Document Recognition for a Million Books

Choudhury, Sayeed; DiLauro, Tim; Ferguson, Robert; Droettboom, Michael; Fujinaga, Ichiro

doi:10.1045/march2006-choudhury

Cited by 15 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…">Holistic and/or conceptual analyses (8 works; e.g., Jeanneney, 2006; Leetaru, 2008) Descriptions or development of technological infrastructure (6 works; e.g., Choudhury et al , 2006; Langley & Bloomberg, 2008) Analyses of LSDIs' burgeoning collections (6 works; e.g., Kousha & Thelwall, 2009; Lavoie et al , 2005) …”

Section: The Outlines Of An Absencementioning

confidence: 99%

See 1 more Smart Citation

Conceptualizing large-scale information access efforts: The case for historical context

Jones

2010

Proc. Am. Soc. Info. Sci. Tech.

View full text Add to dashboard Cite

Large-scale digitization initiatives (LSDIs) like Google Book Search and the Open Content Alliance have extraordinary potential to reshape the social world. However, the scholarly community currently lacks adequate conceptualizations to describe these phenomena and assess what they might portend. This paper examines the current state of the literature on LSDIs, finding hundreds of related articles and documents -only a fraction of which add to the conceptualization process. It then describes one way forward in developing a holistic concept of LSDIs upon which to ground further study: by placing them in historical context, as efforts to democratize access to information.

show abstract

Section: The Outlines Of An Absencementioning

confidence: 99%

“…Descriptions or development of technological infrastructure (6 works; e.g., Choudhury et al , 2006; Langley & Bloomberg, 2008)…”

Section: The Outlines Of An Absencementioning

confidence: 99%

Conceptualizing large-scale information access efforts: The case for historical context

Jones

2010

Proc. Am. Soc. Info. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…The basic characteristic of these documents is that there is no space between two consecutive words. In [4] an open-source programming framework is introduced for building systems that extract information from digitized historical documents empowering the document experts themselves to develop systems with reduced effort. In [19], a complete OCR methodology for recognizing historical documents, either printed or handwritten without any knowledge of the font, is presented.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive evaluation methodology for noisy historical document recognition techniques

Stamatopoulos

Louloudis

Gatos

2009

Proceedings of the Third Workshop on Analytics for Noisy Unstructured Text Data

View full text Add to dashboard Cite

In this paper, we propose a new comprehensive methodology in order to evaluate the performance of noisy historical document recognition techniques. We aim to evaluate not only the final noisy recognition result but also the main intermediate stages of text line, word and character segmentation. For this purpose, we efficiently create the text line, word and character segmentation ground truth guided by the transcription of the historical documents. The proposed methodology consists of (i) a semiautomatic procedure in order to detect the text line, word and character segmentation ground truth regions making use of the correct document transcription, (ii) calculation of proper evaluation metrics in order to measure the performance of the final OCR result as well as of the intermediate segmentation stages. The semi-automatic procedure for detecting the ground truth regions has been evaluated and proved efficient and time saving. Experimental results prove that using the proposed technique, the percentage of time saved for the text line, word and character segmentation ground truth creation is more than 90%. An analytic experiment using a commercial OCR engine applied to a historical book is also presented.

show abstract

“…The basic characteristic of these documents is that there is no space between two consecutive words. Choudhury et al [8] introduces an open-source programming framework for building systems that extract information from digitized historical documents empowering the document experts themselves to develop systems with reduced effort [9] [10].…”

Section: Introductionmentioning

confidence: 99%