Automatic classification of electrospun fiber polarized light images using mueller matrix depolarization parameter

Abstract

Electrospun fibers are widely used in various fields of biology, medicine, and chemistry due to their unique morphological characteristics that determine their distinct application properties. Accurate and rapid classification of these fibers based on their morphology is critical for their effective utilization. Non-destructive and low-cost imaging methods are highly desirable for this purpose, so we obtained the polarization images of different forms of electrospun fibers (smooth surfaces, microporous, and beaded microspheres) by polarized light microscopy. In this study, we have explored the automatic classification of electrospun fibers based on their Mueller matrix depolarization parameter, which is highly correlated with the rough microporous structures on the surface of the object. To achieve this, we employed transfer learning and various convolutional neural networks (CNNs). Our proposed method outperformed the conventional approach that only utilizes a single Mueller matrix M44 image for classification, thus enabling researchers to effectively classify electrospun fibers. Given the high accuracy of our method, it may find significant utility in fields such as material science, nanotechnology, and bioengineering.