The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Un problème de reconnaissance d'images dans des circonstances pratiques est qu'une image observée est souvent dégradée par un système d'imagerie. Une méthode conventionnelle dans un tel cas consiste d’abord à estimer les paramètres du système d’imagerie, puis à restaurer l’image avant analyse. Nous proposons ici une approche alternative basée sur des invariants de phase dans le domaine de Fourier qui ne nécessite aucune restauration et est assez robuste au flou et au bruit. Nous montrons que les phases d'image dans la région positive de la transformée de Fourier de la fonction d'étalement de points (PSF) sont invariantes au flou à condition que la PSF soit à symétrie centrale. Dans l'hypothèse d'invariance de phase, une fonction de corrélation de phase entre une image standard et l'image dégradée est utilisée dans le développement de l'algorithme de reconnaissance. L'efficacité de cet algorithme est démontrée par des expériences utilisant dix classes d'images de figures provenant de plaques d'immatriculation de voitures.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Jianyin LU, Yasuo YOSHIDA, "Blurred Image Recognition Based on Phase Invariants" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 8, pp. 1450-1455, August 1999, doi: .
Abstract: A problem in image recognition in practical circumstances is that an observed image is often degraded by an imaging system. A conventional method in such a case is first to estimate the parameters of the imaging system and then restore the image before analysis. Here, we propose an alternative approach based on phase invariants in Fourier domain that needs no restoration and is fairly robust against both blur and noise. We show that the image phases in positive region of the Fourier transform of the point spread function (PSF) are blur-invariant provided that the PSF is central symmetric. Under the phase-invariant assumption, a phase correlation function between a standard image and the degraded image is used in developing the recognition algorithm. The effectiveness of this algorithm is demonstrated through experiments using ten classes of figure images from car license plates.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_8_1450/_p
Copier
@ARTICLE{e82-a_8_1450,
author={Jianyin LU, Yasuo YOSHIDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blurred Image Recognition Based on Phase Invariants},
year={1999},
volume={E82-A},
number={8},
pages={1450-1455},
abstract={A problem in image recognition in practical circumstances is that an observed image is often degraded by an imaging system. A conventional method in such a case is first to estimate the parameters of the imaging system and then restore the image before analysis. Here, we propose an alternative approach based on phase invariants in Fourier domain that needs no restoration and is fairly robust against both blur and noise. We show that the image phases in positive region of the Fourier transform of the point spread function (PSF) are blur-invariant provided that the PSF is central symmetric. Under the phase-invariant assumption, a phase correlation function between a standard image and the degraded image is used in developing the recognition algorithm. The effectiveness of this algorithm is demonstrated through experiments using ten classes of figure images from car license plates.},
keywords={},
doi={},
ISSN={},
month={August},}
Copier
TY - JOUR
TI - Blurred Image Recognition Based on Phase Invariants
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1450
EP - 1455
AU - Jianyin LU
AU - Yasuo YOSHIDA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 1999
AB - A problem in image recognition in practical circumstances is that an observed image is often degraded by an imaging system. A conventional method in such a case is first to estimate the parameters of the imaging system and then restore the image before analysis. Here, we propose an alternative approach based on phase invariants in Fourier domain that needs no restoration and is fairly robust against both blur and noise. We show that the image phases in positive region of the Fourier transform of the point spread function (PSF) are blur-invariant provided that the PSF is central symmetric. Under the phase-invariant assumption, a phase correlation function between a standard image and the degraded image is used in developing the recognition algorithm. The effectiveness of this algorithm is demonstrated through experiments using ten classes of figure images from car license plates.
ER -