Details
| Original language | English |
|---|---|
| Title of host publication | CHI ´18 |
| Subtitle of host publication | Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 1-11 |
| Number of pages | 11 |
| ISBN (electronic) | 9781450356206 |
| Publication status | Published - 19 Apr 2018 |
| Event | 2018 CHI Conference on Human Factors in Computing Systems, CHI 2018 - Montreal, Canada Duration: 21 Apr 2018 → 26 Apr 2018 |
Abstract
Digital pens emit ink on paper and digitize handwriting. The range of the pen is typically limited to a special writing surface on which the pen's tip is tracked. We present Pentelligence, a pen for handwritten digit recognition that operates on regular paper and does not require a separate tracking device. It senses the pen tip's motions and sound emissions when stroking. Pen motions and writing sounds exhibit complementary properties. Combining both types of sensor data substantially improves the recognition rate. Hilbert envelopes of the writing sounds and mean-filtered motion data are fed to neural networks for majority voting. The results on a dataset of 9408 handwritten digits taken from 26 individuals show that motion+sound outperforms single-sensor approaches at an accuracy of 78.4% for 10 test users. Retraining the networks for a single writer on a dataset of 2120 samples increased the precision to 100% for single handwritten digits at an overall accuracy of 98.3%.
Keywords
- Digit recognition, Digital pen, Handwriting recognition, Neural networks, Sound emissions, Writing motion, Writing sound
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Human-Computer Interaction
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
CHI ´18: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery (ACM), 2018. p. 1-11 131.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Pentelligence
T2 - 2018 CHI Conference on Human Factors in Computing Systems, CHI 2018
AU - Schrapel, Maximilian
AU - Stadler, Max Ludwig
AU - Rohs, Michael
N1 - Publisher Copyright: © 2018 ACM. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2018/4/19
Y1 - 2018/4/19
N2 - Digital pens emit ink on paper and digitize handwriting. The range of the pen is typically limited to a special writing surface on which the pen's tip is tracked. We present Pentelligence, a pen for handwritten digit recognition that operates on regular paper and does not require a separate tracking device. It senses the pen tip's motions and sound emissions when stroking. Pen motions and writing sounds exhibit complementary properties. Combining both types of sensor data substantially improves the recognition rate. Hilbert envelopes of the writing sounds and mean-filtered motion data are fed to neural networks for majority voting. The results on a dataset of 9408 handwritten digits taken from 26 individuals show that motion+sound outperforms single-sensor approaches at an accuracy of 78.4% for 10 test users. Retraining the networks for a single writer on a dataset of 2120 samples increased the precision to 100% for single handwritten digits at an overall accuracy of 98.3%.
AB - Digital pens emit ink on paper and digitize handwriting. The range of the pen is typically limited to a special writing surface on which the pen's tip is tracked. We present Pentelligence, a pen for handwritten digit recognition that operates on regular paper and does not require a separate tracking device. It senses the pen tip's motions and sound emissions when stroking. Pen motions and writing sounds exhibit complementary properties. Combining both types of sensor data substantially improves the recognition rate. Hilbert envelopes of the writing sounds and mean-filtered motion data are fed to neural networks for majority voting. The results on a dataset of 9408 handwritten digits taken from 26 individuals show that motion+sound outperforms single-sensor approaches at an accuracy of 78.4% for 10 test users. Retraining the networks for a single writer on a dataset of 2120 samples increased the precision to 100% for single handwritten digits at an overall accuracy of 98.3%.
KW - Digit recognition
KW - Digital pen
KW - Handwriting recognition
KW - Neural networks
KW - Sound emissions
KW - Writing motion
KW - Writing sound
UR - http://www.scopus.com/inward/record.url?scp=85046949220&partnerID=8YFLogxK
U2 - 10.1145/3173574.3173705
DO - 10.1145/3173574.3173705
M3 - Conference contribution
AN - SCOPUS:85046949220
SP - 1
EP - 11
BT - CHI ´18
PB - Association for Computing Machinery (ACM)
Y2 - 21 April 2018 through 26 April 2018
ER -