摘要：Speckle-tracking imaging has the advantages of simple setup and high-sensitivity to slowly varying phase gradients. Subset size choice is regarded as a trade-off problem for speckle-tracking X-ray imaging where one needs to balance the spatial resolution and accuracy, where the subset was defined as the region of interest of windowing choice for digital image correlation algorithm. An adaptive subset size choice method based on a Fourier transform for effectively detecting sample phase information without foreknowledge of the sample structure is presented in this study. The speckle-tracking phase-contrast and the form of dark-field imaging based on this method have the advantages of (i) high resolution and time saving compared to large subset choice and (ii) partially improvement the influence from experimental noises, background fluctuations, and false signals compared to small subset choice at the same time. This method has proven to be particularly robust in the experimental condition of poor signal-to-noise ratio. The proposed method may be expanded to all speckle-based imaging methods and other imaging techniques based on the subset or window matching.
