Neural Computing and Applications

, Volume 28, Issue 9, pp 2373–2382 | Cite as

Querying out-of-vocabulary words in lexicon-based keyword spotting

  • Joan Puigcerver
  • Alejandro H. Toselli
  • Enrique Vidal


Lexicon-based handwritten text keyword spotting (KWS) has proven to be a faster and more accurate alternative to lexicon-free methods. Nevertheless, since lexicon-based KWS relies on a predefined vocabulary, fixed in the training phase, it does not support queries involving out-of-vocabulary (OOV) keywords. In this paper, we outline previous work aimed at solving this problem and present a new approach based on smoothing the (null) scores of OOV keywords by means of the information provided by “similar” in-vocabulary words. Good results achieved using this approach are compared with previously published alternatives on different data sets.


Keyword spotting Lexicon-based Smoothing Out-of-vocabulary Handwritten text recognition 



This work was partially supported by the Spanish MEC under FPU Grant FPU13/06281, by the Generalitat Valenciana under the Prometeo/2009/014 Project Grant ALMAMATER, and through the EU Projects: HIMANIS (JPICH programme, Spanish grant Ref. PCIN-2015-068) and READ (Horizon-2020 programme, grant Ref. 674943).


  1. 1.
    Almazan J, Gordo A, Fornes A, Valveny E (2013) Handwritten word spotting with corrected attributes. In: 2013 IEEE international conference on computer vision (ICCV), pp 1017–1024. doi: 10.1109/ICCV.2013.130
  2. 2.
    Amengual JC, Vidal E (2000) On the estimation of error-correcting parameters. In: Proceedings 15th international conference on pattern recognition, 2000, vol 2, pp 883–886Google Scholar
  3. 3.
    Fernández D, Lladós J, Fornés A (2011) Handwritten word spotting in old manuscript images using a pseudo-structural descriptor organized in a hash structure. In: Vitri'a J, Sanches JM, Hern'andez M (eds) Pattern recognition and image analysis: Proceedings of 5th Iberian Conference, IbPRIA 2011, Las Palmas de Gran Canaria, Spain, June 8–10. Springer, Berlin, Heidelberg, pp 628–635. doi: 10.1007/978-3-642-21257-4_78
  4. 4.
    Fischer A, Keller A, Frinken V, Bunke H (2012) Lexicon-free handwritten word spotting using character HMMs. Pattern Recognit Lett 33(7):934–942. doi: 10.1016/j.patrec.2011.09.009 Special Issue on Awards from ICPR 2010CrossRefGoogle Scholar
  5. 5.
    Fornés A, Frinken V, Fischer A, Almazán J, Jackson G, Bunke H (2011) A keyword spotting approach using blurred shape model-based descriptors. In: Proceedings of the 2011 workshop on historical document imaging and processing, pp 83–90. ACMGoogle Scholar
  6. 6.
    Frinken V, Fischer A, Manmatha R, Bunke H (2012) A novel word spotting method based on recurrent neural networks. IEEE Trans Pattern Anal Mach Intell 34(2):211–224. doi: 10.1109/TPAMI.2011.113 CrossRefGoogle Scholar
  7. 7.
    Gatos B, Pratikakis I (2009) Segmentation-free word spotting in historical printed documents. In: 10th International conference on document analysis and recognition, 2009. ICDAR’09, pp 271–275. IEEEGoogle Scholar
  8. 8.
    Jelinek F (1998) Statistical methods for speech recognition. MIT Press, CambridgeGoogle Scholar
  9. 9.
    Kneser R, Ney H (1995) Improved backing-off for N-gram language modeling. In: International conference on acoustics, speech and signal processing (ICASSP ’95), vol 1, pp 181–184. IEEE Computer Society, Los Alamitos, CA, USA. doi:
  10. 10.
    Kolcz A, Alspector J, Augusteijn M, Carlson R, Popescu GV (2000) A line-oriented approach to word spotting in handwritten documents. Pattern Anal Appl 3:153–168. doi: 10.1007/s100440070020 CrossRefGoogle Scholar
  11. 11.
    Konidaris T, Gatos B, Ntzios K, Pratikakis I, Theodoridis S, Perantonis SJ (2007) Keyword-guided word spotting in historical printed documents using synthetic data and user feedback. Int J Doc Anal Recognit 9(2–4):167–177CrossRefGoogle Scholar
  12. 12.
    Kumar G, Govindaraju V (2014) Bayesian active learning for keyword spotting in handwritten documents. In: 2014 22nd International conference on pattern recognition (ICPR), pp 2041–2046. IEEEGoogle Scholar
  13. 13.
    Levenshtein VI (1966) Binary codes capable of correcting deletions, insertions and reversals. Sov Phys Dokl 10(8):707–710Google Scholar
  14. 14.
    Manning CD, Raghavan P, Schtze H (2008) Introduction to information retrieval. Cambridge University Press, New YorkCrossRefzbMATHGoogle Scholar
  15. 15.
    Marti UV, Bunke H (2002) The IAM-database: an English sentence database for offline handwriting recognition. Int J Doc Anal Recognit 5(1):39–46. doi: 10.1007/s100320200071 CrossRefzbMATHGoogle Scholar
  16. 16.
    Puigcerver J, Toselli AH, Vidal E (2014) Word-graph and character-lattice combination for KWS in handwritten documents. In: 14th International conference on frontiers in handwriting recognition (ICFHR), pp 181–186Google Scholar
  17. 17.
    Puigcerver J, Toselli AH, Vidal E (2014) Word-graph-based handwriting keyword spotting of out-of-vocabulary queries. In: 22nd International conference on pattern recognition (ICPR), pp 2035–2040Google Scholar
  18. 18.
    Puigcerver J, Toselli AH, Vidal E (2015) A new smoothing method for lexicon-based handwritten text keyword spotting. In: 7th Iberian conference on pattern recognition and image analysis. SpringerGoogle Scholar
  19. 19.
    Rath T, Manmatha R (2007) Word spotting for historical documents. Int J Doc Anal Recognit 9:139–152CrossRefGoogle Scholar
  20. 20.
    Robertson S. (2008) A new interpretation of average precision. In: Proceedings of the international. ACM SIGIR conference on research and development in information retrieval (SIGIR ’08), pp 689–690. ACM, New York, NY, USA. doi:
  21. 21.
    Rodriguez-Serrano JA, Perronnin F (2009) Handwritten word-spotting using hidden markov models and universal vocabularies. Pattern Recognit 42(9):2106–2116. doi: 10.1016/j.patcog.2009.02.005.
  22. 22.
    Rusinol M, Aldavert D, Toledo R, Llados J (2011) Browsing heterogeneous document collections by a segmentation-free word spotting method. In: International conference on document analysis and recognition (ICDAR), pp 63–67. doi: 10.1109/ICDAR.2011.22
  23. 23.
    Shang H, Merrettal T (1996) Tries for approximate string matching. IEEE Trans Knowl Data Eng 8(4):540–547CrossRefGoogle Scholar
  24. 24.
    Toselli AH, Vidal E (2013) Fast HMM-Filler approach for key word spotting in handwritten documents. In: Proceedings of the 12th international conference on document analysis and recognition (ICDAR), pp 501–505Google Scholar
  25. 25.
    Toselli AH, Vidal E (2014) Word-graph based handwriting key-word spotting: impact of word-graph size on performance. In: 11th IAPR international workshop on document analysis systems (DAS), pp 176–180. IEEEGoogle Scholar
  26. 26.
    Toselli AH, Vidal E, Romero V, Frinken V (2013) Word-graph based keyword spotting and indexing of handwritten document images. Technical report, Universitat Politécnica de ValénciaGoogle Scholar
  27. 27.
    Vidal E, Toselli AH, Puigcerver J (2015) High performance query-by-example keyword spotting using query-by-string techniques. In: 2015 13th International conference on document analysis and recognition (ICDAR), pp 741–745. IEEEGoogle Scholar
  28. 28.
    Woodland P, Leggetter C, Odell J, Valtchev V, Young S (1995) The 1994 HTK large vocabulary speech recognition system. In: International conference on acoustics, speech, and signal processing (ICASSP ’95), vol 1, pp 73 –76. doi: 10.1109/ICASSP.1995.479276
  29. 29.
    Wshah S, Kumar G, Govindaraju V (2012) Script independent word spotting in offline handwritten documents based on hidden markov models. In: 2012 International conference on frontiers in handwriting recognition (ICFHR), pp 14–19. doi: 10.1109/ICFHR.2012.264

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  1. 1.PRHLT Research CenterUniversitat Politècnica de ValènciaValenciaSpain

Personalised recommendations