Blind image deconvolution using specified 2-D HPF for feature extraction and conjugate gradient method in frequency domain

Takanori Fujisawa, Masaaki Ikehara

Research output: Contribution to journalArticle

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.

Original languageEnglish
Pages (from-to)846-853
Number of pages8
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE100A
Issue number3
DOIs
Publication statusPublished - 2017 Mar 1

Fingerprint

High pass filters
Conjugate gradient method
Deconvolution
Conjugate Gradient Method
Feature Extraction
Frequency Domain
Feature extraction
Filter
Kernel Estimation
Convolution
kernel
Blind Deconvolution
Framework
Prior Information
Estimate
Execution Time
Accelerate
Preprocessing
Computational Cost
Eliminate

Keywords

  • Deblurring
  • Feature extraction
  • Optimization

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{ec2ccbc72b3c4e46a80561de17e6daa3,
title = "Blind image deconvolution using specified 2-D HPF for feature extraction and conjugate gradient method in frequency domain",
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 = "Deblurring, Feature extraction, Optimization",
author = "Takanori Fujisawa and Masaaki Ikehara",
year = "2017",
month = "3",
day = "1",
doi = "10.1587/transfun.E100.A.846",
language = "English",
volume = "E100A",
pages = "846--853",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "3",

}

TY - JOUR

T1 - Blind image deconvolution using specified 2-D HPF for feature extraction and conjugate gradient method in frequency domain

AU - Fujisawa, Takanori

AU - Ikehara, Masaaki

PY - 2017/3/1

Y1 - 2017/3/1

N2 - 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.

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.

KW - Deblurring

KW - Feature extraction

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=85016177066&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016177066&partnerID=8YFLogxK

U2 - 10.1587/transfun.E100.A.846

DO - 10.1587/transfun.E100.A.846

M3 - Article

VL - E100A

SP - 846

EP - 853

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 3

ER -