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
Esta carta apresenta uma métrica de avaliação de qualidade de imagem (IQA) para imagens de microscopia eletrônica de varredura (SEM) com base em pintura de textura. Inspirado pela observação de que a informação de textura das imagens SEM é bastante sensível a distorções, uma rede de pintura de textura é primeiro treinada para extrair características de textura. Em seguida, os pesos da rede de pintura de textura treinada são transferidos para a rede IQA para ajudá-la a aprender uma representação de textura eficaz da imagem distorcida. Finalmente, o ajuste fino supervisionado é realizado na rede IQA para prever a pontuação de qualidade da imagem. Resultados experimentais no conjunto de dados de qualidade de imagem SEM demonstram as vantagens do método apresentado.
Zhaolin LU
China University of Mining and Technology
Ziyan ZHANG
China University of Mining and Technology
Yi WANG
Jiangsu Normal University Kewen College
Liang DONG
China University of Mining and Technology
Song LIANG
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.
Copiar
Zhaolin LU, Ziyan ZHANG, Yi WANG, Liang DONG, Song LIANG, "SEM Image Quality Assessment Based on Texture Inpainting" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 2, pp. 341-345, February 2021, doi: 10.1587/transinf.2020EDL8123.
Abstract: This letter presents an image quality assessment (IQA) metric for scanning electron microscopy (SEM) images based on texture inpainting. Inspired by the observation that the texture information of SEM images is quite sensitive to distortions, a texture inpainting network is first trained to extract texture features. Then the weights of the trained texture inpainting network are transferred to the IQA network to help it learn an effective texture representation of the distorted image. Finally, supervised fine-tuning is conducted on the IQA network to predict the image quality score. Experimental results on the SEM image quality dataset demonstrate the advantages of the presented method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8123/_p
Copiar
@ARTICLE{e104-d_2_341,
author={Zhaolin LU, Ziyan ZHANG, Yi WANG, Liang DONG, Song LIANG, },
journal={IEICE TRANSACTIONS on Information},
title={SEM Image Quality Assessment Based on Texture Inpainting},
year={2021},
volume={E104-D},
number={2},
pages={341-345},
abstract={This letter presents an image quality assessment (IQA) metric for scanning electron microscopy (SEM) images based on texture inpainting. Inspired by the observation that the texture information of SEM images is quite sensitive to distortions, a texture inpainting network is first trained to extract texture features. Then the weights of the trained texture inpainting network are transferred to the IQA network to help it learn an effective texture representation of the distorted image. Finally, supervised fine-tuning is conducted on the IQA network to predict the image quality score. Experimental results on the SEM image quality dataset demonstrate the advantages of the presented method.},
keywords={},
doi={10.1587/transinf.2020EDL8123},
ISSN={1745-1361},
month={February},}
Copiar
TY - JOUR
TI - SEM Image Quality Assessment Based on Texture Inpainting
T2 - IEICE TRANSACTIONS on Information
SP - 341
EP - 345
AU - Zhaolin LU
AU - Ziyan ZHANG
AU - Yi WANG
AU - Liang DONG
AU - Song LIANG
PY - 2021
DO - 10.1587/transinf.2020EDL8123
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2021
AB - This letter presents an image quality assessment (IQA) metric for scanning electron microscopy (SEM) images based on texture inpainting. Inspired by the observation that the texture information of SEM images is quite sensitive to distortions, a texture inpainting network is first trained to extract texture features. Then the weights of the trained texture inpainting network are transferred to the IQA network to help it learn an effective texture representation of the distorted image. Finally, supervised fine-tuning is conducted on the IQA network to predict the image quality score. Experimental results on the SEM image quality dataset demonstrate the advantages of the presented method.
ER -