A statistically based, highly accurate text-line segmentation method

Author

Liang, Jisheng ; Phillips, Ihsin T. ; Haralick, Robert M.

Author_Institution

Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA

fYear

1999

fDate

20-22 Sep 1999

Firstpage

551

Lastpage

554

Abstract

This paper describes a text-line identification and segmentation technique that is probability based, where all probabilities are estimated from an extensive training set of various kind of measurements of distances between the terminal and non-terminal entities with which the algorithm works. The off-line probabilities estimated in the training then drive all decisions in the on-line segmentation algorithm. On the UW-III database of some 1600 scanned document image pages, having some 105020 text lines, the algorithm identifies and segments 104773 correctly, an accuracy of 99.76%

Keywords

document image processing; image segmentation; probability; statistical analysis; visual databases; UW-III database; document image scanning; probability; statistical analysis; text-line identification; text-line segmentation method; training set; Computer science; Electric variables measurement; Image databases; Image segmentation; Labeling; Partitioning algorithms; Probability; Tellurium;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on

Conference_Location

Bangalore

Print_ISBN

0-7695-0318-7

Type

conf

DOI

10.1109/ICDAR.1999.791847

Filename

791847