Combining gradient ascent search and support vector machines for effective autofocus of a field emission–scanning electron microscope

Abstract

Autofocus is an important issue in electron microscopy, particularly at high magnification. It consists in searching for sharp image of a specimen, that is corresponding to the peak of focus. The paper presents a machine learning solution to this issue. From seven focus measures, support vector machines fitting is used to compute the peak with an initial guess obtained from a gradient ascent search, that is search in the direction of higher gradient of focus. The solution is implemented on a Carl Zeiss Auriga FE-SEM with a three benchmark specimen and magnification ranging from x300 to x160 000. Based on regularized nonlinear least squares optimization, the solution overtakes the literature nonregularized search and Fibonacci search methods: accuracy improvement ranges from 1.25 to 8 times, fidelity improvement ranges from 1.6 to 28 times, and speed improvement ranges from 1.5 to 4 times. Moreover, the solution is practical by requiring only an off-line easy automatic train with cross-validation of the support vector machines.

An autofocus algorithm considering wavelength changes for large scale microscopic hyperspectral pathological imaging system

“…2. If traversal search is adopted, the start and end of the search are determined by (10) and then a set of image sharpness evaluation value of the image captured by the step size of L temp is calculated. The position of the clearest image is the optical position in this iteration.…”

“…If quadratic curve simulation with fixed number of points is used, the start and end of the search are defined by (10) and the step size of a single movement L Δ under a fixed number of points is calculated in (11).…”

“…Hardwarebased methods directly measure the distance from object lens to slide and software-based methods will determine the optical focus position using the out-of-focus images acquired in stack along the z-axis [9]. Software-based autofocus scheme is mainly composed of two steps: image sharpness evaluation algorithm and peak search algorithm [10]. Image sharpness function has direct effects on the focus curve and it is of great importance in calculating the difficulty coefficient of image quality assessment and find out the best path to ideal focusing peak [11].…”