US 12,406,486 B2
Systems and methods for manipulated image detection and image reconstruction
Subham Biswas, Thane (IN); and Saurabh Tahiliani, Noida (IN)
Assigned to Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed by Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed on Sep. 21, 2022, as Appl. No. 17/933,902.
Prior Publication US 2024/0096075 A1, Mar. 21, 2024
Int. Cl. G06V 10/00 (2022.01); G06V 10/70 (2022.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/82 (2022.01) [G06V 10/768 (2022.01); G06V 10/776 (2022.01); G06V 10/7796 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving a plurality of images to train a first neural network;
masking a portion of each of the plurality of images;
inputting the masked images to the first neural network;
generating, by the first neural network, probable pixel values for pixels located in the masked portion of each of the plurality of images;
forwarding the images including the probable pixel values to a second neural network;
determining, by the second neural network, whether each of the probable pixel values is contextually suitable;
identifying pixels in each of the plurality of images that are not contextually suitable;
receiving, by the second neural network, a first image;
detecting, by the second neural network, a manipulated region of the first image; and
masking the manipulated region of the first image.