Unsupervised spatial-resolution enhancement of electron beam measurement using deconvolution

Abstract

This paper presents an unsupervised de-blurring technique that enhances the spatial resolution of electron beam (EB) diagnostic instruments. The inherent degradation in EB diagnosis waveforms is modeled using the convolution between the EB current distribution and the sensor characteristic function. Due to the use of various sensors, the diagnosis results are device dependent. Sensor inaccuracy has a detrimental effect on the deconvolution-based restoration of the ground truth signal. In this research this adverse effect is mitigated by an accurate sensor's Point Spread Function (PSF) derivation, which allows the successful restoration of waveforms. As approximate size of the sensor is known, a probability distribution is assigned to the expected interval of PSF features in the frequency domain, which increases the accuracy of the PSF analysis. By deploying this method, sensor inaccuracies are considered in the dynamic PSF formation, hence providing a promising consistency to the restoration. Restoration is performed with Wiener inverse filter and blind-deconvolution and results are compared with the ground truth pulses, obtained using a sensitive sensor (18um diameter). Experimental results confirm that the purposed method delivers a universal device independent measurement, facilitates instrument production, and EB characterization.