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
초해상도(SR) 이미지 재구성은 최근 관심이 높아지고 있으며 하나 또는 여러 개의 저해상도 이미지에서 고해상도 이미지를 복원하기 위해 많은 SR 이미지 재구성 알고리즘이 제안되었습니다. 그러나 SR 재구성 이미지의 품질을 객관적으로 평가하는 방법은 아직 해결되지 않은 문제로 남아 있습니다. 수많은 이미지 품질 지표가 제안되었지만 SR 재구성 이미지의 품질을 평가하는 데는 상당히 제한적입니다. 이에 영감을 받아 이 논문은 XNUMX차 및 XNUMX차 구조적 저하를 사용하여 SR 재구성 이미지에 대한 블라인드 품질 지수를 제시합니다. 첫째, SR 재구성 이미지는 XNUMX차 및 XNUMX차 구조적 표현에 효과적인 다중 차수 미분 크기 맵으로 분해됩니다. 그런 다음 주파수 영역에서 이러한 다차 미분 크기 맵에서 로그 에너지 기반 특징이 추출됩니다. 마지막으로 서포트 벡터 회귀는 SR 재구성 이미지의 품질 모델을 학습하는 데 사용됩니다. 하나의 공개 데이터베이스에서 수행된 광범위한 실험 결과는 제안된 방법이 기존 품질 지표보다 우수한 성능을 보여줍니다. 또한 제안된 방법은 훈련 이미지 수에 덜 의존하고 계산 비용도 저렴하다.
Jiansheng QIAN
China University of Mining and Technology
Bo HU
China University of Mining and Technology
Lijuan TANG
Jiangsu Vocational College of Business
Jianying ZHANG
China University of Mining and Technology
Song LIANG
China University of Mining and Technology
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.
부
Jiansheng QIAN, Bo HU, Lijuan TANG, Jianying ZHANG, Song LIANG, "Blind Quality Index for Super Resolution Reconstructed Images Using First- and Second-Order Structural Degradation" in IEICE TRANSACTIONS on Fundamentals,
vol. E102-A, no. 11, pp. 1533-1541, November 2019, doi: 10.1587/transfun.E102.A.1533.
Abstract: Super resolution (SR) image reconstruction has attracted increasing attention these years and many SR image reconstruction algorithms have been proposed for restoring a high-resolution image from one or multiple low-resolution images. However, how to objectively evaluate the quality of SR reconstructed images remains an open problem. Although a great number of image quality metrics have been proposed, they are quite limited to evaluate the quality of SR reconstructed images. Inspired by this, this paper presents a blind quality index for SR reconstructed images using first- and second-order structural degradation. First, the SR reconstructed image is decomposed into multi-order derivative magnitude maps, which are effective for first- and second-order structural representation. Then, log-energy based features are extracted on these multi-order derivative magnitude maps in the frequency domain. Finally, support vector regression is used to learn the quality model for SR reconstructed images. The results of extensive experiments that were conducted on one public database demonstrate the superior performance of the proposed method over the existing quality metrics. Moreover, the proposed method is less dependent on the number of training images and has low computational cost.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E102.A.1533/_p
부
@ARTICLE{e102-a_11_1533,
author={Jiansheng QIAN, Bo HU, Lijuan TANG, Jianying ZHANG, Song LIANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blind Quality Index for Super Resolution Reconstructed Images Using First- and Second-Order Structural Degradation},
year={2019},
volume={E102-A},
number={11},
pages={1533-1541},
abstract={Super resolution (SR) image reconstruction has attracted increasing attention these years and many SR image reconstruction algorithms have been proposed for restoring a high-resolution image from one or multiple low-resolution images. However, how to objectively evaluate the quality of SR reconstructed images remains an open problem. Although a great number of image quality metrics have been proposed, they are quite limited to evaluate the quality of SR reconstructed images. Inspired by this, this paper presents a blind quality index for SR reconstructed images using first- and second-order structural degradation. First, the SR reconstructed image is decomposed into multi-order derivative magnitude maps, which are effective for first- and second-order structural representation. Then, log-energy based features are extracted on these multi-order derivative magnitude maps in the frequency domain. Finally, support vector regression is used to learn the quality model for SR reconstructed images. The results of extensive experiments that were conducted on one public database demonstrate the superior performance of the proposed method over the existing quality metrics. Moreover, the proposed method is less dependent on the number of training images and has low computational cost.},
keywords={},
doi={10.1587/transfun.E102.A.1533},
ISSN={1745-1337},
month={November},}
부
TY - JOUR
TI - Blind Quality Index for Super Resolution Reconstructed Images Using First- and Second-Order Structural Degradation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1533
EP - 1541
AU - Jiansheng QIAN
AU - Bo HU
AU - Lijuan TANG
AU - Jianying ZHANG
AU - Song LIANG
PY - 2019
DO - 10.1587/transfun.E102.A.1533
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E102-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2019
AB - Super resolution (SR) image reconstruction has attracted increasing attention these years and many SR image reconstruction algorithms have been proposed for restoring a high-resolution image from one or multiple low-resolution images. However, how to objectively evaluate the quality of SR reconstructed images remains an open problem. Although a great number of image quality metrics have been proposed, they are quite limited to evaluate the quality of SR reconstructed images. Inspired by this, this paper presents a blind quality index for SR reconstructed images using first- and second-order structural degradation. First, the SR reconstructed image is decomposed into multi-order derivative magnitude maps, which are effective for first- and second-order structural representation. Then, log-energy based features are extracted on these multi-order derivative magnitude maps in the frequency domain. Finally, support vector regression is used to learn the quality model for SR reconstructed images. The results of extensive experiments that were conducted on one public database demonstrate the superior performance of the proposed method over the existing quality metrics. Moreover, the proposed method is less dependent on the number of training images and has low computational cost.
ER -