Iris Image Blur Detection with Multiple Kernel Learning

Lili PAN; Mei XIE; Ling MAO

doi:10.1587/transinf.E95.D.1698

Iris Image Blur Detection with Multiple Kernel Learning

Lili PAN, Mei XIE, Ling MAO

Full Text Views

0

Share
Cite this

Summary :

In this letter, we analyze the influence of motion and out-of-focus blur on both frequency spectrum and cepstrum of an iris image. Based on their characteristics, we define two new discriminative blur features represented by Energy Spectral Density Distribution (ESDD) and Singular Cepstrum Histogram (SCH). To merge the two features for blur detection, a merging kernel which is a linear combination of two kernels is proposed when employing Support Vector Machine. Extensive experiments demonstrate the validity of our method by showing the improved blur detection performance on both synthetic and real datasets.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.6 pp.1698-1701

Publication Date: 2012/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.1698

Type of Manuscript: LETTER

Category: Pattern Recognition

Cite this

Copy

Lili PAN, Mei XIE, Ling MAO, "Iris Image Blur Detection with Multiple Kernel Learning" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 6, pp. 1698-1701, June 2012, doi: 10.1587/transinf.E95.D.1698.
Abstract: In this letter, we analyze the influence of motion and out-of-focus blur on both frequency spectrum and cepstrum of an iris image. Based on their characteristics, we define two new discriminative blur features represented by Energy Spectral Density Distribution (ESDD) and Singular Cepstrum Histogram (SCH). To merge the two features for blur detection, a merging kernel which is a linear combination of two kernels is proposed when employing Support Vector Machine. Extensive experiments demonstrate the validity of our method by showing the improved blur detection performance on both synthetic and real datasets.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E95.D.1698/_p

Copy

@ARTICLE{e95-d_6_1698,
author={Lili PAN, Mei XIE, Ling MAO, },
journal={IEICE TRANSACTIONS on Information},
title={Iris Image Blur Detection with Multiple Kernel Learning},
year={2012},
volume={E95-D},
number={6},
pages={1698-1701},
abstract={In this letter, we analyze the influence of motion and out-of-focus blur on both frequency spectrum and cepstrum of an iris image. Based on their characteristics, we define two new discriminative blur features represented by Energy Spectral Density Distribution (ESDD) and Singular Cepstrum Histogram (SCH). To merge the two features for blur detection, a merging kernel which is a linear combination of two kernels is proposed when employing Support Vector Machine. Extensive experiments demonstrate the validity of our method by showing the improved blur detection performance on both synthetic and real datasets.},
keywords={},
doi={10.1587/transinf.E95.D.1698},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Iris Image Blur Detection with Multiple Kernel Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1698
EP - 1701
AU - Lili PAN
AU - Mei XIE
AU - Ling MAO
PY - 2012
DO - 10.1587/transinf.E95.D.1698
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2012
AB - In this letter, we analyze the influence of motion and out-of-focus blur on both frequency spectrum and cepstrum of an iris image. Based on their characteristics, we define two new discriminative blur features represented by Energy Spectral Density Distribution (ESDD) and Singular Cepstrum Histogram (SCH). To merge the two features for blur detection, a merging kernel which is a linear combination of two kernels is proposed when employing Support Vector Machine. Extensive experiments demonstrate the validity of our method by showing the improved blur detection performance on both synthetic and real datasets.
ER -