= http://dx.doi.org/10.1177/0165551514551903. Google ScholarDigital Library
- Liu, Y. et al. 2007. TableSeer: Automatic Table Metadata Extraction and Searching in Digital Libraries Categories and Subject Descriptors. In Proceedings of the 7th ACM/IEEECS Joint Conference on Digital libraries (Vancouver, British Columbia, Canada, June 18-23, 2007), ACM, New York, NY, 91--100. DOI= http://doi.acm.org/10.1145/1255175.1255193. Google ScholarDigital Library
- Nurminen, A. 2013. Algorithmic Extraction of Data in Tables in PDF Documents. Tampere University of Technology.Google Scholar
- Rastan, R. et al. 2015. TEXUS: A Task-based Approach for Table Extraction and Understanding. Proceedings of the 2015 ACM Symposium on Document Engineering (Lausanne, Switzerland, 2015), ACM, New York, NY, 25--34. DOI= http://doi.acm.org/10.1145/2682571.2797069. Google ScholarDigital Library
- Seth, S. et al. 2010. Analysis and taxonomy of column header categories for web tables. In Proceedings of the 8th IAPR International Workshop on Document Analysis Systems (Boston, Massachusetts, USA, June 9-11, 2010), ACM, New York, NY, 81--88. DOI= http://dx.doi.org/10.1145/1815330.1815341. Google ScholarDigital Library
- Wang, Y. et al. 2004. Table Structure Understanding and its Performance Evaluation. Pattern Recognition. 37, 7 (2004), 1479--1497. DOI= http://dx.doi.org/10.1016/j.patcog.2004.01.012.Google ScholarCross Ref
- Xinxin, W. 1996. Tabular Extraction, Editing and Formating. University of Waterloo Waterloo, Ont., Canada.Google Scholar
- Yildiz, B. et al. 2005. PDF2Table: A Method to Extract Table Information from PDF Files. In Proceedings of the 2nd Indian International Conference on Artificial Intelligence (December 20-22, Pune, India, 2005), Research Gate, 1773--178.Google Scholar
Recommendations
Script-Independent Text Segmentation from Document Images
Document image analysis finds broad application in the digital world for the purpose of information retrieval. This includes optical character recognition (OCR), indexing of digital libraries, web image processing, etc. One of the important steps in ...
Fisher–Tippett Region-Merging Approach to Transrectal Ultrasound Prostate Lesion Segmentation
In this paper, a computerized approach to segmenting prostate lesions in transrectal ultrasound (TRUS) images is presented. The segmentation of prostate lesions from TRUS images is very challenging due to issues, such as poor contrast, low SNRs, and ...
A semi-automatic approach for segmentation of three-dimensional microscopic image stacks of cardiac tissue
FIMH'13: Proceedings of the 7th international conference on Functional Imaging and Modeling of the HeartThe segmentation of three-dimensional microscopic images of cardiac tissues provides important parameters for characterizing cardiac diseases and modeling of tissue function. Segmenting these images is, however, challenging. Currently only time-consuming ...
Comments