Fig. 1
From: Deep learning-based analysis of macaque corneal sub-basal nerve fibers in confocal microscopy images
Pre-processing of the input images using background subtraction. The input images are first pre-processed using a simple flat-fielding technique. On the left is an example input image. Its background intensity is estimated using morphological opening (center image). These background intensities are then subtracted from the original image to produce the image on the right showing more even contrast across its entire field of view