Handwritten character skeletonisation for forensic document analysis

Vladimir Pervouchine; Graham Leedham; Konstantin Melikhov

doi:10.1145/1066677.1066850

Handwritten character skeletonisation for forensic document analysis

Vladimir Pervouchine
, Graham Leedham
, Konstantin Melikhov

Computer Science

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

27 Citations (Scopus)

Abstract

A new method of skeletonisation (stroke extraction) of handwritten character images is presented. The method has been designed to extract the skeleton which is very close to human perception of the original pen tip trajectory. The need in such skeletonisation arises from feature extraction algorithms which are sensitive to inaccuracies in positions of skeleton curves. One class of such algorithms are those for extraction of features used in forensic analysis of handwriting. The skeleton is constructed in three steps directly from the grayscale image and is represented as a set of curves, which, in turn, are represented as cubic B-splines. Such representation also eases feature extraction. Experiments have been performed on 150 images of grapheme "th" written by different writers. The assessment of the skeletonisation results are presented.

Original language	English
Title of host publication	Proceedings of the 2005 ACM Symposium on Applied Computing
Place of Publication	New York, United States of America
Publisher	Association for Computing Machinery (ACM)
Pages	754-758
Volume	1
ISBN (Print)	1581139640
DOIs	https://doi.org/10.1145/1066677.1066850
Publication status	Published - 2005
Event	SAC 2005: 20th Annual ACM Symposium on Applied Computing - Santa Fe, United States of America Duration: 13 Mar 2005 → 17 Mar 2005

Conference

Conference	SAC 2005: 20th Annual ACM Symposium on Applied Computing
City	Santa Fe, United States of America
Period	13/03/05 → 17/03/05

Keywords

Image Processing
Computer Vision

Access to Document

10.1145/1066677.1066850

https://hdl.handle.net/1959.11/6663

Handle.net

Persistent link

Cite this

@inproceedings{22d3af9d0fdb4860b8343d58bed33858,

title = "Handwritten character skeletonisation for forensic document analysis",

abstract = "A new method of skeletonisation (stroke extraction) of handwritten character images is presented. The method has been designed to extract the skeleton which is very close to human perception of the original pen tip trajectory. The need in such skeletonisation arises from feature extraction algorithms which are sensitive to inaccuracies in positions of skeleton curves. One class of such algorithms are those for extraction of features used in forensic analysis of handwriting. The skeleton is constructed in three steps directly from the grayscale image and is represented as a set of curves, which, in turn, are represented as cubic B-splines. Such representation also eases feature extraction. Experiments have been performed on 150 images of grapheme {"}th{"} written by different writers. The assessment of the skeletonisation results are presented.",

keywords = "Image Processing, Computer Vision",

author = "Vladimir Pervouchine and Graham Leedham and Konstantin Melikhov",

year = "2005",

doi = "10.1145/1066677.1066850",

language = "English",

isbn = "1581139640",

volume = "1",

pages = "754--758",

booktitle = "Proceedings of the 2005 ACM Symposium on Applied Computing",

publisher = "Association for Computing Machinery (ACM)",

note = "SAC 2005: 20th Annual ACM Symposium on Applied Computing ; Conference date: 13-03-2005 Through 17-03-2005",

}

Pervouchine, V, Leedham, G & Melikhov, K 2005, Handwritten character skeletonisation for forensic document analysis. in Proceedings of the 2005 ACM Symposium on Applied Computing. vol. 1, Association for Computing Machinery (ACM), New York, United States of America, pp. 754-758, SAC 2005: 20th Annual ACM Symposium on Applied Computing, Santa Fe, United States of America, 13/03/05. https://doi.org/10.1145/1066677.1066850

Handwritten character skeletonisation for forensic document analysis. / Pervouchine, Vladimir; Leedham, Graham; Melikhov, Konstantin.
Proceedings of the 2005 ACM Symposium on Applied Computing. Vol. 1 New York, United States of America: Association for Computing Machinery (ACM), 2005. p. 754-758.

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

TY - GEN

T1 - Handwritten character skeletonisation for forensic document analysis

AU - Pervouchine, Vladimir

AU - Leedham, Graham

AU - Melikhov, Konstantin

PY - 2005

Y1 - 2005

N2 - A new method of skeletonisation (stroke extraction) of handwritten character images is presented. The method has been designed to extract the skeleton which is very close to human perception of the original pen tip trajectory. The need in such skeletonisation arises from feature extraction algorithms which are sensitive to inaccuracies in positions of skeleton curves. One class of such algorithms are those for extraction of features used in forensic analysis of handwriting. The skeleton is constructed in three steps directly from the grayscale image and is represented as a set of curves, which, in turn, are represented as cubic B-splines. Such representation also eases feature extraction. Experiments have been performed on 150 images of grapheme "th" written by different writers. The assessment of the skeletonisation results are presented.

AB - A new method of skeletonisation (stroke extraction) of handwritten character images is presented. The method has been designed to extract the skeleton which is very close to human perception of the original pen tip trajectory. The need in such skeletonisation arises from feature extraction algorithms which are sensitive to inaccuracies in positions of skeleton curves. One class of such algorithms are those for extraction of features used in forensic analysis of handwriting. The skeleton is constructed in three steps directly from the grayscale image and is represented as a set of curves, which, in turn, are represented as cubic B-splines. Such representation also eases feature extraction. Experiments have been performed on 150 images of grapheme "th" written by different writers. The assessment of the skeletonisation results are presented.

KW - Image Processing

KW - Computer Vision

U2 - 10.1145/1066677.1066850

DO - 10.1145/1066677.1066850

M3 - Conference contribution

SN - 1581139640

VL - 1

SP - 754

EP - 758

BT - Proceedings of the 2005 ACM Symposium on Applied Computing

PB - Association for Computing Machinery (ACM)

CY - New York, United States of America

T2 - SAC 2005: 20th Annual ACM Symposium on Applied Computing

Y2 - 13 March 2005 through 17 March 2005

ER -

Handwritten character skeletonisation for forensic document analysis

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this