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
La fonction de flou réelle ou fonction d'étalement de points (PSF) dans une image, dans la plupart des cas, est similaire à un modèle paramétrique ou idéal. Les méthodes de déconvolution aveugle récemment proposées utilisent cette idée pour l'apprentissage lors de l'estimation de la PSF. Sa dépendance vis-à-vis des valeurs estimées peut entraîner un apprentissage inefficace lorsque le modèle est sélectionné par erreur. Pour surmonter ce problème, nous proposons d'exploiter les maxima de l'image afin d'en extraire une fonction d'étalement de point de référence (RPSF). Cela dépend uniquement de l'image dégradée et a une structure qui ressemble beaucoup à un flou de mouvement paramétrique en supposant une taille de support de flou connue. Son utilisation se traduira par un processus d'apprentissage et d'estimation plus stable puisqu'il ne change pas par rapport à l'itération ou à toute valeur estimée. Nous définissons une fonction de coût sous forme vectorielle-matrice qui prend en compte le contour de la fonction de flou ainsi que l'apprentissage vers le RPSF. L'efficacité de l'utilisation de RPSF et de la fonction de coût proposée dans diverses directions de mouvement et tailles de support sera démontrée par les résultats expérimentaux.
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
Rachel Mabanag CHONG, Toshihisa TANAKA, "Maxima Exploitation for Reference Blurring Function in Motion Deconvolution" in IEICE TRANSACTIONS on Fundamentals,
vol. E94-A, no. 3, pp. 921-928, March 2011, doi: 10.1587/transfun.E94.A.921.
Abstract: The actual blurring function or point spread function (PSF) in an image, in most cases, is similar to a parametric or ideal model. Recently proposed blind deconvolution methods employ this idea for learning during the estimation of PSF. Its dependence on the estimated values may result in ineffective learning when the model is erroneously selected. To overcome this problem, we propose to exploit the image maxima in order to extract a reference point spread function (RPSF). This is only dependent on the degraded image and has a structure that closely resembles a parametric motion blur assuming a known blur support size. Its usage will result in a more stable learning and estimation process since it does not change with respect to iteration or any estimated value. We define a cost function in the vector-matrix form which accounts for the blurring function contour as well as learning towards the RPSF. The effectiveness of using RPSF and the proposed cost function under various motion directions and support sizes will be demonstrated by the experimental results.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.921/_p
Copier
@ARTICLE{e94-a_3_921,
author={Rachel Mabanag CHONG, Toshihisa TANAKA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Maxima Exploitation for Reference Blurring Function in Motion Deconvolution},
year={2011},
volume={E94-A},
number={3},
pages={921-928},
abstract={The actual blurring function or point spread function (PSF) in an image, in most cases, is similar to a parametric or ideal model. Recently proposed blind deconvolution methods employ this idea for learning during the estimation of PSF. Its dependence on the estimated values may result in ineffective learning when the model is erroneously selected. To overcome this problem, we propose to exploit the image maxima in order to extract a reference point spread function (RPSF). This is only dependent on the degraded image and has a structure that closely resembles a parametric motion blur assuming a known blur support size. Its usage will result in a more stable learning and estimation process since it does not change with respect to iteration or any estimated value. We define a cost function in the vector-matrix form which accounts for the blurring function contour as well as learning towards the RPSF. The effectiveness of using RPSF and the proposed cost function under various motion directions and support sizes will be demonstrated by the experimental results.},
keywords={},
doi={10.1587/transfun.E94.A.921},
ISSN={1745-1337},
month={March},}
Copier
TY - JOUR
TI - Maxima Exploitation for Reference Blurring Function in Motion Deconvolution
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 921
EP - 928
AU - Rachel Mabanag CHONG
AU - Toshihisa TANAKA
PY - 2011
DO - 10.1587/transfun.E94.A.921
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2011
AB - The actual blurring function or point spread function (PSF) in an image, in most cases, is similar to a parametric or ideal model. Recently proposed blind deconvolution methods employ this idea for learning during the estimation of PSF. Its dependence on the estimated values may result in ineffective learning when the model is erroneously selected. To overcome this problem, we propose to exploit the image maxima in order to extract a reference point spread function (RPSF). This is only dependent on the degraded image and has a structure that closely resembles a parametric motion blur assuming a known blur support size. Its usage will result in a more stable learning and estimation process since it does not change with respect to iteration or any estimated value. We define a cost function in the vector-matrix form which accounts for the blurring function contour as well as learning towards the RPSF. The effectiveness of using RPSF and the proposed cost function under various motion directions and support sizes will be demonstrated by the experimental results.
ER -