SEM Image Quality Assessment Based on Texture Inpainting

Zhaolin LU  Ziyan ZHANG  Yi WANG  Liang DONG  Song LIANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E104-D    No.2    pp.341-345
Publication Date: 2021/02/01
Publicized: 2020/10/30
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2020EDL8123
Type of Manuscript: LETTER
Category: Image Processing and Video Processing
image quality assessment,  no-reference,  SEM image,  texture-inpainting,  

Full Text: PDF(2.3MB)>>
Buy this Article

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.

open access publishing via