US 11,854,113 B2
Deep learning methods for event verification and image re-purposing detection
Lakshmanan Nataraj, Goleta, CA (US); Michael Gene Goebel, Santa Barbara, CA (US); Bangalore S. Manjunath, Santa Barbara, CA (US); and Shivkumar Chandrasekaran, Santa Barbara, CA (US)
Assigned to Mayachitra, Inc., Santa Barbara, CA (US)
Filed by Mayachitra, Inc., Santa Barbara, CA (US)
Filed on Nov. 3, 2020, as Appl. No. 17/088,132.
Claims priority of provisional application 62/957,021, filed on Jan. 3, 2020.
Prior Publication US 2021/0209425 A1, Jul. 8, 2021
Int. Cl. G06K 9/00 (2022.01); G06T 1/00 (2006.01); G06F 16/55 (2019.01); G06T 3/40 (2006.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06F 18/2415 (2023.01); G06F 18/22 (2023.01); G06F 18/213 (2023.01); G06F 18/2431 (2023.01); G06V 30/24 (2022.01); G06V 10/764 (2022.01); G06V 20/00 (2022.01); G06V 20/40 (2022.01)
CPC G06T 1/0028 (2013.01) [G06F 16/55 (2019.01); G06F 18/213 (2023.01); G06F 18/22 (2023.01); G06F 18/2415 (2023.01); G06F 18/2431 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06T 3/40 (2013.01); G06V 10/764 (2022.01); G06V 20/35 (2022.01); G06V 30/248 (2022.01); G06V 20/44 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing, using one or more processors, an image, the image being attributed to a first specific event designated by a first time period and a first location;
generating a resized image using the image;
generating an image feature vector by applying an image classification neural network to the resized image, the image classification neural network comprising a convolutional layer that outputs to a fully-connected layer that generates the image feature vector;
generating analysis of the image by processing the image feature vector using a machine-learning classifier trained to analyze the image feature vector;
based on the analysis, determining a second specific event designated by a second time period and second location that is attributed to the image, the second specific event being different than the first specific event; and
authenticating the image based on a probability that the image was captured at the second specific event instead of the first specific event.