Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners

Graham Leedham; Vladimir Pervouchine; Wei Kei Tan; Arun Jacob

Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners

Graham Leedham
, Vladimir Pervouchine
, Wei Kei Tan
, Arun Jacob

Computer Science

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

Abstract

In this paper we examine tile automatic extraction of visual or structural features as used by document examiners in the comparison of handwriting samples. We have extracted between 7 and 14 different features from four letters ("y", "d", "f" and "t"). This analysis was earned out on a total of 3077 letters from 30 different writers. On average these features are extracted with about 88% accuracy and can be used to assess the similarity of different writing samples.

Original language	English
Title of host publication	Proceedings of the 11th Conference of the International Graphonomics Society (IGS 2003)
Editors	HL Teulings, AWA Van Gemmert
Place of Publication	Tempe, United States of America
Publisher	NeuroScript
Pages	291-294
ISBN (Print)	0974636509
Publication status	Published - 2003
Event	IGS 2003: 11th Conference of the International Graphonomics Society - Connecting Sciences Using Graphonomic Research - Scottsdale, United States of America Duration: 2 Nov 2003 → 5 Nov 2003

Conference

Conference	IGS 2003: 11th Conference of the International Graphonomics Society - Connecting Sciences Using Graphonomic Research
City	Scottsdale, United States of America
Period	2/11/03 → 5/11/03

Keywords

Computer Vision
Image Processing
Artificial Intelligence and Image Processing

Access to Document

https://hdl.handle.net/1959.11/6655

Handle.net

Persistent link

Cite this

@inproceedings{f637f96866004c3b8518fca7e6589966,

title = "Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners",

abstract = "In this paper we examine tile automatic extraction of visual or structural features as used by document examiners in the comparison of handwriting samples. We have extracted between 7 and 14 different features from four letters ({"}y{"}, {"}d{"}, {"}f{"} and {"}t{"}). This analysis was earned out on a total of 3077 letters from 30 different writers. On average these features are extracted with about 88\% accuracy and can be used to assess the similarity of different writing samples.",

keywords = "Computer Vision, Image Processing, Artificial Intelligence and Image Processing",

author = "Graham Leedham and Vladimir Pervouchine and Tan, \{Wei Kei\} and Arun Jacob",

year = "2003",

language = "English",

isbn = "0974636509",

pages = "291--294",

editor = "HL Teulings and \{Van Gemmert\}, AWA",

booktitle = "Proceedings of the 11th Conference of the International Graphonomics Society (IGS 2003)",

publisher = "NeuroScript",

note = "IGS 2003: 11th Conference of the International Graphonomics Society - Connecting Sciences Using Graphonomic Research ; Conference date: 02-11-2003 Through 05-11-2003",

}

Leedham, G, Pervouchine, V, Tan, WK & Jacob, A 2003, Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners. in HL Teulings & AWA Van Gemmert (eds), Proceedings of the 11th Conference of the International Graphonomics Society (IGS 2003). NeuroScript, Tempe, United States of America, pp. 291-294, IGS 2003: 11th Conference of the International Graphonomics Society - Connecting Sciences Using Graphonomic Research, Scottsdale, United States of America, 2/11/03. <https://hdl.handle.net/1959.11/6655>

Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners. / Leedham, Graham; Pervouchine, Vladimir; Tan, Wei Kei et al.
Proceedings of the 11th Conference of the International Graphonomics Society (IGS 2003). ed. / HL Teulings; AWA Van Gemmert. Tempe, United States of America: NeuroScript, 2003. p. 291-294.

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

TY - GEN

T1 - Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners

AU - Leedham, Graham

AU - Pervouchine, Vladimir

AU - Tan, Wei Kei

AU - Jacob, Arun

PY - 2003

Y1 - 2003

N2 - In this paper we examine tile automatic extraction of visual or structural features as used by document examiners in the comparison of handwriting samples. We have extracted between 7 and 14 different features from four letters ("y", "d", "f" and "t"). This analysis was earned out on a total of 3077 letters from 30 different writers. On average these features are extracted with about 88% accuracy and can be used to assess the similarity of different writing samples.

AB - In this paper we examine tile automatic extraction of visual or structural features as used by document examiners in the comparison of handwriting samples. We have extracted between 7 and 14 different features from four letters ("y", "d", "f" and "t"). This analysis was earned out on a total of 3077 letters from 30 different writers. On average these features are extracted with about 88% accuracy and can be used to assess the similarity of different writing samples.

KW - Computer Vision

KW - Image Processing

KW - Artificial Intelligence and Image Processing

UR - http://www.graphonomics.org/igs2003/

UR - http://www3.ntu.edu.sg/SCE/labs/forse/PDF/docExam_8.pdf

M3 - Conference contribution

SN - 0974636509

SP - 291

EP - 294

BT - Proceedings of the 11th Conference of the International Graphonomics Society (IGS 2003)

A2 - Teulings, HL

A2 - Van Gemmert, AWA

PB - NeuroScript

CY - Tempe, United States of America

T2 - IGS 2003: 11th Conference of the International Graphonomics Society - Connecting Sciences Using Graphonomic Research

Y2 - 2 November 2003 through 5 November 2003

ER -

Automatic Quantitative Letter-level Extraction of Features Used by Document Examiners

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this