Size of image input of neural networks while resizing may not be appropriate


I have the following problem while using convolutional neural networks to detect forgeries: Resizing the image to fit the required input size may not be a good way because the forgery detection largely relies on the details of images, for example, the noise. Thus the resizing process may change/hurt the details.

Existing methods mainly use image patches (obtained from cropping) that have the same size. This way, however, will drop the spatial information.

I'm looking for some suggestions on how to deal with this problem (input size inconsistency) without leaving out the spatial information.

Ivan Zhu

Posted 2019-11-19T13:04:34.387

Reputation: 51

What exactly is the spatial information that you fear to lose? How would it be an input to the forgery detection? If I understood correctly, the detection depends mostly on local features, so cropping seems to be a valid step. – Hans-Martin Mosner – 2019-11-20T11:04:05.320

No answers