Blind Image Deconvolution Using Specified 2-D HPF for Feature Extraction and Conjugate Gradient Method in Frequency Domain

Takanori FUJISAWA; Masaaki IKEHARA

doi:10.1587/transfun.E100.A.846

Blind Image Deconvolution Using Specified 2-D HPF for Feature Extraction and Conjugate Gradient Method in Frequency Domain

Takanori FUJISAWA, Masaaki IKEHARA

Full Text Views

0

Share
Cite this

Summary :

Image deconvolution is the task to recover the image information that was lost by taking photos with blur. Especially, to perform image deconvolution without prior information about blur kernel, is called blind image deconvolution. This framework is seriously ill-posed and an additional operation is required such as extracting image features. Many blind deconvolution frameworks separate the problem into kernel estimation problem and deconvolution problem. In order to solve the kernel estimation problem, previous frameworks extract the image's salient features by preprocessing, such as edge extraction. The disadvantage of these frameworks is that the quality of the estimated kernel is influenced by the region with no salient edges. Moreover, the optimization in the previous frameworks requires iterative calculation of convolution, which takes a heavy computational cost. In this paper, we present a blind image deconvolution framework using a specified high-pass filter (HPF) for feature extraction to estimate a blur kernel. The HPF-based feature extraction properly weights the image's regions for the optimization problem. Therefore, our kernel estimation problem can estimate the kernel in the region with no salient edges. In addition, our approach accelerates both kernel estimation and deconvolution processes by utilizing a conjugate gradient method in a frequency domain. This method eliminates costly convolution operations from these processes and reduces the execution time. Evaluation for 20 test images shows our framework not only improves the quality of recovered images but also performs faster than conventional frameworks.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.3 pp.846-853

Publication Date: 2017/03/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E100.A.846

Type of Manuscript: PAPER

Category: Image

Authors

Takanori FUJISAWA
Keio University
Masaaki IKEHARA
Keio University

Keyword

deblurring, feature extraction, optimization

Cite this

Copy

Takanori FUJISAWA, Masaaki IKEHARA, "Blind Image Deconvolution Using Specified 2-D HPF for Feature Extraction and Conjugate Gradient Method in Frequency Domain" in IEICE TRANSACTIONS on Fundamentals, vol. E100-A, no. 3, pp. 846-853, March 2017, doi: 10.1587/transfun.E100.A.846.
Abstract: Image deconvolution is the task to recover the image information that was lost by taking photos with blur. Especially, to perform image deconvolution without prior information about blur kernel, is called blind image deconvolution. This framework is seriously ill-posed and an additional operation is required such as extracting image features. Many blind deconvolution frameworks separate the problem into kernel estimation problem and deconvolution problem. In order to solve the kernel estimation problem, previous frameworks extract the image's salient features by preprocessing, such as edge extraction. The disadvantage of these frameworks is that the quality of the estimated kernel is influenced by the region with no salient edges. Moreover, the optimization in the previous frameworks requires iterative calculation of convolution, which takes a heavy computational cost. In this paper, we present a blind image deconvolution framework using a specified high-pass filter (HPF) for feature extraction to estimate a blur kernel. The HPF-based feature extraction properly weights the image's regions for the optimization problem. Therefore, our kernel estimation problem can estimate the kernel in the region with no salient edges. In addition, our approach accelerates both kernel estimation and deconvolution processes by utilizing a conjugate gradient method in a frequency domain. This method eliminates costly convolution operations from these processes and reduces the execution time. Evaluation for 20 test images shows our framework not only improves the quality of recovered images but also performs faster than conventional frameworks.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.846/_p

Copy

@ARTICLE{e100-a_3_846,
author={Takanori FUJISAWA, Masaaki IKEHARA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blind Image Deconvolution Using Specified 2-D HPF for Feature Extraction and Conjugate Gradient Method in Frequency Domain},
year={2017},
volume={E100-A},
number={3},
pages={846-853},
abstract={Image deconvolution is the task to recover the image information that was lost by taking photos with blur. Especially, to perform image deconvolution without prior information about blur kernel, is called blind image deconvolution. This framework is seriously ill-posed and an additional operation is required such as extracting image features. Many blind deconvolution frameworks separate the problem into kernel estimation problem and deconvolution problem. In order to solve the kernel estimation problem, previous frameworks extract the image's salient features by preprocessing, such as edge extraction. The disadvantage of these frameworks is that the quality of the estimated kernel is influenced by the region with no salient edges. Moreover, the optimization in the previous frameworks requires iterative calculation of convolution, which takes a heavy computational cost. In this paper, we present a blind image deconvolution framework using a specified high-pass filter (HPF) for feature extraction to estimate a blur kernel. The HPF-based feature extraction properly weights the image's regions for the optimization problem. Therefore, our kernel estimation problem can estimate the kernel in the region with no salient edges. In addition, our approach accelerates both kernel estimation and deconvolution processes by utilizing a conjugate gradient method in a frequency domain. This method eliminates costly convolution operations from these processes and reduces the execution time. Evaluation for 20 test images shows our framework not only improves the quality of recovered images but also performs faster than conventional frameworks.},
keywords={},
doi={10.1587/transfun.E100.A.846},
ISSN={1745-1337},
month={March},}

Copy

TY - JOUR
TI - Blind Image Deconvolution Using Specified 2-D HPF for Feature Extraction and Conjugate Gradient Method in Frequency Domain
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 846
EP - 853
AU - Takanori FUJISAWA
AU - Masaaki IKEHARA
PY - 2017
DO - 10.1587/transfun.E100.A.846
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2017
AB - Image deconvolution is the task to recover the image information that was lost by taking photos with blur. Especially, to perform image deconvolution without prior information about blur kernel, is called blind image deconvolution. This framework is seriously ill-posed and an additional operation is required such as extracting image features. Many blind deconvolution frameworks separate the problem into kernel estimation problem and deconvolution problem. In order to solve the kernel estimation problem, previous frameworks extract the image's salient features by preprocessing, such as edge extraction. The disadvantage of these frameworks is that the quality of the estimated kernel is influenced by the region with no salient edges. Moreover, the optimization in the previous frameworks requires iterative calculation of convolution, which takes a heavy computational cost. In this paper, we present a blind image deconvolution framework using a specified high-pass filter (HPF) for feature extraction to estimate a blur kernel. The HPF-based feature extraction properly weights the image's regions for the optimization problem. Therefore, our kernel estimation problem can estimate the kernel in the region with no salient edges. In addition, our approach accelerates both kernel estimation and deconvolution processes by utilizing a conjugate gradient method in a frequency domain. This method eliminates costly convolution operations from these processes and reduces the execution time. Evaluation for 20 test images shows our framework not only improves the quality of recovered images but also performs faster than conventional frameworks.
ER -