schliessen

Filtern

 

Bibliotheken

SHOW: Smart Handwriting on Watches

Smart watch is becoming a new gateway through which people stay connected and track everyday activities, and text-entry on it is becoming a frequent need. With the two de facto solutions: tap-on-screen and voice input, text-entry on the watch remains a tedious task because 1. Tap-on-screen is error... Full description

Journal Title: Proceedings of the ACM on Interactive Mobile, Wearable and Ubiquitous Technologies, 08 January 2018, Vol.1(4), pp.1-23
Main Author: Lin, Xinye
Other Authors: Chen, Yixin , Chang, Xiao-Wen , Liu, Xue , Wang, Xiaodong
Format: Electronic Article Electronic Article
Language: English
Subjects:
Quelle: ACM Digital Library (Association for Computing Machinery)
ID: E-ISSN: 2474-9567 ; DOI: 10.1145/3161412
Link: http://dl.acm.org/citation.cfm?id=3161412
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: acm3161412
title: SHOW: Smart Handwriting on Watches
format: Article
creator:
  • Lin, Xinye
  • Chen, Yixin
  • Chang, Xiao-Wen
  • Liu, Xue
  • Wang, Xiaodong
subjects:
  • Accelerometer
  • Gyroscope
  • Handwriting
  • Input Method
  • N-Gram
  • Smart Watches
  • Text Entry
  • Virtual Keyboard
ispartof: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 08 January 2018, Vol.1(4), pp.1-23
description: Smart watch is becoming a new gateway through which people stay connected and track everyday activities, and text-entry on it is becoming a frequent need. With the two de facto solutions: tap-on-screen and voice input, text-entry on the watch remains a tedious task because 1. Tap-on-screen is error prone due to the small screen; 2. Voice input is strongly constrained by the surroundings and suffers from privacy leak. In this paper, we propose SHOW, which enables the user to input as they handwrite on horizontal surfaces, and the only requirement is to use the elbow as the support point. SHOW captures the gyroscope and accelerometer traces and deduces the user's handwriting thereafter. SHOW differs from previous work of gesture recognition in that: 1. it employs a novel rotation injection technique to substantially reduce the effort of data collection; 2. it does not require whole-arm posture, hence is better suited to space-limited places (e.g. vehicles). Our experiments show that SHOW can effectively generate 60 traces from one real handwriting trace and achieve high accuracy at 99.9% when recognizing the 62 different characters written by 10 volunteers. Furthermore, having more screen space after removing the virtual keyboard, SHOW can display 4x candidate words for autocompletion. Aided by the tolerance of character ambiguity and accurate character recognition, SHOW achieves over 70% lower mis-recognition-rate, 43% lower no-response-rate in both daily and general purposed text-entry scenarios, and 33.3% higher word suggestion coverage than the tap-on-screen method using a virtual QWERTY keyboard.
language: eng
source: ACM Digital Library (Association for Computing Machinery)
identifier: E-ISSN: 2474-9567 ; DOI: 10.1145/3161412
fulltext: fulltext
issn:
  • 2474-9567
  • 24749567
url: Link


@attributes
ID1119366395
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid3161412
sourceidacm
recordidTN_acm3161412
sourcesystemOther
dbid
0ACM
1GUFHI
display
typearticle
titleSHOW: Smart Handwriting on Watches
creatorLin, Xinye ; Chen, Yixin ; Chang, Xiao-Wen ; Liu, Xue ; Wang, Xiaodong
ispartofProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 08 January 2018, Vol.1(4), pp.1-23
identifierE-ISSN: 2474-9567 ; DOI: 10.1145/3161412
subjectAccelerometer ; Gyroscope ; Handwriting ; Input Method ; N-Gram ; Smart Watches ; Text Entry ; Virtual Keyboard
descriptionSmart watch is becoming a new gateway through which people stay connected and track everyday activities, and text-entry on it is becoming a frequent need. With the two de facto solutions: tap-on-screen and voice input, text-entry on the watch remains a tedious task because 1. Tap-on-screen is error prone due to the small screen; 2. Voice input is strongly constrained by the surroundings and suffers from privacy leak. In this paper, we propose SHOW, which enables the user to input as they handwrite on horizontal surfaces, and the only requirement is to use the elbow as the support point. SHOW captures the gyroscope and accelerometer traces and deduces the user's handwriting thereafter. SHOW differs from previous work of gesture recognition in that: 1. it employs a novel rotation injection technique to substantially reduce the effort of data collection; 2. it does not require whole-arm posture, hence is better suited to space-limited places (e.g. vehicles). Our experiments show that SHOW can effectively generate 60 traces from one real handwriting trace and achieve high accuracy at 99.9% when recognizing the 62 different characters written by 10 volunteers. Furthermore, having more screen space after removing the virtual keyboard, SHOW can display 4x candidate words for autocompletion. Aided by the tolerance of character ambiguity and accurate character recognition, SHOW achieves over 70% lower mis-recognition-rate, 43% lower no-response-rate in both daily and general purposed text-entry scenarios, and 33.3% higher word suggestion coverage than the tap-on-screen method using a virtual QWERTY keyboard.
languageeng
source
0ACM Digital Library (Association for Computing Machinery)
1KESLI (ACM Digital Library)
version2
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dl.acm.org/citation.cfm?id=3161412$$EView_record_in_ACM
search
creatorcontrib
0Lin, Xinye
1Chen, Yixin
2Chang, Xiao-Wen
3Liu, Xue
4Wang, Xiaodong
titleSHOW: Smart Handwriting on Watches
description

Smart watch is becoming a new gateway through which people stay connected and track everyday activities, and text-entry on it is becoming a frequent need. With the two de facto solutions: tap-on-screen and voice input, text-entry on the watch remains a tedious task because 1. Tap-on-screen is error prone due to the small screen; 2. Voice input is strongly constrained by the surroundings and suffers from privacy leak. In this paper, we propose SHOW, which enables the user to input as they handwrite on horizontal surfaces, and the only requirement is to use the elbow as the support point. SHOW captures the gyroscope and accelerometer traces and deduces the user's handwriting thereafter. SHOW differs from previous work of gesture recognition in that: 1. it employs a novel rotation injection technique to substantially reduce the effort of data collection; 2. it does not require whole-arm posture, hence is better suited to space-limited places (e.g. vehicles). Our experiments show that SHOW can effectively generate 60 traces from one real handwriting trace and achieve high accuracy at 99.9% when recognizing the 62 different characters written by 10 volunteers. Furthermore, having more screen space after removing the virtual keyboard, SHOW can display 4x candidate words for autocompletion. Aided by the tolerance of character ambiguity and accurate character recognition, SHOW achieves over 70% lower mis-recognition-rate, 43% lower no-response-rate in both daily and general purposed text-entry scenarios, and 33.3% higher word suggestion coverage than the tap-on-screen method using a virtual QWERTY keyboard.

subject
0Accelerometer
1Gyroscope
2Handwriting
3Input Method
4N-Gram
5Smart Watches
6Text Entry
7Virtual Keyboard
general
0English
1ACM
210.1145/3161412
3ACM Digital Library
4KESLI (ACM Digital Library)
5ACM Digital Library (Association for Computing Machinery)
sourceidacm
recordidacm3161412
issn
02474-9567
124749567
rsrctypearticle
creationdate2018
addtitleProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
searchscope
0acm_full
1acm1
2acm3
scope
0acm_full
1acm1
2acm3
lsr44$$EView_record_in_ACM
tmp01
0ACM Digital Library (Association for Computing Machinery)
1KESLI (ACM Digital Library)
tmp02
0ACM
1GUFHI
startdate20180108
enddate20180108
lsr40Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 08 January 2018, Vol.1 (4), pp.1-23
doi10.1145/3161412
citationpf 1 pt 23 vol 1 issue 4
sort
titleSHOW: Smart Handwriting on Watches
authorLin, Xinye ; Chen, Yixin ; Chang, Xiao-Wen ; Liu, Xue ; Wang, Xiaodong
creationdate20180108
lso0120180108
facets
frbrgroupid6842118738317078525
frbrtype5
newrecords20180320
languageeng
topic
0Accelerometer
1Gyroscope
2Handwriting
3Input Method
4N-Gram
5Smart Watches
6Text Entry
7Virtual Keyboard
collection
0ACM Digital Library
1KESLI (ACM Digital Library)
prefilterarticles
rsrctypearticles
creatorcontrib
0Lin, Xinye
1Chen, Yixin
2Chang, Xiao-Wen
3Liu, Xue
4Wang, Xiaodong
jtitleProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
creationdate2018
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Lin
1Chen
2Chang
3Liu
4Wang
aufirst
0Xinye
1Yixin
2Xiao-Wen
3Xue
4Xiaodong
auinitX
auinit1X
au
0Lin, Xinye
1Chen, Yixin
2Chang, Xiao-Wen
3Liu, Xue
4Wang, Xiaodong
atitleSHOW: Smart Handwriting on Watches
jtitleProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
risdate20180108
volume1
issue4
spage1
epage23
pages1-23
eissn2474-9567
formatjournal
genrearticle
ristypeJOUR
abstract

Smart watch is becoming a new gateway through which people stay connected and track everyday activities, and text-entry on it is becoming a frequent need. With the two de facto solutions: tap-on-screen and voice input, text-entry on the watch remains a tedious task because 1. Tap-on-screen is error prone due to the small screen; 2. Voice input is strongly constrained by the surroundings and suffers from privacy leak. In this paper, we propose SHOW, which enables the user to input as they handwrite on horizontal surfaces, and the only requirement is to use the elbow as the support point. SHOW captures the gyroscope and accelerometer traces and deduces the user's handwriting thereafter. SHOW differs from previous work of gesture recognition in that: 1. it employs a novel rotation injection technique to substantially reduce the effort of data collection; 2. it does not require whole-arm posture, hence is better suited to space-limited places (e.g. vehicles). Our experiments show that SHOW can effectively generate 60 traces from one real handwriting trace and achieve high accuracy at 99.9% when recognizing the 62 different characters written by 10 volunteers. Furthermore, having more screen space after removing the virtual keyboard, SHOW can display 4x candidate words for autocompletion. Aided by the tolerance of character ambiguity and accurate character recognition, SHOW achieves over 70% lower mis-recognition-rate, 43% lower no-response-rate in both daily and general purposed text-entry scenarios, and 33.3% higher word suggestion coverage than the tap-on-screen method using a virtual QWERTY keyboard.

pubACM
doi10.1145/3161412
date2018-01-08