International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Mongolian Traditional Stamp Recognition using Scalable kNN

  • Gantuya., P (School of Engineering and Applied Sciences, National University of Mongolia) ;
  • Mungunshagai., B (Fine Arts Design and Technology School, Ikh Zasag International University) ;
  • Suvdaa., B (School of Engineering and Applied Sciences, National University of Mongolia)
  • Received : 2015.09.18
  • Accepted : 2015.11.10
  • Published : 2015.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

The stamp is one of the crucial information of traditional historical and cultural for nations. In this paper, we purpose to detect official stamps from scanned document and recognize the Mongolian traditional, historical stamps. Therefore we performed following steps: first, we detect official stamps from scanned document based on red-color segmentation and document standard. Then we collected 234 traditional stamp images with 6 classes and 100 official stamp images from scanned document images. Also we implemented the processing algorithms for noise removing, resize and reshape etc. Finally, we proposed a new scale invariant classification algorithm based on KNN (k-nearest neighbor). In the experimental result, our proposed a method had shown proper recognition rate.

Keywords

References

  1. Mongolian National Standard, Documents, Mongolian Agency for Standardization and Metrology, 2002.
  2. Ts.Battulga, Mongolian Runi documents, 2005.
  3. Kh.Perlee, Research collection, 2012.
  4. S.Dulam, Symbolization, 2010.
  5. Hossein Ebrahimpour and Abbas Kouzani, "Face Recognition using bagging KNN," Int'l Conf. on CVPR, IEEE, pp. 209-216, 1996.
  6. Pawel Forczmanski, Stamp detection in scanned documents, Chair of Multimedia Systems, West Pomeranian University of Technology, pp.61-68., 2010.
  7. Barbora Micenkovfi, Joost van Beusekom, and Faisal Shafait, Stamp Verification for Automated Document Authentication, German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany, 2009.
  8. Guangyu Zhu*, Stefan Jaeger, David Doermann, A robust stamp detection framework on degraded documents, Institute for Advanced Computer Studies, University of Maryland, College Park, MD, USA 20742, 2005.
  9. Patrik K, Martina Z, Robert H, Roman J, Miroslav B and Jan H, A Novel Approach to Face Recognition using Image Segmentation Based on SPCA-KNN Method, University of Zilina, Univerzitna 1, 010 26 Zilina, Slovakia, 2013.
  10. Mohammad K. H., Abu A. S. R., Rajibul A., and Dr.William P., Automatic Face Recognition System using P-tree and K-Nearest Neighbor Classifier, 2004.
  11. Guancong LiJune, "Postage stamp recognition using image processing", Faculty of Engineering and Sustainable Development, 2011.
  12. Xiang-rong Chen and HongJiang Zhang, "Photo time-stamp detection and recognition," 7th International Conference on Document Analysis and Recognition (ICDAR 2003), 2-Volume Set, Edinburgh, Scotland, UK, pp.319-322, 2003.
  13. Chunmei Liu, Chunheng Wang and Ruwei Dai, "Text detection in images based on unsupervised classification of edge-based features," In proceeding of: Document Analysis and Recognition, Seoul, Korea, pp. 610-614, August 2005.
  14. Hasan Fleyeh, Traffic and Road Sign Recognition, doctoral thesis, Napier University, 2008.
  15. Usman Zakir, Automatic Road Sign Detection and Recognition, doctoral thesis, Department of Computer Science, Loughborough University, 2011.