A study of Bag-of-Visual-Words representations for handwritten keyword spotting

David Aldavert, Marçal Rusiñol, Ricardo Toledo, Josep Lladós

Research output: Contribution to journalArticleResearchpeer-review

44 Citations (Scopus)


© 2015, Springer-Verlag Berlin Heidelberg. The Bag-of-Visual-Words (BoVW) framework has gained popularity among the document image analysis community, specifically as a representation of handwritten words for recognition or spotting purposes. Although in the computer vision field the BoVW method has been greatly improved, most of the approaches in the document image analysis domain still rely on the basic implementation of the BoVW method disregarding such latest refinements. In this paper, we present a review of those improvements and its application to the keyword spotting task. We thoroughly evaluate their impact against a baseline system in the well-known George Washington dataset and compare the obtained results against nine state-of-the-art keyword spotting methods. In addition, we also compare both the baseline and improved systems with the methods presented at the Handwritten Keyword Spotting Competition 2014.
Original languageEnglish
Pages (from-to)223-234
JournalInternational Journal on Document Analysis and Recognition
Issue number3
Publication statusPublished - 19 Sept 2015


  • Bag-of-Visual-Words
  • Handwritten documents
  • Keyword spotting
  • Performance evaluation


Dive into the research topics of 'A study of Bag-of-Visual-Words representations for handwritten keyword spotting'. Together they form a unique fingerprint.

Cite this