Logo PTI
Polish Information Processing Society
Logo FedCSIS

Annals of Computer Science and Information Systems, Volume 8

Proceedings of the 2016 Federated Conference on Computer Science and Information Systems

Caption-guided patent image segmentation

, ,

DOI: http://dx.doi.org/10.15439/2016F541

Citation: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 8, pages 261270 ()

Full text

Abstract. The paper presents a method of splitting patent drawings into subimages. For the image based patent retrieval and automatic document understanding it is required to use the individual subimages that are referenced in the text of a patent document. Our method utilizes the fact that subimages have their individual captions inscribed into the compound image. To find the approximate positions of subimages, first the specific captions are localized. Then subimages are found using the empirical rules concerning the relative positions of connected components to the subimage captions. These rules are based on the common sense observation that distances between connected components belonging to the same subimage are smaller than distances between connected components belonging to various subimages and that captions are located close to the corresponding subimages. Alternatively, the image segmentation can be defined as a specific optimization problem, that is aimed on maximizing the gaps between hypothetical subimages while preserving their relations to corresponding captions. The proposed segmentation method can be treated as the approximate solution of this problem.


  1. K. Suchet Chachra, Z. Xue, S. Antani, D. Demner-Fushman, and G. R. Thoma. Extraction and labeling high-resolution images from pdf documents. In Proc. SPIE 9021, Document Recognition and Retrieval XXI, 90210Q (24 March 2014);, 2014. http://dx.doi.org/10.1117/12.2042336.
  2. A. Chhatkuli, A. Foncubierta-Rodriguez, D. Markonis, F. Meriaudeaub, and H. Mueller. Separating compound figures in journal articles to allow for subfigure classification. In Proc. SPIE 8674, Medical Imaging 2013: Advanced PACS-based Imaging Informatics and Therapeutic Applications, 2013. http://dx.doi.org/10.1117/12.2007971.
  3. C. Clark and S. Divvala. Looking beyond text: Extracting figures, tables, and captions from computer science paper. In Scholarly Big Data: AI Perspectives, Challenges, and Ideas: Papers from the 2015 AAAI Workshop, pages 2–8, 2015.
  4. D. Hunt, L. Nguyen, and M. Rodgers. Patent Searching: Tools & Techniques. Wiley, 2007.
  5. L. D. Lopez, J. Yu, C. O. Tudor, C. N. Arighi, H. Huang, K. Vijay-Shanker, and C. H. Wu. Robust segmentation of biomedical figures for image-based document retrieval. In 2012 IEEE International Conference on Bioinformatics and Biomedicine, 2012. http://dx.doi.org/10.1109/BIBM.2012.6392706.
  6. X. Lu, S. Kataria, W. J. Brouwer, J. Z. Wang, and M. Prasenjit ůand C. Lee Giles. Automated analysis of images in documents for intelligent document search. IJDAR, 2009. http://dx.doi.org/10.1007/s10032-009-0081-0.
  7. X. Lu, P. Mitra, J. Z. Wang, and C. Lee Giles. Automatic categorization of figures in scientific documents. In Joint Conference on Digital Library, JCDL 06, USA., 2006. http://dx.doi.org/10.1145/1141753.1141778.
  8. J. Macqueen. Some methods for classification and analysis of multi-variate observations. In In 5-th Berkeley Symposium on Mathematical Statistics and Probability, pages 281–297, 1967.
  9. P. A. Praczyk, J. Nogueras-Iso, and S. Mele. Automatic extraction of figures from scientific publications in high-energy physics. Information Technology and Libraries, pages 25–52, December 2013.
  10. M. Prasenjit S. R. Choudhury and G. Clyde Lee. Automatic extraction of figures from scholarly documents. In DocEng ’15 Proceedings of the 2015 ACM Symposium on Document Engineering, pages 47–50, 2015. http://dx.doi.org/10.1145/2682571.2797085.
  11. J. Sas and A. Zolnierek. Three-stage method of text region extraction from diagram raster images. In Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013, Milkow, Poland, 27-29 May 2013, pages 527–538, 2013. http://dx.doi.org/10.1007/978-3-319-00969-8-52.
  12. A. W. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain. Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell., 22(12):1349–1380, December 2000. http://dx.doi.org/10.1109/34.895972.
  13. S. Vrochidis, S. Papadopoulos, A. Moumtzidou, P. Sidiropoulos, E. Pianta, and I. Kompatsiaris. Towards content-based patent image retrieval; a framework perspective. World Patent Information Journal, 32(2):94–106, 2010. http://dx.doi.org/10.1016/j.wpi.2009.05.010.
  14. X. Yuan and D. Ang. A novel figure panel classification and extraction. Int. J. Data Min. Bioinformatics, 9(1):22–36, November 2014. http://dx.doi.org/10.1504/IJDMB.2014.057779.