Trilingual 3D Script Identification and Recognition using Leap Motion Sensor
Document identifier: oai:DiVA.org:ltu-77257
Access full text here:
10.1109/ICDARW.2019.40076Keyword: Natural Sciences,
Computer and Information Sciences,
Computer Sciences,
Naturvetenskap,
Data- och informationsvetenskap,
Datavetenskap (datalogi),
Air-writing,
Leap motion,
Word recognition,
Script Identification,
HMM,
Maskininlärning,
Machine LearningPublication year: 2019Relevant Sustainable Development Goals (SDGs):
The SDG label(s) above have been assigned by OSDG.aiAbstract: Recently, the development of depth sensing technologies such as Leap motion and Microsoft Kinect sensors facilitate a touch-less environment to interact with computers and mobile devices. Several research have been carried out for the air-written text recognition with the help of these devices. However, there are several countries (like India) where multiple scripts are used to write official languages. Therefore, for the development of an effective text recognition system, the script of the text has to be identified first. The task becomes more challenging when it comes to 3D handwriting. Since, the 3D text written in air is consists of single stoke only. This paper presents a 3D script identification and recognition system written in three languages, namely, Hindi, English and Punjabi using Leap motion sensor. In the first stage, script identification was carried out in one of the three language. Next, Hidden Markov Model (HMM) was used to recognize the words. An accuracy of 96.4% was recorded in script identification whereas accuracies of 72.99%, 73.25% and 60.5% were recorded in script identification of Hindi, English and Punjabi scripts, respectively.
Authors
Rajkumar Saini
Luleå tekniska universitet; EISLAB
Other publications
>>
Pradeep Kumar
IIT Roorkee, India
Other publications
>>
Shweta Patidar
IIT Roorkee, India
Other publications
>>
Partha Roy
IIT Roorkee, India
Other publications
>>
Marcus Liwicki
Luleå tekniska universitet; EISLAB
Other publications
>>
Record metadata
Click to view metadata
header:
identifier: oai:DiVA.org:ltu-77257
datestamp: 2021-05-07T23:05:02Z
setSpec: SwePub-ltu
metadata:
mods:
@attributes:
version: 3.7
recordInfo:
recordContentSource: ltu
recordCreationDate: 2019-12-27
identifier:
http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-77257
10.1109/ICDARW.2019.40076
titleInfo:
@attributes:
lang: eng
title: Trilingual 3D Script Identification and Recognition using Leap Motion Sensor
abstract: Recently the development of depth sensing technologies such as Leap motion and Microsoft Kinect sensors facilitate a touch-less environment to interact with computers and mobile devices. Several research have been carried out for the air-written text recognition with the help of these devices. However there are several countries (like India) where multiple scripts are used to write official languages. Therefore for the development of an effective text recognition system the script of the text has to be identified first. The task becomes more challenging when it comes to 3D handwriting. Since the 3D text written in air is consists of single stoke only. This paper presents a 3D script identification and recognition system written in three languages namely Hindi English and Punjabi using Leap motion sensor. In the first stage script identification was carried out in one of the three language. Next Hidden Markov Model (HMM) was used to recognize the words. An accuracy of 96.4% was recorded in script identification whereas accuracies of 72.99% 73.25% and 60.5% were recorded in script identification of Hindi English and Punjabi scripts respectively.
subject:
@attributes:
lang: eng
authority: uka.se
topic:
Natural Sciences
Computer and Information Sciences
Computer Sciences
@attributes:
lang: swe
authority: uka.se
topic:
Naturvetenskap
Data- och informationsvetenskap
Datavetenskap (datalogi)
@attributes:
lang: eng
topic: Air-writing
@attributes:
lang: eng
topic: Leap motion
@attributes:
lang: eng
topic: Word recognition
@attributes:
lang: eng
topic: Script Identification
@attributes:
lang: eng
topic: HMM
@attributes:
lang: swe
authority: ltu
topic: Maskininlärning
genre: Research subject
@attributes:
lang: eng
authority: ltu
topic: Machine Learning
genre: Research subject
language:
languageTerm: eng
genre:
conference/other
vet
note:
Published
5
name:
@attributes:
type: personal
authority: ltu
namePart:
Saini
Rajkumar
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
EISLAB
nameIdentifier:
rajsai
0000-0001-8532-0895
@attributes:
type: personal
namePart:
Kumar
Pradeep
role:
roleTerm: aut
affiliation: IIT Roorkee India
@attributes:
type: personal
namePart:
Patidar
Shweta
role:
roleTerm: aut
affiliation: IIT Roorkee India
@attributes:
type: personal
namePart:
Roy
Partha
role:
roleTerm: aut
affiliation: IIT Roorkee India
@attributes:
type: personal
authority: ltu
namePart:
Liwicki
Marcus
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
EISLAB
nameIdentifier:
marliw
0000-0003-4029-6574
originInfo:
dateIssued: 2019
publisher: IEEE
relatedItem:
@attributes:
type: host
titleInfo:
title: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW)
part:
extent:
start: 24
end: 28
identifier: 978-1-7281-5054-3
@attributes:
type: series
titleInfo:
title: International Conference on Document Analysis and Recognition Workshops (ICDARW)
physicalDescription:
form: print
typeOfResource: text