Contour–Context Joint Blind Image Inpainting Network for Molecular Sieve Particle Size Measurement of SEM Images

Abstract

Scanning electron microscope (SEM) images generated in the experiment of high-throughput molecular sieves catalysts contain particle size information of various molecular sieves. However, a certain proportion of molecular sieves in SEM images are occluded due to their characteristics of cluster distribution, which cause difficulties to measure the particle size of these occluded molecular sieves. In this paper, we leverage the image inpainting technique to reconstruct missing regions, and then calculate the particle size. Aiming at the problem that the generated regions of recent image inpainting methods exist blurriness in contour and context, we propose a contour-context joint blind image inpainting network, which is specifically a two-stage model with full utilization of edge information to reconstruct the contour and context of these occluded molecular sieve images. In the first stage, the edge of occluded region is reconstructed. In the second stage, the reconstructed edge is introduced through down sampling and skip connection to generate images with complete contour. Meanwhile, a novel encoder loss is proposed to motivate the encoder to extract more reasonable features. Compared with the existing methods, our model achieved more integral results visually and higher quantitative metrics. Thus, our approach can accurately predict the particle size from reconstructed molecular sieve images.