A Superimposed Divide-and-Conquer Image Recognition Method for SEM Images of Nanoparticles on The Surface of Monocrystalline silicon with High Aggregation Degree

TL;DR

This paper introduces a superimposed divide-and-conquer image recognition method for SEM images of silicon nanoparticles, enabling automatic and accurate analysis of particle size and distribution, especially in highly aggregated conditions.

Contribution

The paper presents a novel superposition partitioning approach combined with morphological processing for automatic recognition of complex nanoparticle SEM images, outperforming existing methods.

Findings

Higher recognition accuracy than existing methods

Improved algorithm efficiency

Effective for various SEM imaging conditions

Abstract

The nanoparticle size and distribution information in the SEM images of silicon crystals are generally counted by manual methods. The realization of automatic machine recognition is significant in materials science. This paper proposed a superposition partitioning image recognition method to realize automatic recognition and information statistics of silicon crystal nanoparticle SEM images. Especially for the complex and highly aggregated characteristics of silicon crystal particle size, an accurate recognition step and contour statistics method based on morphological processing are given. This method has technical reference value for the recognition of Monocrystalline silicon surface nanoparticle images under different SEM shooting conditions. Besides, it outperforms other methods in terms of recognition accuracy and algorithm efficiency.