Please use this identifier to cite or link to this item:
Title: A benchmark dataset of online handwritten gurmukhi script words and numerals
Authors: Singh H
Sharma R.K
Kumar R
Verma K
Kumar R
Kumar M.
Keywords: Another benchmark dataset
Gurmukhi script
Online handwriting recognition
Issue Date: 2020
Publisher: Springer
Abstract: This paper presents an online handwritten benchmark dataset (OHWR-Gurmukhi) for Gurmukhi script. TIET, Patiala released the unconstrained online handwriting databases, OHWR-GNumerals and OHWR-GScript, which contain isolated strokes samples produced by 190 writers. The OHWR-GNumerals covers 10 stroke classes and OHWR-GScript covers 95 stroke classes to represent the Gurmukhi character set. For data collection, two data sets of Gurmukhi words have been finalized after having a consultation with language experts in order to collect the balanced stroke samples. The preprocessing methods used to prepare these datasets include: size normalization, removing duplicate points, interpolating missing points and re-sampling. The purpose of this benchmark is to create a common platform and make the benchmark dataset publically available for research endeavors in the area of online handwriting recognition. The dataset is available as supplement at � Springer Nature Singapore Pte Ltd 2020.
URI: 10.1007/978-981-15-4018-9_41
Appears in Collections:Conferences

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.