Filters








651 Hits in 3.6 sec

Mathematical formula recognition using graph grammar

Stephane Lavirotte, Loic Pottier, Daniel P. Lopresti, Jiangying Zhou
1998 Document Recognition V  
This paper describes current results of Ofr (Optical Formula Recognition), a system for extracting and understanding mathematical expressions in documents.  ...  We currently also study use of this system for direct input of formulas with a graphical tablet for computer algebra system softwares.  ...  Firstly, a sheet can contains many formulas, and a bottom-up approach allow local treatment of the sheet.  ... 
doi:10.1117/12.304644 dblp:conf/drr/LavirotteP98 fatcat:gdau4f5dv5ec5l2kxfih33shcq

Towards a Parser for Mathematical Formula Recognition [chapter]

Amar Raja, Matthew Rayner, Alan Sexton, Volker Sorge
2006 Lecture Notes in Computer Science  
A robust system for this task needs to combine low level character recognition with higher level structural analysis of mathematical formulas.  ...  We present progress towards this goal by extending a database-driven optical character recognition system for mathematics with two high level analysis features.  ...  Most such systems, when used for mathematical formula recognition, restrict the replacement fragment to be a simple node.  ... 
doi:10.1007/11812289_12 fatcat:oi2tcazwrvd7bfx7aemvibrcc4

Mathematical Formulae Recognition Using 2D Grammars

D. Pru_a, D. Pru_a, V. Hlavac, V. Hlavac
2007 Proceedings of the International Conference on Document Analysis and Recognition  
We present a method for off-line mathematical formulae recognition based on the structural construction paradigm and two-dimensional grammars.  ...  This allows the system to avoid errors usually appearing during the segmentation phase.  ...  Schlesinger from the Ukrainian Academy of Sciences in Kiev for discussions on the issue.  ... 
doi:10.1109/icdar.2007.4377035 dblp:conf/icdar/PrusaH07 fatcat:5raqarvtnbbvbpzvuhq22ic5i4

Extraction of Logical Structure from Articles in Mathematics [chapter]

Koji Nakagawa, Akihiro Nomura, Masakazu Suzuki
2004 Lecture Notes in Computer Science  
We implemented this method in INFTY which is an integrated OCR system for mathematical documents.  ...  By the browser printed mathematical documents can be scanned and recognized by OCR (Optical Character Recognition).  ...  Especially recognition of mathematical formulae is the most important in recognizing mathematical documents. The mathematical formulae recognition has been well investigated [8] .  ... 
doi:10.1007/978-3-540-27818-4_20 fatcat:bljntj4l5nb6bn3bhkv2pcvfqu

Comparing Approaches to Mathematical Document Analysis from PDF

Josef B. Baker, Alan P. Sexton, Volker Sorge, Masakazu Suzuki
2011 2011 International Conference on Document Analysis and Recognition  
One uses an OCR approach for character recognition together with a virtual link network for structural analysis.  ...  Document analysis of mathematical texts is a challenging problem even for born-digital documents in standard formats.  ...  ACKNOWLEDGMENT We thank the Royal Society for their support through the International Joint Project 2008/R3.  ... 
doi:10.1109/icdar.2011.99 dblp:conf/icdar/BakerSSS11 fatcat:snqynbc4yje3ldz3hbxic3rhoi

Probabilistic Mathematical Formula Recognition Using a 2D Context-Free Graph Grammar

Mehmet Celik, Berrin Yanikoglu
2011 2011 International Conference on Document Analysis and Recognition  
We present a probabilistic framework for the mathematical expression recognition problem.  ...  The developed system is flexible in that its grammar can be extended easily thanks to its graph grammar which eliminates the need for specifying rule precedence.  ...  We thank the reviewers for their useful suggestions and criticism.  ... 
doi:10.1109/icdar.2011.41 dblp:conf/icdar/CelikY11 fatcat:xson45doijcgvmvvtcxcu5ewly

Optical Character Recognition and Parsing of Typeset Mathematics1

Richard J. Fateman, Taku Tokuyasu, Benjamin P. Berman, Nicholas Mitchell
1996 Journal of Visual Communication and Image Representation  
We h a ve a l s o d e v eloped routines for rapid access to this information, speci cally for nding matches with formulas in a table of integrals.  ...  Our work intends to encode, for use by computer algebra systems, integral tables and other documents currently available in hardcopy only.  ...  For access to these programs, contact R. Fateman (fateman@cs.berkeley.edu).  ... 
doi:10.1006/jvci.1996.0002 fatcat:llyu2ae2lzbu7fzymfouajx76a

Practical Segmentation Methods for Logical and Geometric Layout Analysis to Improve Scanned PDF Accessibility to Vision Impaired

Azadeh Nazemi, Iain Murray, David A. Mc Meekin
2014 International Journal of Signal Processing, Image Processing and Pattern Recognition  
A scanned PDF is an image and does not actually contain any text. For the vision-impaired user who is dependent upon a screen reader to access this information, this format is not useful.  ...  Accurate tagging produces a searchable and navigable scanned PDF document.  ...  In order to design affordable, stand-aloneand simple to use software/hardware embedded system for reading electronic documents to vision impaired further development contains running these scripts in System  ... 
doi:10.14257/ijsip.2014.7.4.03 fatcat:off6b6jljbhtvml3yfatbo5cv4

Digitization Workflow in the Czech Digital Mathematics Library [chapter]

Petr Sojka
2014 Computer Mathematics  
Experience in setting up a workflow from scanned images of mathematical writings into a fully fledged mathematical library is described on the example of the project Czech Digital Mathematics Library DML-CZ  ...  An overview of the whole process is given, with detailed description of production steps involving scanned image processing and optical character recognition.  ...  The FINEREADER software development kit (SDK for Windows version 8.1) was used to develop a part of the system for the location and recognition of page numbers, and a batch system DML-CZ OCR [19, 22]  ... 
doi:10.1007/978-3-662-43799-5_13 dblp:conf/ascm/Sojka09 fatcat:avkdppxfqbaujm475nvk5kkubi

How to find mathematics on a scanned page

Richard J. Fateman, Daniel P. Lopresti, Jiangying Zhou
1999 Document Recognition and Retrieval VII  
We e xplore the extent to which this separation can be automated in the context of scanning archival material for a digital library project including mathematical and scienti c journal material.  ...  The second stream, consisting of material judged to be mathematics, can be fed to a specialized recognizer.  ...  In the absence of special mathematics recognition, the natural fall-back position for an OCR system is to try to decode math as ordinary text, and provide whatever is closest to (some) text within that  ... 
doi:10.1117/12.373482 dblp:conf/drr/Fateman00 fatcat:5wertancujbm5mant7q5hbyzey

Converting Optically Scanned Regular or Irregular Tables to a Standardised Markup Format to be Accessible to Vision-Impaired

Azadeh Nazemi, Iain Murray, Chandrika Fernaando, David MacMeekin
2016 World Journal of Education  
output is in mark-up format and provides navigation ability to access content of a table.  ...  The lack of access to table contents limits educational and workplace opportunities for people with vision impairment. They require a complete equivalent to access table.  ...  A table may contain different kinds of objects such as text, graphics and mathematical formula (Watanabe, Luo, & Sugie, 1995) , (Tsuruoka, Takao, Tanaka, Yoshikawa, & Shinogi, 2001) .  ... 
doi:10.5430/wje.v6n5p9 fatcat:pxfcpgi3vnellkc4kpltyk6qgm

Historical document digitization through layout analysis and deep content classification

Andrea Corbelli, Lorenzo Baraldi, Costantino Grana, Rita Cucchiara
2016 2016 23rd International Conference on Pattern Recognition (ICPR)  
Our layout analysis method merges a classic top-down approach and a bottom-up classification process based on local geometrical features, while regions are classified by means of features extracted from  ...  Document layout segmentation and recognition is an important task in the creation of digitized documents collections, especially when dealing with historical documents.  ...  There are two main approaches to this task, namely bottom up and top down.  ... 
doi:10.1109/icpr.2016.7900272 dblp:conf/icpr/CorbelliBGC16 fatcat:qhpnmbhdrzdnppxxq7hert7ule

A Survey and Comparative Evaluation of Selected off-line Arabic handwritten Character Recognition Systems

Kasmiran Jumari, Mohamed A. Ali
2002 Jurnal Teknologi  
In this study we tried to cover the Optical Character Recognition (OCR) systems used for off-line Arabic Optical Text Recognition (AOTR). We cast some light on the characteristics of Arabic writing.  ...  In addition, evaluation methods for different AOTR systems are presented.  ...  Nevertheless, there are some systems designed for recognition of isolated characters (Simon, 1991 and Saadallah and Yacu, 1985) and handwritten mathematical formulas (El-Sheikh, 1990 and .  ... 
doi:10.11113/jt.v36.584 fatcat:n3fn7lmbr5exnkrvzygr2ngmlq

Development of a Gold-standard Pashto Dataset and a Segmentation App

Yan Han, Marek Rychlik
2021 Information Technology and Libraries  
The app can also be used for Persian and other languages using the Arabic writing system.  ...  The dataset can be used for OCR training, OCR testing, and machine learning applications related to content in Pashto.  ...  We are also using this dataset to train and evaluate our current OCR algorithms with RNN and other ML models.  ... 
doi:10.6017/ital.v40i1.12553 fatcat:nnpwn3ep2zd4rdz75wsghdgek4

A Linear Grammar Approach to Mathematical Formula Recognition from PDF [chapter]

Josef B. Baker, Alan P. Sexton, Volker Sorge
2009 Lecture Notes in Computer Science  
Many approaches have been proposed over the years for the recognition of mathematical formulae from scanned documents. More recently a need has arisen to recognise formulae from PDF documents.  ...  The simplicity of the original method leads to a very efficient recognition technique that not only is very simple to implement but also yields results of high accuracy for the recognition of mathematical  ...  Enclosing symbols: These pose a traditional problem for OCR systems.  ... 
doi:10.1007/978-3-642-02614-0_19 fatcat:g6si7jah3vgyljkxbg4ozxhk2m
« Previous Showing results 1 — 15 out of 651 results