Evaluating Japanese Document Recognition in the Internet/Intranet Environment

Tao, Hong; Wu, Shufang; Srihari, Sargur N.

doi:10.1142/9789812797704_0024

Search citation statements

Order By: Relevance

Paper Sections

Select...

An Experiments On Evaluating Japanese Document Recognition Us1

Citation Types

Supporting

Mentioning

Contrasting

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simple Perl scripts can be written to convert the OCR results into HTML les. More detail description of the experiment can be found in [3].…”

Section: An Experiments On Evaluating Japanese Document Recognition Usmentioning

confidence: 99%

Representing OCRed documents in HTML

Tao

Srihari

Proceedings of the Fourth International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

OCR is an error-prone process. It is time-consuming and expensive t o m a n ually proofread OCR results. The errors remaining in OCRed texts can cause serious problems in reading and understanding if they do not refer to the original image representation. As demonstrated in this paper, a hybrid document which combines symbolic representation and image representation may relieve the problem. If we represent a OCRed document properly in HTML, OCR errors will not have m uch negative eect on the human reading process in a HTML browser and can be corrected by using a HTML authoring tool. Under the approach, an experiment e v aluating a Japanese OCR system developed in CEDAR is also reported in this paper.

show abstract

“…Simple Perl scripts can be written to convert the OCR results into HTML les. More detail description of the experiment can be found in [3].…”

Section: An Experiments On Evaluating Japanese Document Recognition Usmentioning

confidence: 99%