PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
We present a new tool based on unsupervised learning to ensure the pictorial information recorded is as close as possible to the original by denoising the images produced, and thereby allowing to make more knowledgeable decisions. The algorithm is used to clean off-axis holograms. To denoise the acquired off-axis holograms, our technique takes advantage of the prior knowledge we have regarding the expected image and uses it to erase the noise, providing a significantly clearer image. We applied the technique to off-axis holograms of individual sperm cells acquired without labeling.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.