This letter presents an objective quality index for benchmarking image inpainting algorithms. Under the guidance of the masks of damaged areas, the boundary region and the inpainting region are first located. Then, the statistical features are extracted from the boundary and inpainting regions respectively. For the boundary region, we utilize Weibull distribution to fit the gradient magnitude histograms of the exterior and interior regions around the boundary, and the Kullback-Leibler Divergence (KLD) is calculated to measure the boundary distortions caused by imperfect inpainting. Meanwhile, the quality of the inpainting region is measured by comparing the naturalness factors between the inpainted image and the reference image. Experimental results demonstrate that the proposed metric outperforms the relevant state-of-the-art quality metrics.
Song LIANG
China University of Mining and Technology
Leida LI
China University of Mining and Technology
Bo HU
China University of Mining and Technology
Jianying ZHANG
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.
Copy
Song LIANG, Leida LI, Bo HU, Jianying ZHANG, "Quality Index for Benchmarking Image Inpainting Algorithms with Guided Regional Statistics" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 7, pp. 1430-1433, July 2019, doi: 10.1587/transinf.2018EDL8206.
Abstract: This letter presents an objective quality index for benchmarking image inpainting algorithms. Under the guidance of the masks of damaged areas, the boundary region and the inpainting region are first located. Then, the statistical features are extracted from the boundary and inpainting regions respectively. For the boundary region, we utilize Weibull distribution to fit the gradient magnitude histograms of the exterior and interior regions around the boundary, and the Kullback-Leibler Divergence (KLD) is calculated to measure the boundary distortions caused by imperfect inpainting. Meanwhile, the quality of the inpainting region is measured by comparing the naturalness factors between the inpainted image and the reference image. Experimental results demonstrate that the proposed metric outperforms the relevant state-of-the-art quality metrics.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8206/_p
Copy
@ARTICLE{e102-d_7_1430,
author={Song LIANG, Leida LI, Bo HU, Jianying ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Quality Index for Benchmarking Image Inpainting Algorithms with Guided Regional Statistics},
year={2019},
volume={E102-D},
number={7},
pages={1430-1433},
abstract={This letter presents an objective quality index for benchmarking image inpainting algorithms. Under the guidance of the masks of damaged areas, the boundary region and the inpainting region are first located. Then, the statistical features are extracted from the boundary and inpainting regions respectively. For the boundary region, we utilize Weibull distribution to fit the gradient magnitude histograms of the exterior and interior regions around the boundary, and the Kullback-Leibler Divergence (KLD) is calculated to measure the boundary distortions caused by imperfect inpainting. Meanwhile, the quality of the inpainting region is measured by comparing the naturalness factors between the inpainted image and the reference image. Experimental results demonstrate that the proposed metric outperforms the relevant state-of-the-art quality metrics.},
keywords={},
doi={10.1587/transinf.2018EDL8206},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Quality Index for Benchmarking Image Inpainting Algorithms with Guided Regional Statistics
T2 - IEICE TRANSACTIONS on Information
SP - 1430
EP - 1433
AU - Song LIANG
AU - Leida LI
AU - Bo HU
AU - Jianying ZHANG
PY - 2019
DO - 10.1587/transinf.2018EDL8206
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2019
AB - This letter presents an objective quality index for benchmarking image inpainting algorithms. Under the guidance of the masks of damaged areas, the boundary region and the inpainting region are first located. Then, the statistical features are extracted from the boundary and inpainting regions respectively. For the boundary region, we utilize Weibull distribution to fit the gradient magnitude histograms of the exterior and interior regions around the boundary, and the Kullback-Leibler Divergence (KLD) is calculated to measure the boundary distortions caused by imperfect inpainting. Meanwhile, the quality of the inpainting region is measured by comparing the naturalness factors between the inpainted image and the reference image. Experimental results demonstrate that the proposed metric outperforms the relevant state-of-the-art quality metrics.
ER -