Fig. 6: Unsupervised Machine Learning Approach for Retinal Fundus Image Denoising. | npj Microgravity

Fig. 6: Unsupervised Machine Learning Approach for Retinal Fundus Image Denoising.

From: Terrestrial health applications of visual assessment technology and machine learning in spaceflight associated neuro-ocular syndrome

Fig. 6

An unsupervised approach for denoising fundus images using Auto-encoder architecture. The architecture consists of an encoder and decoder network. The encoder consists of convolution followed by downsampling layers, Whereas the decoder consists of upsampling layers. Other than that, it has multiple skin connections in between using concatenate layers.

Back to article page