Distinguishing text from graphics in on-line handwritten ink

C.M. Bishop; M. Svensen; Geoffrey E. Hinton

doi:10.1109/IWFHR.2004.34

Distinguishing text from graphics in on-line handwritten ink

C.M. Bishop, M. Svensen, Geoffrey E. Hinton

School of Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

We present a system that separates text from graphics strokes in handwritten digital ink. It utilizes not just the characteristics of the strokes, but also the information provided by the gaps between the strokes, as well as the temporal characteristics of the stroke sequence. It is built using machine learning techniques that infer the internal parameters of the system from real digital ink, collected using a tablet PC.

Original language	English
Title of host publication	Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on
Pages	142-147
Number of pages	6
DOIs	https://doi.org/10.1109/IWFHR.2004.34
Publication status	Published - 1 Oct 2004

Keywords / Materials (for Non-textual outputs)

handwriting recognition
image classification
image sequences
learning (artificial intelligence)
text analysis
graphics stroke
machine learning
online handwritten digital ink
stroke sequence
tablet PC
text separation
Computer graphics
Computer science
Control systems
Data mining
Educational institutions
Engines
Ink
Machine learning
Personal digital assistants
Text recognition

Access to Document

10.1109/IWFHR.2004.34

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=1363901

Cite this

@inproceedings{0da0e05458d5412c9662f0e48c421d26,

title = "Distinguishing text from graphics in on-line handwritten ink",

abstract = "We present a system that separates text from graphics strokes in handwritten digital ink. It utilizes not just the characteristics of the strokes, but also the information provided by the gaps between the strokes, as well as the temporal characteristics of the stroke sequence. It is built using machine learning techniques that infer the internal parameters of the system from real digital ink, collected using a tablet PC.",

keywords = "handwriting recognition, image classification, image sequences, learning (artificial intelligence), text analysis, graphics stroke, machine learning, online handwritten digital ink, stroke sequence, tablet PC, text separation, Computer graphics, Computer science, Control systems, Data mining, Educational institutions, Engines, Ink, Machine learning, Personal digital assistants, Text recognition",

author = "C.M. Bishop and M. Svensen and Hinton, {Geoffrey E.}",

year = "2004",

month = oct,

day = "1",

doi = "10.1109/IWFHR.2004.34",

language = "English",

pages = "142--147",

booktitle = "Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on",

}

TY - GEN

T1 - Distinguishing text from graphics in on-line handwritten ink

AU - Bishop, C.M.

AU - Svensen, M.

AU - Hinton, Geoffrey E.

PY - 2004/10/1

Y1 - 2004/10/1

N2 - We present a system that separates text from graphics strokes in handwritten digital ink. It utilizes not just the characteristics of the strokes, but also the information provided by the gaps between the strokes, as well as the temporal characteristics of the stroke sequence. It is built using machine learning techniques that infer the internal parameters of the system from real digital ink, collected using a tablet PC.

AB - We present a system that separates text from graphics strokes in handwritten digital ink. It utilizes not just the characteristics of the strokes, but also the information provided by the gaps between the strokes, as well as the temporal characteristics of the stroke sequence. It is built using machine learning techniques that infer the internal parameters of the system from real digital ink, collected using a tablet PC.

KW - handwriting recognition

KW - image classification

KW - image sequences

KW - learning (artificial intelligence)

KW - text analysis

KW - graphics stroke

KW - machine learning

KW - online handwritten digital ink

KW - stroke sequence

KW - tablet PC

KW - text separation

KW - Computer graphics

KW - Computer science

KW - Control systems

KW - Data mining

KW - Educational institutions

KW - Engines

KW - Ink

KW - Machine learning

KW - Personal digital assistants

KW - Text recognition

U2 - 10.1109/IWFHR.2004.34

DO - 10.1109/IWFHR.2004.34

M3 - Conference contribution

SP - 142

EP - 147

BT - Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on

ER -

Distinguishing text from graphics in on-line handwritten ink

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this