Spherical Nanoparticle Parameter Measurement Method based on Mask R-CNN Segmentation and Edge Fitting

Nanoparticle size measurement and character description are important in Nano technology. In order to accurately measure the parameter of nanoparticles and evaluate the quality of nanomaterials, a spherical nanoparticle size measurement method based on Mask R-CNN segmentation and edge fitting is proposed according to the image captured by transmission electron microscopy. Firstly, according to the characteristics of the agglomerated adhesion particles in the nanoparticle image, the Mask R-CNN network is selected to segment the nanoparticle image. Secondly, based on the particle segmentation results, the nanoparticle boundary is fitted with a circle, and an edge correction scheme is proposed for the incomplete nanoparticles. Finally, the particle size and shape parameters of the particles are measured based on the fitting results. The experimental results verify the effectiveness of the proposed method.