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
Kaedah mengecat melalui perwakilan jarang berdasarkan metrik kualiti tanpa fasa baharu dibentangkan dalam kertas ini. Memandangkan spektrum kuasa, ciri tanpa fasa, bagi kawasan setempat dalam imej membolehkan perwakilan ciri teksturnya yang lebih berjaya berbanding dengan nilai pikselnya, metrik kualiti baharu berdasarkan ciri tanpa fasa ini baru diperoleh untuk perwakilan imej. Secara khusus, kaedah yang dicadangkan membolehkan perwakilan ganti isyarat sasaran, iaitu, tampalan sasaran, termasuk keamatan yang hilang dengan memantau ralat yang disatukan oleh pengambilan fasa sebagai metrik kualiti tanpa fasa novel. Ini adalah sumbangan utama kajian kami. Dalam pendekatan ini, algoritma pengambilan fasa yang digunakan dalam kaedah kami mempunyai dua peranan penting berikut: (1) terbitan metrik kualiti baharu yang boleh diperoleh walaupun untuk imej termasuk keamatan yang hilang dan (2) penukaran ciri tanpa fasa, iaitu, kuasa spektrum, kepada nilai piksel, iaitu, keamatan. Oleh itu, pendekatan novel di atas menyelesaikan masalah sedia ada yang tidak dapat menggunakan ciri yang lebih baik atau metrik kualiti yang lebih baik untuk mengecat. Keputusan eksperimen menunjukkan bahawa kaedah yang dicadangkan menggunakan perwakilan jarang berdasarkan metrik kualiti tanpa fasa baharu mengatasi kaedah yang dilaporkan sebelum ini yang secara langsung menggunakan nilai piksel untuk mengecat.
Takahiro OGAWA
Hokkaido University
Keisuke MAEDA
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.
Salinan
Takahiro OGAWA, Keisuke MAEDA, Miki HASEYAMA, "Inpainting via Sparse Representation Based on a Phaseless Quality Metric" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 12, pp. 1541-1551, December 2020, doi: 10.1587/transfun.2020SMP0020.
Abstract: An inpainting method via sparse representation based on a new phaseless quality metric is presented in this paper. Since power spectra, phaseless features, of local regions within images enable more successful representation of their texture characteristics compared to their pixel values, a new quality metric based on these phaseless features is newly derived for image representation. Specifically, the proposed method enables spare representation of target signals, i.e., target patches, including missing intensities by monitoring errors converged by phase retrieval as the novel phaseless quality metric. This is the main contribution of our study. In this approach, the phase retrieval algorithm used in our method has the following two important roles: (1) derivation of the new quality metric that can be derived even for images including missing intensities and (2) conversion of phaseless features, i.e., power spectra, to pixel values, i.e., intensities. Therefore, the above novel approach solves the existing problem of not being able to use better features or better quality metrics for inpainting. Results of experiments showed that the proposed method using sparse representation based on the new phaseless quality metric outperforms previously reported methods that directly use pixel values for inpainting.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020SMP0020/_p
Salinan
@ARTICLE{e103-a_12_1541,
author={Takahiro OGAWA, Keisuke MAEDA, Miki HASEYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Inpainting via Sparse Representation Based on a Phaseless Quality Metric},
year={2020},
volume={E103-A},
number={12},
pages={1541-1551},
abstract={An inpainting method via sparse representation based on a new phaseless quality metric is presented in this paper. Since power spectra, phaseless features, of local regions within images enable more successful representation of their texture characteristics compared to their pixel values, a new quality metric based on these phaseless features is newly derived for image representation. Specifically, the proposed method enables spare representation of target signals, i.e., target patches, including missing intensities by monitoring errors converged by phase retrieval as the novel phaseless quality metric. This is the main contribution of our study. In this approach, the phase retrieval algorithm used in our method has the following two important roles: (1) derivation of the new quality metric that can be derived even for images including missing intensities and (2) conversion of phaseless features, i.e., power spectra, to pixel values, i.e., intensities. Therefore, the above novel approach solves the existing problem of not being able to use better features or better quality metrics for inpainting. Results of experiments showed that the proposed method using sparse representation based on the new phaseless quality metric outperforms previously reported methods that directly use pixel values for inpainting.},
keywords={},
doi={10.1587/transfun.2020SMP0020},
ISSN={1745-1337},
month={December},}
Salinan
TY - JOUR
TI - Inpainting via Sparse Representation Based on a Phaseless Quality Metric
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1541
EP - 1551
AU - Takahiro OGAWA
AU - Keisuke MAEDA
AU - Miki HASEYAMA
PY - 2020
DO - 10.1587/transfun.2020SMP0020
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2020
AB - An inpainting method via sparse representation based on a new phaseless quality metric is presented in this paper. Since power spectra, phaseless features, of local regions within images enable more successful representation of their texture characteristics compared to their pixel values, a new quality metric based on these phaseless features is newly derived for image representation. Specifically, the proposed method enables spare representation of target signals, i.e., target patches, including missing intensities by monitoring errors converged by phase retrieval as the novel phaseless quality metric. This is the main contribution of our study. In this approach, the phase retrieval algorithm used in our method has the following two important roles: (1) derivation of the new quality metric that can be derived even for images including missing intensities and (2) conversion of phaseless features, i.e., power spectra, to pixel values, i.e., intensities. Therefore, the above novel approach solves the existing problem of not being able to use better features or better quality metrics for inpainting. Results of experiments showed that the proposed method using sparse representation based on the new phaseless quality metric outperforms previously reported methods that directly use pixel values for inpainting.
ER -