Vector Model Based Indexing and Retrieval of Handwritten Medical Forms

Author

Cao, Huaigu ; Govindaraju, Venu

Author_Institution

Univ. at Buffalo, Buffalo

Volume

1

fYear

2007

fDate

23-26 Sept. 2007

Firstpage

88

Lastpage

92

Abstract

A vector model based information retrieval of handwritten medical forms is presented in this paper. In order to improve the IR performance on the erroneous output of handwriting recognition (HR) systems, a variation of the vector model is made to estimate the number of occurrences of terms from word segmentation and recognition probabilities. IR Tests show that our approach outperforms the retrieval of ordinary HR text in terms of mean average precision (MAP), R-Precision, and interpolated 11-point precisions.

Keywords

handwriting recognition; image recognition; image segmentation; information retrieval; medical computing; medical information systems; probability; handwriting recognition system; handwritten medical form retrieval; vector model based indexing; word image segmentation; word recognition probability; Frequency; Handwriting recognition; Image databases; Image recognition; Image retrieval; Image segmentation; Indexing; Information retrieval; Medical services; Optical character recognition software;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on

Conference_Location

Parana

ISSN

1520-5363

Print_ISBN

978-0-7695-2822-9

Type

conf

DOI

10.1109/ICDAR.2007.4378681

Filename

4378681