STROKE EXTRACTION FOR HANDPRINTED CHARACTER RECOGNITION

Files

1995-557-9.pdf (48.29 KB)
1995-557-9.ps.gz (41.03 KB)

Date

1995-04-01

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Many structural pattern recognition methods use straight line segments as features. Others depend on the ability to identify a stroke, or a curve drawn with a single pen down and a single pen up motion. Here a method is presented for identifying linear strokes that does not depend on a structural thinning step. It can be used for character and symbol recognition, and the features can be connected to form curves.

Description

Keywords

Computer Science

Citation

URI

http://hdl.handle.net/1880/46432

Collections

Science Research & Publications

Powered by

Libraries & Cultural Resources

Start Something.

University of Calgary
2500 University Drive NW
Calgary Alberta T2N 1N4
CANADA

Copyright © 2023

The University of Calgary, located in the heart of Southern Alberta, both acknowledges and pays tribute to the traditional territories of the peoples of Treaty 7, which include the Blackfoot Confederacy (comprised of the Siksika, the Piikani, and the Kainai First Nations), the Tsuut’ina First Nation, and the Stoney Nakoda (including Chiniki, Bearspaw, and Goodstoney First Nations). The City of Calgary is also home to the Métis Nation of Alberta (Districts 5 and 6).

The University of Calgary is situated on land Northwest of where the Bow River meets the Elbow River, a site traditionally known as Moh’kins’tsis to the Blackfoot, Wîchîspa to the Stoney Nakoda, and Guts’ists’i to the Tsuut’ina. On this land and in this place we strive to learn together, walk together, and grow together “in a good way.”