Segmentation-Based Historical Handwritten Word Spotting Using Document-Specific Local Features
Authors:
- Konstantinos ZagorisKZKonstantinos Zagoris
- Ioannis PratikakisIPIoannis Pratikakis
- Basilis GatosBGBasilis Gatos
- 1 September 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14 (21676445) , 9-14
Abstract
Many word spotting strategies for the modern documents are not directly applicable to historical handwritten documents due to writing styles variety and intense degradation. In this paper, a new method that permits effective word spotting in handwritten documents is presented that relies upon document-specific local features which take into account texture information around representative key points. Experimental work on two historical handwritten datasets using standard evaluation measures shows the improved performance achieved by the proposed methodology.Keywords
This publication has 18 references indexed in Scilit:
- Distinction between handwritten and machine-printed text based on the bag of visual words modelPattern Recognition, 2014
- ON THE INFLUENCE OF WORD REPRESENTATIONS FOR HANDWRITTEN WORD SPOTTING IN HISTORICAL DOCUMENTSInternational Journal of Pattern Recognition and Artificial Intelligence, 2012
- Word Image Retrieval Using Bag of Visual Words2012
- Browsing Heterogeneous Document Collections by a Segmentation-Free Word Spotting Method2011
- Image retrieval systems based on compact shape descriptor and relevance feedback informationJournal of Visual Communication and Image Representation, 2011
- A word spotting framework for historical machine-printed documentsInternational Journal on Document Analysis and Recognition (IJDAR), 2010
- A Document Image Retrieval SystemEngineering Applications of Artificial Intelligence, 2010
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Holistic word recognition for handwritten historical documents2004
- Fuzzy clustering with a fuzzy covariance matrix1978