US 12,412,228 B2
Learning systems and methods
Tony F. Rodriguez, Portland, OR (US); Osama M. Alattar, Tigard, OR (US); Hugh L. Brunk, Portland, OR (US); Joel R. Meyer, Lake Oswego, OR (US); William Y. Conwell, Portland, OR (US); and Ajith M. Kamath, Beaverton, OR (US)
Assigned to Digimarc Corporation, Beaverton, OR (US)
Filed by Digimarc Corporation, Beaverton, OR (US)
Filed on Mar. 14, 2022, as Appl. No. 17/694,396.
Application 17/694,396 is a division of application No. 17/152,498, filed on Jan. 19, 2021, granted, now 11,625,805.
Application 17/152,498 is a division of application No. 15/446,811, filed on Mar. 1, 2017, granted, now 10,902,539, issued on Jan. 26, 2021.
Application 15/446,811 is a continuation of application No. 14/449,821, filed on Aug. 1, 2014, granted, now 9,594,983, issued on Mar. 14, 2017.
Claims priority of provisional application 61/880,798, filed on Sep. 20, 2013.
Claims priority of provisional application 61/861,931, filed on Aug. 2, 2013.
Prior Publication US 2022/0270199 A1, Aug. 25, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 1/00 (2006.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06F 21/16 (2013.01); G06V 10/24 (2022.01); G06V 10/774 (2022.01); G06V 20/20 (2022.01)
CPC G06T 1/0021 (2013.01) [G06F 18/214 (2023.01); G06F 18/2155 (2023.01); G06F 18/2413 (2023.01); G06F 21/16 (2013.01); G06V 10/245 (2022.01); G06V 10/774 (2022.01); G06V 10/7753 (2022.01); G06V 20/20 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising the acts:
providing plural images as training images to a learning system;
decoding machine-readable identifiers from said plural images;
providing information based on the decoded machine-readable identifiers to the learning system for use in training the learning system with the training images; and
training the learning system with information obtained about the training images from the decoded machine-readable identifiers wherein the machine-readable identifiers comprise digital watermarks, the learning system comprises a neural network, wherein the neural network is incorporated into a digital watermark detector to improve digital watermark detection in images as measured by a signal confidence metric, and the method further comprises the acts of:
decoding digital watermarks from the plural images, yielding payload data;
using the payload data to assess the plural images from which the payload data is decoded; and
employing the payload data in training the neural network.