Automated nanofibre sizing by multi‐image processing and deep learning with revised UNet model

Abstract

AbstractNanofibres have been widely used in many chemical engineering applications and their performance greatly depends on the size distribution of the nanofibres. Researchers have developed automated tools to determine nanofibre diameters, primarily using commercial MATLAB software package. However, no researchers have reported automatic processing of multiple images, which is essential to the consistency and accuracy of results. Nor has anyone reported nanofibre sizing using deep learning. Therefore, this paper reports an automated tool to measure the size distribution of electrospun nanofibres by simultaneous multi‐image processing. This tool determines the diameters of nanofibres using deep learning based on UNet model. Results show that the UNet‐based deep learning approach is more accurate than those obtained using existing methods, compared to experimental data.