Blind image restoration method by PCA-based subspace generation

Brian Sumali, Nozomu Hamada, Yasue Mitsukura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Principal Component Analysis (PCA) has been effectively applied for image restoration. Original idea underlying PCA approach has two different roots. One is from the fact that PCA is relevant to variance of pixel intensity by which the missing high frequency components in blurred image should be recovered. The other comes from the idea of source separation based on PCA. In the light of PCA approach we have proposed an image restoration algorithm which contains the following three novel aspects: iterative application of PCA, Gaussian smoothing filtering for image ensemble creation, and no-reference image quality index for iteration number management. This paper aims to investigate and propose a non-iterative PCA-based image restoration with some generalizations. First, through conducted experiments the variance of Gaussian filters as well as the number of created images by them are appropriately determined. Second, weights are introduced to the principal component images. Finally, optimal weights are determined by maximizing the image quality index with no reference. Experimental results by the proposed method provide higher PSNR than the previous iterative PCA approach.

Original languageEnglish
Title of host publication2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages204-209
Number of pages6
ISBN (Print)9781467364997
DOIs
Publication statusPublished - 2016 Mar 11
EventInternational Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015 - Nusa Dua, Bali, Indonesia
Duration: 2015 Nov 92015 Nov 12

Other

OtherInternational Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015
CountryIndonesia
CityNusa Dua, Bali
Period15/11/915/11/12

Fingerprint

Image reconstruction
Principal component analysis
Image quality
Source separation
Pixels

Keywords

  • Blind image restoration
  • Gaussian blur
  • Image quality assessment
  • Principal component analysis
  • Single image restoration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Signal Processing

Cite this

Sumali, B., Hamada, N., & Mitsukura, Y. (2016). Blind image restoration method by PCA-based subspace generation. In 2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015 (pp. 204-209). [7432766] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISPACS.2015.7432766

Blind image restoration method by PCA-based subspace generation. / Sumali, Brian; Hamada, Nozomu; Mitsukura, Yasue.

2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 204-209 7432766.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sumali, B, Hamada, N & Mitsukura, Y 2016, Blind image restoration method by PCA-based subspace generation. in 2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015., 7432766, Institute of Electrical and Electronics Engineers Inc., pp. 204-209, International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015, Nusa Dua, Bali, Indonesia, 15/11/9. https://doi.org/10.1109/ISPACS.2015.7432766
Sumali B, Hamada N, Mitsukura Y. Blind image restoration method by PCA-based subspace generation. In 2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 204-209. 7432766 https://doi.org/10.1109/ISPACS.2015.7432766
Sumali, Brian ; Hamada, Nozomu ; Mitsukura, Yasue. / Blind image restoration method by PCA-based subspace generation. 2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 204-209
@inproceedings{4790ac3f79ed452388689d853d96eae7,
title = "Blind image restoration method by PCA-based subspace generation",
abstract = "Principal Component Analysis (PCA) has been effectively applied for image restoration. Original idea underlying PCA approach has two different roots. One is from the fact that PCA is relevant to variance of pixel intensity by which the missing high frequency components in blurred image should be recovered. The other comes from the idea of source separation based on PCA. In the light of PCA approach we have proposed an image restoration algorithm which contains the following three novel aspects: iterative application of PCA, Gaussian smoothing filtering for image ensemble creation, and no-reference image quality index for iteration number management. This paper aims to investigate and propose a non-iterative PCA-based image restoration with some generalizations. First, through conducted experiments the variance of Gaussian filters as well as the number of created images by them are appropriately determined. Second, weights are introduced to the principal component images. Finally, optimal weights are determined by maximizing the image quality index with no reference. Experimental results by the proposed method provide higher PSNR than the previous iterative PCA approach.",
keywords = "Blind image restoration, Gaussian blur, Image quality assessment, Principal component analysis, Single image restoration",
author = "Brian Sumali and Nozomu Hamada and Yasue Mitsukura",
year = "2016",
month = "3",
day = "11",
doi = "10.1109/ISPACS.2015.7432766",
language = "English",
isbn = "9781467364997",
pages = "204--209",
booktitle = "2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Blind image restoration method by PCA-based subspace generation

AU - Sumali, Brian

AU - Hamada, Nozomu

AU - Mitsukura, Yasue

PY - 2016/3/11

Y1 - 2016/3/11

N2 - Principal Component Analysis (PCA) has been effectively applied for image restoration. Original idea underlying PCA approach has two different roots. One is from the fact that PCA is relevant to variance of pixel intensity by which the missing high frequency components in blurred image should be recovered. The other comes from the idea of source separation based on PCA. In the light of PCA approach we have proposed an image restoration algorithm which contains the following three novel aspects: iterative application of PCA, Gaussian smoothing filtering for image ensemble creation, and no-reference image quality index for iteration number management. This paper aims to investigate and propose a non-iterative PCA-based image restoration with some generalizations. First, through conducted experiments the variance of Gaussian filters as well as the number of created images by them are appropriately determined. Second, weights are introduced to the principal component images. Finally, optimal weights are determined by maximizing the image quality index with no reference. Experimental results by the proposed method provide higher PSNR than the previous iterative PCA approach.

AB - Principal Component Analysis (PCA) has been effectively applied for image restoration. Original idea underlying PCA approach has two different roots. One is from the fact that PCA is relevant to variance of pixel intensity by which the missing high frequency components in blurred image should be recovered. The other comes from the idea of source separation based on PCA. In the light of PCA approach we have proposed an image restoration algorithm which contains the following three novel aspects: iterative application of PCA, Gaussian smoothing filtering for image ensemble creation, and no-reference image quality index for iteration number management. This paper aims to investigate and propose a non-iterative PCA-based image restoration with some generalizations. First, through conducted experiments the variance of Gaussian filters as well as the number of created images by them are appropriately determined. Second, weights are introduced to the principal component images. Finally, optimal weights are determined by maximizing the image quality index with no reference. Experimental results by the proposed method provide higher PSNR than the previous iterative PCA approach.

KW - Blind image restoration

KW - Gaussian blur

KW - Image quality assessment

KW - Principal component analysis

KW - Single image restoration

UR - http://www.scopus.com/inward/record.url?scp=84966659449&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966659449&partnerID=8YFLogxK

U2 - 10.1109/ISPACS.2015.7432766

DO - 10.1109/ISPACS.2015.7432766

M3 - Conference contribution

AN - SCOPUS:84966659449

SN - 9781467364997

SP - 204

EP - 209

BT - 2015 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -