# Does Feeding Edge detected images to the CNNs make sense?

Are edge detected images fed to the CNN based architectures like VGG16, etc? I know that CNNs are able to detect features like Edges, lines, contours, etc but what will happen if one feeds edge detected images to the Convolutional Neural Networks?

• Why would you do that? You might loose additional features in your data. I'd also scale data to [-1, 1] range, where -1 is the background. This data is sparse and you don't want to zero out your net. – Piotr Rarus - Reinstate Monica Dec 10 '19 at 9:52