Detecting particle quantity from raw reconstructed images using digital holography and deep learning

We propose a modified residual neural network (ResNet) to quickly and accurately detect the particle quantity from raw reconstructed images of a high-density particle solution in digital holography. The raw reconstructed image is fed into the modified ResNet to obtain the particle quantity. Then, the quantity and particle concentration in the captured volume are calculated. The metrological challenge is modeled as a regression problem in deep learning. The average relative error of the holograms in the test dataset is less than 10% even when predicting the particle quantities untrained by the model. Hence, an accurate particle quantity is obtained even when the raw reconstructed images are not denoised, thereby reducing the processing time.