This paper proposes an algorithm for exemplar-based image inpainting, which produces the same result as that of Criminisi's original scheme but at the cost of much smaller computation cost. The idea is to compute mean and standard deviation of every patch in the image, and use the values to decide whether to carry out pixel by pixel comparison or not when searching for the best matching patch. Due to the missing pixels in the target patch, the same pixels in the candidate patch should be omitted when computing the distance between patches. Thus, we first compute the range of mean and standard deviation of a candidate patch with missing pixels, using the average and standard deviation of the entire patch. Then we use the range to determine if the pixel comparison should be conducted. Measurements with well-known images in the inpainting literature show that the algorithm can save significant amount of computation cost, without risking degradation of image quality.
Jungmin SO
Hallym University
Baeksop KIM
Hallym University
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
Jungmin SO, Baeksop KIM, "A Fast Exemplar-Based Image Inpainting Method Using Bounding Based on Mean and Standard Deviation of Patch Pixels" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 8, pp. 1553-1561, August 2015, doi: 10.1587/transinf.2014EDP7369.
Abstract: This paper proposes an algorithm for exemplar-based image inpainting, which produces the same result as that of Criminisi's original scheme but at the cost of much smaller computation cost. The idea is to compute mean and standard deviation of every patch in the image, and use the values to decide whether to carry out pixel by pixel comparison or not when searching for the best matching patch. Due to the missing pixels in the target patch, the same pixels in the candidate patch should be omitted when computing the distance between patches. Thus, we first compute the range of mean and standard deviation of a candidate patch with missing pixels, using the average and standard deviation of the entire patch. Then we use the range to determine if the pixel comparison should be conducted. Measurements with well-known images in the inpainting literature show that the algorithm can save significant amount of computation cost, without risking degradation of image quality.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7369/_p
Copy
@ARTICLE{e98-d_8_1553,
author={Jungmin SO, Baeksop KIM, },
journal={IEICE TRANSACTIONS on Information},
title={A Fast Exemplar-Based Image Inpainting Method Using Bounding Based on Mean and Standard Deviation of Patch Pixels},
year={2015},
volume={E98-D},
number={8},
pages={1553-1561},
abstract={This paper proposes an algorithm for exemplar-based image inpainting, which produces the same result as that of Criminisi's original scheme but at the cost of much smaller computation cost. The idea is to compute mean and standard deviation of every patch in the image, and use the values to decide whether to carry out pixel by pixel comparison or not when searching for the best matching patch. Due to the missing pixels in the target patch, the same pixels in the candidate patch should be omitted when computing the distance between patches. Thus, we first compute the range of mean and standard deviation of a candidate patch with missing pixels, using the average and standard deviation of the entire patch. Then we use the range to determine if the pixel comparison should be conducted. Measurements with well-known images in the inpainting literature show that the algorithm can save significant amount of computation cost, without risking degradation of image quality.},
keywords={},
doi={10.1587/transinf.2014EDP7369},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - A Fast Exemplar-Based Image Inpainting Method Using Bounding Based on Mean and Standard Deviation of Patch Pixels
T2 - IEICE TRANSACTIONS on Information
SP - 1553
EP - 1561
AU - Jungmin SO
AU - Baeksop KIM
PY - 2015
DO - 10.1587/transinf.2014EDP7369
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2015
AB - This paper proposes an algorithm for exemplar-based image inpainting, which produces the same result as that of Criminisi's original scheme but at the cost of much smaller computation cost. The idea is to compute mean and standard deviation of every patch in the image, and use the values to decide whether to carry out pixel by pixel comparison or not when searching for the best matching patch. Due to the missing pixels in the target patch, the same pixels in the candidate patch should be omitted when computing the distance between patches. Thus, we first compute the range of mean and standard deviation of a candidate patch with missing pixels, using the average and standard deviation of the entire patch. Then we use the range to determine if the pixel comparison should be conducted. Measurements with well-known images in the inpainting literature show that the algorithm can save significant amount of computation cost, without risking degradation of image quality.
ER -