High performance Query-by-Example keyword spotting using Query-by-String techniques
Authors:
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 741-745
Abstract
Keyword Spotting (KWS) has been traditionally considered under two distinct frameworks: Query-by-Example (QbE) and Query-by-String (QbS). In both cases the user of the system wished to find occurrences of a particular keyword in a collection of document images. The difference is that, in QbE, the keyword is given as an exemplar image while, in QbS the keyword is given as a text string. In several works, the QbS scenario has been approached using QbE techniques; but the converse has not been studied in depth yet, despite of the fact that QbS systems typically achieve higher accuracy. In the present work, we present a very effective probabilistic approach to QbE KWS, based on highly accurate QbS KWS techniques which rely on models which need to be trained from annotated data. To assess the effectiveness of this approach, we tackle the segmentation-free QbE task of the ICFHR-2014 Competition on Handwritten KWS. Our approach achieves a mean average precision (mAP) as high as 0.715, which improves by more than 70% the best mAP achieved in this competition (0.419 under the same experimental conditions).Keywords
This publication has 28 references indexed in Scilit:
- A keyword spotting approach using blurred shape model-based descriptors2011
- Browsing Heterogeneous Document Collections by a Segmentation-Free Word Spotting Method2011
- Handwritten Word Spotting in Old Manuscript Images Using a Pseudo-structural Descriptor Organized in a Hash StructureLecture Notes in Computer Science, 2011
- Accessing the content of Greek historical documents2009
- Segmentation-free Word Spotting in Historical Printed Documents2009
- Efficient Search in Document Image Collections2007
- Keyword-guided word spotting in historical printed documents using synthetic data and user feedbackInternational Journal on Document Analysis and Recognition (IJDAR), 2007
- Text line segmentation of historical documents: a surveyInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- Word spotting for historical documentsInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- A Line-Oriented Approach to Word Spotting in Handwritten DocumentsPattern Analysis and Applications, 2000