Line Segment Distribution of Sketches for Persian Signature Recognition

Abdolah Chalechale; Alfred Mertins

doi:10.1109/TENCON.2003.1273203

Line Segment Distribution of Sketches for Persian Signature Recognition

Abdolah Chalechale, Alfred Mertins

Institute of Signal Processing

University of Wollongong

Abstract

A novel fast method for line segment extraction based on chain code representation of thinned sketches (or edge maps) is presented and exploited for Persian signature recognition. The method has a parallel nature and can be employed on parallel machines. It breaks the macro chains into several micro chains after applying shifting, smoothing and differentiating. The micro chains are then approximated by straight line segments. Length and position distributions of the extracted line segments are used to make a compact feature vector for Iranian cursive signature. The feature vector is invariant under affine transforms and can be used effectively in paperless office projects. Experimental results show fast response and accurate recognition/retrieval rate.

Original language	English
Pages	11-15
Number of pages	5
DOIs	https://doi.org/10.1109/TENCON.2003.1273203
Publication status	Published - 01.12.2003
Event	IEEE TENCON 2003: Confernce on Covergent Technologies for the Asia-Pacific Region - Bangalore, India Duration: 15.10.2003 → 17.10.2003 Conference number: 62906

Conference

Conference	IEEE TENCON 2003: Confernce on Covergent Technologies for the Asia-Pacific Region
Country/Territory	India
City	Bangalore
Period	15.10.03 → 17.10.03

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TENCON.2003.1273203

Cite this

@conference{dd5872660d4749a795553a17de2c1c34,

title = "Line Segment Distribution of Sketches for Persian Signature Recognition",

abstract = "A novel fast method for line segment extraction based on chain code representation of thinned sketches (or edge maps) is presented and exploited for Persian signature recognition. The method has a parallel nature and can be employed on parallel machines. It breaks the macro chains into several micro chains after applying shifting, smoothing and differentiating. The micro chains are then approximated by straight line segments. Length and position distributions of the extracted line segments are used to make a compact feature vector for Iranian cursive signature. The feature vector is invariant under affine transforms and can be used effectively in paperless office projects. Experimental results show fast response and accurate recognition/retrieval rate.",

author = "Abdolah Chalechale and Alfred Mertins",

year = "2003",

month = dec,

day = "1",

doi = "10.1109/TENCON.2003.1273203",

language = "English",

pages = "11--15",

note = "IEEE TENCON 2003: Confernce on Covergent Technologies for the Asia-Pacific Region ; Conference date: 15-10-2003 Through 17-10-2003",

}

TY - CONF

T1 - Line Segment Distribution of Sketches for Persian Signature Recognition

AU - Chalechale, Abdolah

AU - Mertins, Alfred

N1 - Conference code: 62906

PY - 2003/12/1

Y1 - 2003/12/1

N2 - A novel fast method for line segment extraction based on chain code representation of thinned sketches (or edge maps) is presented and exploited for Persian signature recognition. The method has a parallel nature and can be employed on parallel machines. It breaks the macro chains into several micro chains after applying shifting, smoothing and differentiating. The micro chains are then approximated by straight line segments. Length and position distributions of the extracted line segments are used to make a compact feature vector for Iranian cursive signature. The feature vector is invariant under affine transforms and can be used effectively in paperless office projects. Experimental results show fast response and accurate recognition/retrieval rate.

AB - A novel fast method for line segment extraction based on chain code representation of thinned sketches (or edge maps) is presented and exploited for Persian signature recognition. The method has a parallel nature and can be employed on parallel machines. It breaks the macro chains into several micro chains after applying shifting, smoothing and differentiating. The micro chains are then approximated by straight line segments. Length and position distributions of the extracted line segments are used to make a compact feature vector for Iranian cursive signature. The feature vector is invariant under affine transforms and can be used effectively in paperless office projects. Experimental results show fast response and accurate recognition/retrieval rate.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-2342555689&origin=inward&txGid=fdb75cc95fea9cb3b1653bf1e78aeba4

U2 - 10.1109/TENCON.2003.1273203

DO - 10.1109/TENCON.2003.1273203

M3 - Conference Papers

SP - 11

EP - 15

T2 - IEEE TENCON 2003: Confernce on Covergent Technologies for the Asia-Pacific Region

Y2 - 15 October 2003 through 17 October 2003

ER -

Line Segment Distribution of Sketches for Persian Signature Recognition

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this