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
La représentation binaire clairsemée basée sur des métriques de qualité arbitraires et ses applications sont présentées dans cet article. Les nouveautés de la méthode proposée sont doubles. Premièrement, la méthode proposée dérive une nouvelle représentation clairsemée pour laquelle les coefficients de représentation sont des valeurs binaires, ce qui permet la sélection de métriques arbitraires de qualité d’image. Cette nouvelle représentation clairsemée peut générer des sous-espaces de qualité indépendants des métriques avec une simplification des procédures de calcul. Deuxièmement, la saillance visuelle est utilisée dans la méthode proposée pour regrouper les valeurs de qualité obtenues pour toutes les parties des images cibles. Cette approche permet une approximation visuellement agréable des images cibles avec plus de succès. En introduisant les deux nouvelles approches ci-dessus, une approximation réussie des images prenant en compte la perception humaine devient réalisable. Étant donné que la méthode proposée peut fournir des sous-espaces de dimension inférieure obtenus par de meilleures mesures de qualité d'image, on peut s'attendre à la réalisation de plusieurs tâches de reconstruction d'image. Les résultats expérimentaux ont montré de hautes performances de la méthode proposée en termes de deux tâches de reconstruction d'images, l'inpainting d'images et la super-résolution.
Takahiro OGAWA
Hokkaido University
Sho TAKAHASHI
Hokkaido University
Naofumi WADA
Hokkaido University of Science
Akira TANAKA
Hokkaido University
Miki HASEYAMA
Hokkaido 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.
Copier
Takahiro OGAWA, Sho TAKAHASHI, Naofumi WADA, Akira TANAKA, Miki HASEYAMA, "Binary Sparse Representation Based on Arbitrary Quality Metrics and Its Applications" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 11, pp. 1776-1785, November 2018, doi: 10.1587/transfun.E101.A.1776.
Abstract: Binary sparse representation based on arbitrary quality metrics and its applications are presented in this paper. The novelties of the proposed method are twofold. First, the proposed method newly derives sparse representation for which representation coefficients are binary values, and this enables selection of arbitrary image quality metrics. This new sparse representation can generate quality metric-independent subspaces with simplification of the calculation procedures. Second, visual saliency is used in the proposed method for pooling the quality values obtained for all of the parts within target images. This approach enables visually pleasant approximation of the target images more successfully. By introducing the above two novel approaches, successful image approximation considering human perception becomes feasible. Since the proposed method can provide lower-dimensional subspaces that are obtained by better image quality metrics, realization of several image reconstruction tasks can be expected. Experimental results showed high performance of the proposed method in terms of two image reconstruction tasks, image inpainting and super-resolution.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.1776/_p
Copier
@ARTICLE{e101-a_11_1776,
author={Takahiro OGAWA, Sho TAKAHASHI, Naofumi WADA, Akira TANAKA, Miki HASEYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Binary Sparse Representation Based on Arbitrary Quality Metrics and Its Applications},
year={2018},
volume={E101-A},
number={11},
pages={1776-1785},
abstract={Binary sparse representation based on arbitrary quality metrics and its applications are presented in this paper. The novelties of the proposed method are twofold. First, the proposed method newly derives sparse representation for which representation coefficients are binary values, and this enables selection of arbitrary image quality metrics. This new sparse representation can generate quality metric-independent subspaces with simplification of the calculation procedures. Second, visual saliency is used in the proposed method for pooling the quality values obtained for all of the parts within target images. This approach enables visually pleasant approximation of the target images more successfully. By introducing the above two novel approaches, successful image approximation considering human perception becomes feasible. Since the proposed method can provide lower-dimensional subspaces that are obtained by better image quality metrics, realization of several image reconstruction tasks can be expected. Experimental results showed high performance of the proposed method in terms of two image reconstruction tasks, image inpainting and super-resolution.},
keywords={},
doi={10.1587/transfun.E101.A.1776},
ISSN={1745-1337},
month={November},}
Copier
TY - JOUR
TI - Binary Sparse Representation Based on Arbitrary Quality Metrics and Its Applications
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1776
EP - 1785
AU - Takahiro OGAWA
AU - Sho TAKAHASHI
AU - Naofumi WADA
AU - Akira TANAKA
AU - Miki HASEYAMA
PY - 2018
DO - 10.1587/transfun.E101.A.1776
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2018
AB - Binary sparse representation based on arbitrary quality metrics and its applications are presented in this paper. The novelties of the proposed method are twofold. First, the proposed method newly derives sparse representation for which representation coefficients are binary values, and this enables selection of arbitrary image quality metrics. This new sparse representation can generate quality metric-independent subspaces with simplification of the calculation procedures. Second, visual saliency is used in the proposed method for pooling the quality values obtained for all of the parts within target images. This approach enables visually pleasant approximation of the target images more successfully. By introducing the above two novel approaches, successful image approximation considering human perception becomes feasible. Since the proposed method can provide lower-dimensional subspaces that are obtained by better image quality metrics, realization of several image reconstruction tasks can be expected. Experimental results showed high performance of the proposed method in terms of two image reconstruction tasks, image inpainting and super-resolution.
ER -