Model-guided deformable hand shape recognition without positioning aids

Wei Xiong, Kar Ann Toh, Wei Yun Yau, Xudong Jiang

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

This work addresses the problem of deformable hand shape recognition in biometric systems without any positioning aids. We separate and recognize multiple rigid fingers under Euclidean transformations. An elliptical model is introduced to represent fingers and accelerate the search of optimal alignments of fingers. Unlike other methods, the similarity is measured during alignment search based on finger width measurements defined at nodes by controllable intervals to achieve balanceable recognition accuracy and computational cost. Technically, our method bridges the traditional handcrafted-feature methods and the shape-distance methods. We have tested it using our 108-person-540-sample database with significantly increased positive recognition accuracy.

Original languageEnglish
Pages (from-to)1651-1664
Number of pages14
JournalPattern Recognition
Volume38
Issue number10
DOIs
Publication statusPublished - 2005 Oct 1

Fingerprint

Biometrics
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Xiong, Wei ; Toh, Kar Ann ; Yau, Wei Yun ; Jiang, Xudong. / Model-guided deformable hand shape recognition without positioning aids. In: Pattern Recognition. 2005 ; Vol. 38, No. 10. pp. 1651-1664.
@article{16301b6d7ad0413b83c67339dc44b677,
title = "Model-guided deformable hand shape recognition without positioning aids",
abstract = "This work addresses the problem of deformable hand shape recognition in biometric systems without any positioning aids. We separate and recognize multiple rigid fingers under Euclidean transformations. An elliptical model is introduced to represent fingers and accelerate the search of optimal alignments of fingers. Unlike other methods, the similarity is measured during alignment search based on finger width measurements defined at nodes by controllable intervals to achieve balanceable recognition accuracy and computational cost. Technically, our method bridges the traditional handcrafted-feature methods and the shape-distance methods. We have tested it using our 108-person-540-sample database with significantly increased positive recognition accuracy.",
author = "Wei Xiong and Toh, {Kar Ann} and Yau, {Wei Yun} and Xudong Jiang",
year = "2005",
month = "10",
day = "1",
doi = "10.1016/j.patcog.2004.07.008",
language = "English",
volume = "38",
pages = "1651--1664",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "10",

}

Model-guided deformable hand shape recognition without positioning aids. / Xiong, Wei; Toh, Kar Ann; Yau, Wei Yun; Jiang, Xudong.

In: Pattern Recognition, Vol. 38, No. 10, 01.10.2005, p. 1651-1664.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Model-guided deformable hand shape recognition without positioning aids

AU - Xiong, Wei

AU - Toh, Kar Ann

AU - Yau, Wei Yun

AU - Jiang, Xudong

PY - 2005/10/1

Y1 - 2005/10/1

N2 - This work addresses the problem of deformable hand shape recognition in biometric systems without any positioning aids. We separate and recognize multiple rigid fingers under Euclidean transformations. An elliptical model is introduced to represent fingers and accelerate the search of optimal alignments of fingers. Unlike other methods, the similarity is measured during alignment search based on finger width measurements defined at nodes by controllable intervals to achieve balanceable recognition accuracy and computational cost. Technically, our method bridges the traditional handcrafted-feature methods and the shape-distance methods. We have tested it using our 108-person-540-sample database with significantly increased positive recognition accuracy.

AB - This work addresses the problem of deformable hand shape recognition in biometric systems without any positioning aids. We separate and recognize multiple rigid fingers under Euclidean transformations. An elliptical model is introduced to represent fingers and accelerate the search of optimal alignments of fingers. Unlike other methods, the similarity is measured during alignment search based on finger width measurements defined at nodes by controllable intervals to achieve balanceable recognition accuracy and computational cost. Technically, our method bridges the traditional handcrafted-feature methods and the shape-distance methods. We have tested it using our 108-person-540-sample database with significantly increased positive recognition accuracy.

UR - http://www.scopus.com/inward/record.url?scp=22844443700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22844443700&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2004.07.008

DO - 10.1016/j.patcog.2004.07.008

M3 - Article

VL - 38

SP - 1651

EP - 1664

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 10

ER -