Blur Map Generation Based on Local Natural Image Statistics for Partial Blur Segmentation

Natsuki TAKAYAMA; Hiroki TAKAHASHI

doi:10.1587/transinf.2017EDP7119

Blur Map Generation Based on Local Natural Image Statistics for Partial Blur Segmentation

Natsuki TAKAYAMA, Hiroki TAKAHASHI

Full Text Views

0

Share
Cite this

Summary :

Partial blur segmentation is one of the most interesting topics in computer vision, and it has practical value. The generation of blur maps is a crucial part of partial blur segmentation because partial blur segmentation involves producing a blur map and applying a segmentation algorithm to the blur map. In this study, we address two important issues in order to improve the discrimination of blur maps: (1) estimating a robust local blur feature to consider variations in the intensity amplitude and (2) a scheme for generating blur maps. We propose the ANGHS (Amplitude-Normalized Gradient Histogram Span) as a local blur feature. ANGHS represents the heavy-tailedness of a gradient distribution, where it is calculated from an image gradient normalized using the intensity amplitude. ANGHS is robust to variations in the intensity amplitude, and it can handle local regions in a more appropriate manner than previously proposed local blur features. Blur maps are affected by local blur features but also by the contents and sizes of local regions, and the assignment of blur feature values to pixels. Thus, multiple-sized grids and the EAI (Edge-Aware Interpolation) are employed in each task to improve the discrimination of blur maps. The discrimination of the generated blur maps is evaluated visually and statistically using numerous partial blur images. Comparisons with the results obtained by state-of-the-art methods demonstrate the high discrimination of the blur maps generated using the proposed method.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.12 pp.2984-2992

Publication Date: 2017/12/01

Publicized: 2017/09/05

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDP7119

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Natsuki TAKAYAMA
The University of Electro-Communications
Hiroki TAKAHASHI
The University of Electro-Communications

Keyword

ANGHS, blur map generation, natural image statistics, partial blur segmentation

Cite this

Copy

Natsuki TAKAYAMA, Hiroki TAKAHASHI, "Blur Map Generation Based on Local Natural Image Statistics for Partial Blur Segmentation" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 12, pp. 2984-2992, December 2017, doi: 10.1587/transinf.2017EDP7119.
Abstract: Partial blur segmentation is one of the most interesting topics in computer vision, and it has practical value. The generation of blur maps is a crucial part of partial blur segmentation because partial blur segmentation involves producing a blur map and applying a segmentation algorithm to the blur map. In this study, we address two important issues in order to improve the discrimination of blur maps: (1) estimating a robust local blur feature to consider variations in the intensity amplitude and (2) a scheme for generating blur maps. We propose the ANGHS (Amplitude-Normalized Gradient Histogram Span) as a local blur feature. ANGHS represents the heavy-tailedness of a gradient distribution, where it is calculated from an image gradient normalized using the intensity amplitude. ANGHS is robust to variations in the intensity amplitude, and it can handle local regions in a more appropriate manner than previously proposed local blur features. Blur maps are affected by local blur features but also by the contents and sizes of local regions, and the assignment of blur feature values to pixels. Thus, multiple-sized grids and the EAI (Edge-Aware Interpolation) are employed in each task to improve the discrimination of blur maps. The discrimination of the generated blur maps is evaluated visually and statistically using numerous partial blur images. Comparisons with the results obtained by state-of-the-art methods demonstrate the high discrimination of the blur maps generated using the proposed method.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7119/_p

Copy

@ARTICLE{e100-d_12_2984,
author={Natsuki TAKAYAMA, Hiroki TAKAHASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Blur Map Generation Based on Local Natural Image Statistics for Partial Blur Segmentation},
year={2017},
volume={E100-D},
number={12},
pages={2984-2992},
abstract={Partial blur segmentation is one of the most interesting topics in computer vision, and it has practical value. The generation of blur maps is a crucial part of partial blur segmentation because partial blur segmentation involves producing a blur map and applying a segmentation algorithm to the blur map. In this study, we address two important issues in order to improve the discrimination of blur maps: (1) estimating a robust local blur feature to consider variations in the intensity amplitude and (2) a scheme for generating blur maps. We propose the ANGHS (Amplitude-Normalized Gradient Histogram Span) as a local blur feature. ANGHS represents the heavy-tailedness of a gradient distribution, where it is calculated from an image gradient normalized using the intensity amplitude. ANGHS is robust to variations in the intensity amplitude, and it can handle local regions in a more appropriate manner than previously proposed local blur features. Blur maps are affected by local blur features but also by the contents and sizes of local regions, and the assignment of blur feature values to pixels. Thus, multiple-sized grids and the EAI (Edge-Aware Interpolation) are employed in each task to improve the discrimination of blur maps. The discrimination of the generated blur maps is evaluated visually and statistically using numerous partial blur images. Comparisons with the results obtained by state-of-the-art methods demonstrate the high discrimination of the blur maps generated using the proposed method.},
keywords={},
doi={10.1587/transinf.2017EDP7119},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Blur Map Generation Based on Local Natural Image Statistics for Partial Blur Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 2984
EP - 2992
AU - Natsuki TAKAYAMA
AU - Hiroki TAKAHASHI
PY - 2017
DO - 10.1587/transinf.2017EDP7119
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2017
AB - Partial blur segmentation is one of the most interesting topics in computer vision, and it has practical value. The generation of blur maps is a crucial part of partial blur segmentation because partial blur segmentation involves producing a blur map and applying a segmentation algorithm to the blur map. In this study, we address two important issues in order to improve the discrimination of blur maps: (1) estimating a robust local blur feature to consider variations in the intensity amplitude and (2) a scheme for generating blur maps. We propose the ANGHS (Amplitude-Normalized Gradient Histogram Span) as a local blur feature. ANGHS represents the heavy-tailedness of a gradient distribution, where it is calculated from an image gradient normalized using the intensity amplitude. ANGHS is robust to variations in the intensity amplitude, and it can handle local regions in a more appropriate manner than previously proposed local blur features. Blur maps are affected by local blur features but also by the contents and sizes of local regions, and the assignment of blur feature values to pixels. Thus, multiple-sized grids and the EAI (Edge-Aware Interpolation) are employed in each task to improve the discrimination of blur maps. The discrimination of the generated blur maps is evaluated visually and statistically using numerous partial blur images. Comparisons with the results obtained by state-of-the-art methods demonstrate the high discrimination of the blur maps generated using the proposed method.
ER -