Total views : 261

Search Space Reduction in Printed Persian Sub Word Recognition by a Heretical Method

Affiliations

  • University of Birjand, Birjand,, Iran, Islamic Republic of

Abstract


Objective: In this paper, the search domain of Farsi printed subwords is intensively reduced by a simple and effective method. Methods: At first, the search space has limited to some selective clusters by using simple extraction feature of horizontal and vertical profiles. Results: The proposed method determined the ratio of the sub word width to the sub word height and confines the search range to this ratio. Finally, the subwords symbol positions are as the same as the input subwords. It is explored according to the symbol position. Conclusion: Applying the proposed model, the search space is effectively reduced.

Keywords

Heretical Method, Persian Sub Word, Search Space Reduction

Full Text:

 |  (PDF views: 202)

References


  • Adamek NE, Smeaton AF. Word matching using single closed contours for indexing handwritten historical documents. International Journal of Document Analysis and Recognition. 2007; 9(2):153–65. Available from: https://doi.org/10.1007/s10032-006-0024-y
  • Pinales JR, Rivas RJ, Bleda MC. Holistic cursive word recognition based on perceptual features. Pattern Recognition Letters. 2007; 28:1600–9. Available from: https://doi.org/10.1016/j.patrec.2007.03.017
  • Amin A. Recognition of printed arabic text based on global features and decision tree learning techniques. Pattern Recognition. 2000; 33:1309–23. Available from: https://doi.org/10.1016/S0031-3203(99)00114-4
  • Ebrahimi A. Using of overall shape subwords documentary image retrieval and recognition of texts printed in persian [PhD thesis]. Tehran, Iran: University of Tarbiat Modares; 2005. (In Farsi).
  • Khosravi H. Evaluation of Persian texts based on shape recognition subwords. 2011; 7:267–80. (In Farsi).
  • Madhvanath S, Kim G, Govindaraju V. Chain code contour processing for handwritten word recognition.
  • IEEE Transactions on Pattern Recognition and Machine Intelligence. 1999; 21:928–32. Available from: https://doi.org/10.1109/34.790433
  • Zagoris K, Ergina K, Papamarkos N. A document image retrieval system. Engineering Application of Artificial Intelligence. 2010; 23:872–9. Available from: https://doi.org/10.1016/j.engappai.2010.03.002
  • Bai S, Li L, Tan CL. Keyword spotting in document images through word shape coding. Proceedings of 10th International Conference on Document Analysis and Recognition, ICDAR’09; 2009. p. 331–5. Available from: https://doi.org/10.1109/icdar.2009.54
  • LiL, Lu S, Tan CL. A fast keyword-spotting technique.Proceedings of 9th International Conference on Document Analysis and Recognition, ICDAR’07; 2007. p. 68–72.
  • Lu S, Tan CL. Document image retrieval through word shape coding. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2008; 30:1913–8.
  • Rodriguez-Serrano JA, Perronnin F. Handwritten word spotting using hidden markov models and vocabularies. Pattern Recognition. 2009; 42:2106–16. Available from: https://doi.org/10.1016/j.patcog.2009.02.005
  • RathTM, Manmatha R. Word spotting for historical documents. International Journal of Document Analysis and Recognition (IJDAR). 2007; 9(2):139–52. Available from: https://doi.org/10.1007/s10032-006-0027-8
  • LuY, Tan CL. Information retrieval in document image databases. IEEE Transactions on knowledge and Data Engineering. 2004; 16:1398–410. Available from: https:// doi.org/10.1109/TKDE.2004.76
  • Ebrahimi A, Kabir E. A pictorial dictionary for printed farsi sub words. Pattern Recognition Letters. 2008; 29:656–63. Available from: https://doi.org/10.1016/j.patrec.2007.11.008
  • Rafe V, Nozari M. An efficient indexing approach to find quranic symbols in large texts. Indian Journal of Science and Technology. 2014; 7(10):1643–9.
  • Madhvanath SG, Govindaraju V. The role of holistic paradigms in handwritten word recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2001; 23:149–64. Available from: https://doi.
  • org/10.1109/34.908966
  • Lorigo LM, Govindaraju V. Off- line arabic handwriting recognition: A survey. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2008; 28:712–24. Available from: https://doi.org/10.1109/TPAMI.2006.102
  • Davoudi H, Kabir E. Lexicon reduction for printed Farsi sub words using pictorial and textual dictionaries. IJDAR. 2014; 17(4):359–74. Available from: https://doi.org/10.1007/ s10032-014-0223-x
  • Fthi F. Extract the index letters from printed persian subword [MS thesis]. Iran: Sahand Industrial University of Tabriz; 2010. (In Farsi).
  • Alibigi M. Recognition Persian printed sub word [MS thesis]. Iran: University of Birjand; 2010. (In Farsi).

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.