Skip to main navigation Skip to search Skip to main content

Segmentation-free keyword spotting framework using dynamic background model

  • SUNY Buffalo
  • Hewlett-Packard

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We propose a segmentation free word spotting framework using Dynamic Background Model. The proposed approach is an extension to our previous work where dynamic background model was introduced and integrated with a segmentation based recognizer for keyword spotting. The dynamic background model uses the local character matching scores and global word level hypotheses scores to separate keywords from non-keywords. We integrate and evaluate this model on Hidden Markov Model (HMM) based segmentation free recognizer which works at line level without any need for word segmentation. We outperform the state of the art line level word spotting system on IAM dataset.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Document Recognition and Retrieval XX
DOIs
StatePublished - 2013
EventDocument Recognition and Retrieval XX - Burlingame, CA, United States
Duration: Feb 5 2013Feb 7 2013

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8658
ISSN (Print)0277-786X

Conference

ConferenceDocument Recognition and Retrieval XX
Country/TerritoryUnited States
CityBurlingame, CA
Period02/5/1302/7/13

Keywords

  • Dynamic Background Model
  • Hidden Markov Model
  • Keyword Spotting

Fingerprint

Dive into the research topics of 'Segmentation-free keyword spotting framework using dynamic background model'. Together they form a unique fingerprint.

Cite this