A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification

Human hand back skin texture (HBST) is often consistent for a person and distinctive from person to person. In this paper, we study the HBST pattern recognition problem with applications to personal identification and gender classification. A specially designed system is developed to capture HBST im...

Full description

Bibliographic Details
Main Authors: Jin Xie, Lei Zhang, Jane You, David Zhang, Xiaofeng Qu
Format: Article
Language:English
Published: MDPI AG 2012-06-01
Series:Sensors
Subjects:
Online Access:http://www.mdpi.com/1424-8220/12/7/8691
_version_ 1798006791095713792
author Jin Xie
Lei Zhang
Jane You
David Zhang
Xiaofeng Qu
author_facet Jin Xie
Lei Zhang
Jane You
David Zhang
Xiaofeng Qu
author_sort Jin Xie
collection DOAJ
description Human hand back skin texture (HBST) is often consistent for a person and distinctive from person to person. In this paper, we study the HBST pattern recognition problem with applications to personal identification and gender classification. A specially designed system is developed to capture HBST images, and an HBST image database was established, which consists of 1,920 images from 80 persons (160 hands). An efficient texton learning based method is then presented to classify the HBST patterns. First, textons are learned in the space of filter bank responses from a set of training images using the -minimization based sparse representation (SR) technique. Then, under the SR framework, we represent the feature vector at each pixel over the learned dictionary to construct a representation coefficient histogram. Finally, the coefficient histogram is used as skin texture feature for classification. Experiments on personal identification and gender classification are performed by using the established HBST database. The results show that HBST can be used to assist human identification and gender classification.
first_indexed 2024-04-11T13:00:08Z
format Article
id doaj.art-24cdce1e1b6e487dadc7d97a7a1e3c2e
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-11T13:00:08Z
publishDate 2012-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-24cdce1e1b6e487dadc7d97a7a1e3c2e2022-12-22T04:22:56ZengMDPI AGSensors1424-82202012-06-011278691870910.3390/s120708691A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender ClassificationJin XieLei ZhangJane YouDavid ZhangXiaofeng QuHuman hand back skin texture (HBST) is often consistent for a person and distinctive from person to person. In this paper, we study the HBST pattern recognition problem with applications to personal identification and gender classification. A specially designed system is developed to capture HBST images, and an HBST image database was established, which consists of 1,920 images from 80 persons (160 hands). An efficient texton learning based method is then presented to classify the HBST patterns. First, textons are learned in the space of filter bank responses from a set of training images using the -minimization based sparse representation (SR) technique. Then, under the SR framework, we represent the feature vector at each pixel over the learned dictionary to construct a representation coefficient histogram. Finally, the coefficient histogram is used as skin texture feature for classification. Experiments on personal identification and gender classification are performed by using the established HBST database. The results show that HBST can be used to assist human identification and gender classification.http://www.mdpi.com/1424-8220/12/7/8691biometricshand back skin texturetexton learningsparse representation
spellingShingle Jin Xie
Lei Zhang
Jane You
David Zhang
Xiaofeng Qu
A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification
Sensors
biometrics
hand back skin texture
texton learning
sparse representation
title A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification
title_full A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification
title_fullStr A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification
title_full_unstemmed A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification
title_short A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification
title_sort study of hand back skin texture patterns for personal identification and gender classification
topic biometrics
hand back skin texture
texton learning
sparse representation
url http://www.mdpi.com/1424-8220/12/7/8691
work_keys_str_mv AT jinxie astudyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT leizhang astudyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT janeyou astudyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT davidzhang astudyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT xiaofengqu astudyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT jinxie studyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT leizhang studyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT janeyou studyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT davidzhang studyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification
AT xiaofengqu studyofhandbackskintexturepatternsforpersonalidentificationandgenderclassification