Feature Weight Optimization and Pruning in Historical Text Recognition
2013 (English)In: Advances of Visual Computing: 9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II / [ed] George Bebis, Springer Berlin/Heidelberg, 2013, 98-107 p.Conference paper (Refereed)
In handwritten text recognition, "sliding window" feature extraction represent the visual information contained in written text as feature vector sequences. In this paper, we explore the parameter space of feature weights in search for optimal weights and feature selection using the coordinate descent method. We report a gain of about 5% AUC performance. We use a public dataset for evaluation and also discuss the effects and limitations of "word pruning," a technique in word spotting that is commonly used to boost performance and save computational time.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2013. 98-107 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 8034
handwritten text recognition
Computer Vision and Robotics (Autonomous Systems)
Research subject Computerized Image Analysis
IdentifiersURN: urn:nbn:se:uu:diva-212536DOI: 10.1007/978-3-642-41939-3_10ISI: 000335169000010ISBN: 978-3-642-41939-3ISBN: 978-3-642-41938-6OAI: oai:DiVA.org:uu-212536DiVA: diva2:678242
9th International Symposium, ISVC 2013, July 29-31, 2013, Rethymnon, Crete, Greece
ProjectsFrom Quill to Bytes
FunderSwedish Research Council, 2012-5743