Short U-net model with average pooling based on in-line digital holography for simultaneous restoration of multiple particles

Abstract

We propose a short U-net model with average pooling to restore in-focus images of multiple transparent particles at their ground truth z-positions, while simultaneously removing their zero-order images, conjugate images, defocused images of other particles, and the noise associated with the optical system. Subsequently, we obtain the lateral location and diameter of each particle efficiently, thus acquiring the particle density within the captured volume. Simulations and experimental results demonstrate that the particle density can be acquired quickly via the proposed short U-net model. Moreover, average pooling processes piece-wise patterns more effectively than alternative methods.