Automated Fiber Extraction From SEM Images With Application to Quality Control of Fiber-Reinforced Composites Manufacturing

The morphology of fibers (e.g., spatial uniformity and orientation) plays a decisive role in determining the material properties or fabrication quality of fiber-reinforced nanocomposites. The existing literature lacks a reliable and automatic fiber extraction method for morphology analysis based on the scanning electron microscope (SEM) images. This paper proposes four different methods, namely, the simple Hough Transform, opening method, partitioning Hough Transform and gradient based Hough Transform, to automatically identify the fibers from SEM images to expedite the morphology analysis. The performance of these methods are thoroughly evaluated and compared through simulation studies and real case studies.