| CPC G06T 9/00 (2013.01) [G06F 9/30036 (2013.01); G06F 11/00 (2013.01); G06F 11/08 (2013.01); G06F 17/16 (2013.01); G06K 7/1473 (2013.01); G06N 3/0464 (2023.01); G06N 20/00 (2019.01); G06T 1/0021 (2013.01); G06T 5/60 (2024.01); G06T 7/11 (2017.01); G06T 7/90 (2017.01); G06V 10/70 (2022.01); G06V 10/761 (2022.01); G06V 10/82 (2022.01); H03M 13/00 (2013.01); H03M 13/1105 (2013.01); H03M 13/37 (2013.01); H03M 13/61 (2013.01); H03M 13/616 (2013.01); G06T 2207/10024 (2013.01); H04L 2209/34 (2013.01)] | 12 Claims |

|
1. A system to encode messages into images comprising:
at least one server having one or more processors coupled with memory to:
identify a first image having a first plurality of pixels in a color space having a set of channels;
generate, using a message to encode in the first image, a data matrix identifying a plurality of values;
add, to the message to generate the data matrix, an error correction code determined based at least on a portion of the message; and
apply a machine learning (ML) model comprising a plurality of convolutional layers to the first image and to the data matrix to generate a second image having a second plurality of pixels in the color space, the second image corresponding to the first image encoded with the data matrix across the set of channels in the color space.
|