George Nehmetallah

Traditional analytical Zernike methods for tomographic encoding require multiplying large Zernike polynomial matrices, which leads to substantial computational overhead. Moreover, the inverse Zernike matrices must be precomputed and stored, resulting in significant memory consumption—an issue that becomes increasingly severe as the Zernike order or tomogram resolution grows.

We propose a fast, new, position-independent reconstruction method, to our knowledge, for coherence holography using deep learning (DL) method, dubbed fast deep coherence holography (FDCH). Our trained network was developed to reconstruct the complex object field at the location corresponding to the position of the camera, which opens the ability to apply angular spectrum propagation to reconstruct the 3D object.

This research studied the effect of variations in a sensor’s ${\rm F}\lambda /{\rm d}$ metric value (FLD) on the performance of machine learning algorithms such as the YOLO (You Only Look Once) algorithm for object classification. The YOLO_v3 and YOLO_v10 algorithms were trained using static imagery provided in the commonly available training dataset provided by Teledyne FLIR Systems.