Single image Super Resolution by no-reference image quality index optimization in PCA subspace

Brian Sumali; Haslina Sarkan; Nozomu Hamada; Yasue Mitsukura

doi:10.1109/CSPA.2016.7515828

Single image Super Resolution by no-reference image quality index optimization in PCA subspace

Brian Sumali, Haslina Sarkan, Nozomu Hamada, Yasue Mitsukura

システムデザイン工学科

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Principal Component Analysis (PCA) has been effectively applied for solving atmospheric-turbulence degraded images. PCA-based approaches improve the image quality by adding high-frequency components extracted using PCA to the blurred image. The PCA-based restoration process is similar with conventional single-frame Super-Resolution (SR) methods, which perform SR process by improving the edges portion of low-resolution images. This paper aims to introduce PCA-based restoration to solve SR problem with additive white Gaussian noise. We conducted experiments using standard image database and show comparative result with the latest deep-learning SR approach.

本文言語	English
ホスト出版物のタイトル	Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016
出版社	Institute of Electrical and Electronics Engineers Inc.
ページ	183-187
ページ数	5
ISBN（電子版）	9781467387804
DOI	https://doi.org/10.1109/CSPA.2016.7515828
出版ステータス	Published - 2016 7 18
イベント	12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016 - Melaka, Malaysia 継続期間: 2016 3 4 → 2016 3 6

Other

Other	12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016
Country	Malaysia
City	Melaka
Period	16/3/4 → 16/3/6

ASJC Scopus subject areas

Signal Processing
Control and Systems Engineering
Control and Optimization

文献へのアクセス

10.1109/CSPA.2016.7515828

フィンガープリント「Single image Super Resolution by no-reference image quality index optimization in PCA subspace」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル

Sumali, B., Sarkan, H., Hamada, N., & Mitsukura, Y. (2016). Single image Super Resolution by no-reference image quality index optimization in PCA subspace. In Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016 (pp. 183-187). [7515828] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSPA.2016.7515828

Single image Super Resolution by no-reference image quality index optimization in PCA subspace. / Sumali, Brian; Sarkan, Haslina; Hamada, Nozomu; Mitsukura, Yasue.

Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 183-187 7515828.

研究成果: Conference contribution

Sumali, B, Sarkan, H, Hamada, N & Mitsukura, Y 2016, Single image Super Resolution by no-reference image quality index optimization in PCA subspace. in Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016., 7515828, Institute of Electrical and Electronics Engineers Inc., pp. 183-187, 12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016, Melaka, Malaysia, 16/3/4. https://doi.org/10.1109/CSPA.2016.7515828

Sumali B, Sarkan H, Hamada N, Mitsukura Y. Single image Super Resolution by no-reference image quality index optimization in PCA subspace. In Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 183-187. 7515828 https://doi.org/10.1109/CSPA.2016.7515828

@inproceedings{8fd2eb7045da4b0480e88b7f5bf784f2,

title = "Single image Super Resolution by no-reference image quality index optimization in PCA subspace",

abstract = "Principal Component Analysis (PCA) has been effectively applied for solving atmospheric-turbulence degraded images. PCA-based approaches improve the image quality by adding high-frequency components extracted using PCA to the blurred image. The PCA-based restoration process is similar with conventional single-frame Super-Resolution (SR) methods, which perform SR process by improving the edges portion of low-resolution images. This paper aims to introduce PCA-based restoration to solve SR problem with additive white Gaussian noise. We conducted experiments using standard image database and show comparative result with the latest deep-learning SR approach.",

keywords = "Image Quality Assessment, Noise Robustness, Principal Component Analysis, Single Image, Super Resolution",

author = "Brian Sumali and Haslina Sarkan and Nozomu Hamada and Yasue Mitsukura",

year = "2016",

month = jul,

day = "18",

doi = "10.1109/CSPA.2016.7515828",

language = "English",

pages = "183--187",

booktitle = "Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016 ; Conference date: 04-03-2016 Through 06-03-2016",

}

TY - GEN

T1 - Single image Super Resolution by no-reference image quality index optimization in PCA subspace

AU - Sumali, Brian

AU - Sarkan, Haslina

AU - Hamada, Nozomu

AU - Mitsukura, Yasue

PY - 2016/7/18

Y1 - 2016/7/18

N2 - Principal Component Analysis (PCA) has been effectively applied for solving atmospheric-turbulence degraded images. PCA-based approaches improve the image quality by adding high-frequency components extracted using PCA to the blurred image. The PCA-based restoration process is similar with conventional single-frame Super-Resolution (SR) methods, which perform SR process by improving the edges portion of low-resolution images. This paper aims to introduce PCA-based restoration to solve SR problem with additive white Gaussian noise. We conducted experiments using standard image database and show comparative result with the latest deep-learning SR approach.

AB - Principal Component Analysis (PCA) has been effectively applied for solving atmospheric-turbulence degraded images. PCA-based approaches improve the image quality by adding high-frequency components extracted using PCA to the blurred image. The PCA-based restoration process is similar with conventional single-frame Super-Resolution (SR) methods, which perform SR process by improving the edges portion of low-resolution images. This paper aims to introduce PCA-based restoration to solve SR problem with additive white Gaussian noise. We conducted experiments using standard image database and show comparative result with the latest deep-learning SR approach.

KW - Image Quality Assessment

KW - Noise Robustness

KW - Principal Component Analysis

KW - Single Image

KW - Super Resolution

UR - http://www.scopus.com/inward/record.url?scp=84983517105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983517105&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2016.7515828

DO - 10.1109/CSPA.2016.7515828

M3 - Conference contribution

AN - SCOPUS:84983517105

SP - 183

EP - 187

BT - Proceeding - 2016 IEEE 12th International Colloquium on Signal Processing and its Applications, CSPA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Colloquium on Signal Processing and its Applications, CSPA 2016

Y2 - 4 March 2016 through 6 March 2016

ER -