Dr. Susan E. Hauser Profile

Dr. Susan E. Hauser

Electronics Engineer at National Institutes of Health

SPIE Involvement:

Author

Publications (9)

Proceedings Article | 13 January 2003 Paper

Correcting OCR text by association with historical datasets

Susan Hauser, Jonathan Schlaifer, Tehseen Sabir, Dina Demner-Fushman, Scott Straughan, George Thoma

Proceedings Volume 5010, (2003) https://doi.org/10.1117/12.476046

KEYWORDS: Optical character recognition, Mars, Algorithm development, Databases, Biomedical optics, Telecommunications, Detection and tracking algorithms, Medicine, Software development, Data centers

Read Abstract +

The Medical Article Records System (MARS) developed by the Lister Hill National Center for Biomedical Communications uses scanning, OCR and automated recognition and reformatting algorithms to generate electronic bibliographic citation data from paper biomedical journal articles. The OCR server incorporated in MARS performs well in general, but fares less well with text printed in small or italic fonts. Affiliations are often printed in small italic fonts in the journals processed by MARS. Consequently, although the automatic processes generate much of the citation data correctly, the affiliation field frequently contains incorrect data, which must be manually corrected by verification operators. In contrast, author names are usually printed in large, normal fonts that are correctly converted to text by the OCR server. The National Library of Medicine’s MEDLINE database contains 11 million indexed citations for biomedical journal articles. This paper documents our effort to use the historical author, affiliation relationships from this large dataset to find potential correct affiliations for MARS articles based on the author and the affiliation in the OCR output. Preliminary tests using a table of about 400,000 author/affiliation pairs extracted from the corrected data from MARS indicated that about 44% of the author/affiliation pairs were repeats and that about 47% of newly converted author names would be found in this set. A text-matching algorithm was developed to determine the likelihood that an affiliation found in the table corresponding to the OCR text of the first author was the current, correct affiliation. This matching algorithm compares an affiliation found in the author/affiliation table (found with the OCR text of the first author) to the OCR output affiliation, and calculates a score indicating the similarity of the affiliation found in the table to the OCR affiliation. Using a ground truth set of 519 OCR author/OCR affiliation/correct affiliation triples, the matching algorithm is able to select a correct affiliation for the author 43% of the time with a false positive rate of 6%, a true negative rate of 44% and a false negative rate of 7%. MEDLINE citations with United States affiliations typically include the zip code. In addition to using author names as clues to correct affiliations, we are investigating the value of the OCR text of zip codes as clues to correct USA affiliations. Current work includes generation of an author/affiliation/zipcode table from the entire MEDLINE database and development of a daemon module to implement affiliation selection and matching for the MARS system using both author names and zip codes. Preliminary results from the initial version of the daemon module and the partially filled author/affiliation/zipcode table are encouraging.

Proceedings Article | 21 December 2000 Paper

Pattern matching techniques for correcting low-confidence OCR words in a known context

Glenn Ford, Susan Hauser, Daniel Le, George Thoma

Proceedings Volume 4307, (2000) https://doi.org/10.1117/12.410842

KEYWORDS: Optical character recognition, Associative arrays, Mars, Medicine, Biomedical optics, Algorithm development, Databases, Reliability, Software, Distance measurement

Read Abstract +

Proceedings Article | 21 December 2000 Paper

Approximate string matching algorithms for limited-vocabulary OCR output correction

Thomas Lasko, Susan Hauser

Proceedings Volume 4307, (2000) https://doi.org/10.1117/12.410841

KEYWORDS: Optical character recognition, Associative arrays, Detection and tracking algorithms, Biology, Evolutionary algorithms, Medicine, Data archive systems, Databases, Bismuth, Matrices

Read Abstract +

Proceedings Article | 22 December 1999 Paper

Automated zone correction in bitmapped document images

Susan Hauser, Daniel Le, George Thoma

Proceedings Volume 3967, (1999) https://doi.org/10.1117/12.373499

KEYWORDS: Optical character recognition, Image segmentation, Telecommunications, Biomedical optics, Medicine, Algorithm development, Mars, Image processing, Data conversion, Optical inspection

Read Abstract +

Proceedings Article | 20 August 1999 Paper

Speech recognition for program control and data entry in a production environment

Susan Hauser, Tehseen Sabir, George Thoma

Proceedings Volume 3833, (1999) https://doi.org/10.1117/12.359522

KEYWORDS: Speech recognition, Telecommunications, Mars, Human-machine interfaces, Optical character recognition, Medicine, Biomedical optics, Control systems, Data centers, Data communications

Read Abstract +

Proceedings Article | 1 November 1996 Paper

Performance of RAID as a storage system for Internet image delivery

Susan Hauser, Lewis Berman, George Thoma

Proceedings Volume 2916, (1996) https://doi.org/10.1117/12.257289

KEYWORDS: Internet, Time metrology, Telecommunications, Image retrieval, Image storage, Biomedical optics, Tolerancing, Databases, Prototyping, Medicine

Read Abstract +

Proceedings Article | 12 October 1994 Paper

Optical disk jukebox performance in multi-user applications

Susan Hauser, Gautam Roy, George Thoma

Proceedings Volume 2338, (1994) https://doi.org/10.1117/12.190169

KEYWORDS: Databases, Optical discs, Image storage, Telecommunications, Digital imaging, Internet, Biomedical optics, Optical communications, Prototyping, Interfaces

Read Abstract +

Proceedings Article | 2 September 1993 Paper

Request routing with a backerror propagation network

Susan Hauser, Wayne Hsu, George Thoma

Proceedings Volume 1965, (1993) https://doi.org/10.1117/12.152572

KEYWORDS: Artificial neural networks, Medicine, Biomedical optics, Medical research, Matrix multiplication, Imaging systems, Electronic imaging, Document imaging, Computing systems, Software development

Read Abstract +

Proceedings Article | 2 September 1993 Paper

Using back error propagation networks for automatic document image classification

Susan Hauser, Timothy Cookson, George Thoma

Proceedings Volume 1965, (1993) https://doi.org/10.1117/12.152534

KEYWORDS: Image processing, Artificial neural networks, Binary data, Network architectures, Image segmentation, Image classification, Medicine, Biomedical optics, Telecommunications, Medical research

Read Abstract +

Showing 5 of 9 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years