US 11,758,069 B2
Systems and methods for identifying non-compliant images using neural network architectures
Theban Stanley, San Bruno, CA (US); Binwei Yang, Milpitas, CA (US); and Cun Mu, Jersey City, NJ (US)
Assigned to WALMART APOLLO, LLC, Bentonville, AR (US)
Filed by Walmart Apollo, LLC, Bentonville, AR (US)
Filed on Jan. 27, 2020, as Appl. No. 16/773,114.
Prior Publication US 2021/0232620 A1, Jul. 29, 2021
Int. Cl. G06V 10/40 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); H04N 1/32 (2006.01); G06F 16/53 (2019.01); G06F 16/953 (2019.01); G06N 3/04 (2023.01)
CPC H04N 1/32283 (2013.01) [G06F 16/53 (2019.01); G06F 16/953 (2019.01); G06N 3/04 (2013.01); G06V 10/40 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising:
receiving images, via the one or more processors, at an electronic platform;
generating, using a fingerprinting network associated with a neural network architecture, feature embeddings corresponding to features in the images, wherein the fingerprinting network associated with the neural network architecture comprises a feature extraction component, and wherein generating the feature embeddings further comprises using the feature extraction component to generate the feature embeddings corresponding to the features in the images;
generating, using the fingerprinting network, codes for the images, wherein the codes are based on the feature embeddings;
storing the codes in one or more databases;
receiving, at the electronic platform, a non-compliant image comprising non-compliant content;
identifying the non-compliant content in the non-compliant image; and
searching, using multi-modal search options that enable both image content and text content of the images to be searched, the codes in the one or more databases to identify one or more of the images comprising non-compliant content similar to, or same as, the non-compliant content included in the non-compliant image.