Zhong L Zheng

US Patent:

20210004648, Jan 7, 2021

Filed:

Jul 2, 2020

Appl. No.:

16/919840

Inventors:

- Jersey City NJ, US
Zhong Zheng - Jersey City NJ, US
Terrance E. Boult - Colorado Springs CO, US
Maneesh Kumar Singh - Lawrenceville NJ, US

Assignee:

Insurance Services Office, Inc. - Jersey City NJ

International Classification:

G06K 9/62
G06K 9/00
G06K 9/40
G06K 9/46
G06N 3/08
G06N 3/04

Abstract:

Computer vision systems and methods for localizing image forgery are provided. The system generates a constrained convolution via a plurality of learned rich filters. The system trains a convolutional neural network with the constrained convolution and a plurality of images of a dataset to learn a low level representation of each image among the plurality of images. The low level representation is indicative of a statistical signature of at least one source camera model of each image. The system can determine a splicing manipulation localization by the trained convolutional neural network.