Estimation of Nano-Pore Size Using Image Processing

Abstract

Nanopores, which are nanometer-sized holes, have been utilized in apparatus that point toward sensing a range of molecules such as DNA and RNA and single proteins The important factor for sensing molecules is diameters of nanopores which can be found through a substantial process called segmenting for nanopores of scanning electron microscope (SEM) images. In this investigation, four segmentation methods, namely, threshold, bilateral filter, k-means, and expectation maximization - Gaussian mixture model (EM-GMM) which has been utilized to segment three SEM images of nanopores efficiently. The quality of segmentation evaluated objectively through computing Rand index among them. Consequently, the nanopore size of Al2O3 films computed by means of SEM images. This study found that EM-GMM segmenting method gives promising results among other examined methods. It is for their high R-index, minimum adjustment parameters (just one variable which set usually 2), and low consuming time. Hence, it can be used efficiently for computing nanopore count and size.

Index Terms: Feature Extraction, Image Segmentation, Nanopore, Segmentation Evaluation