6

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.

nbro
  • 39,006
  • 12
  • 98
  • 176
Ivan Zhu
  • 61
  • 1
  • 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 Nov 20 '19 at 11:04
  • Would you share the average size of your image? Have you tried with large input tensor? – Cloud Cho Jun 30 '21 at 19:21

1 Answers1

0

I don't think that the input size inconsistency won't leave out spatial information in the Convolutional Neural Network. The image resizing would loose the characteristics of the object on the image.

It looks like that you don't want to crop your input image, which looks like being fabricated. I like to suggest these preprocessing before the Convolutional Neural Network:

  (1) Find an original image or a picture of the real object
  (2) Perform image registration between a suspicious image and the original image (the registration result should be fine)
  (3) Calculate color difference in each pixel position
  (4) Generate new image with these differences
  (5) Feed to your Convolutional Neural Network for the anomaly detection

Cloud Cho
  • 157
  • 1
  • 7