US 11,704,923 B2
Efficient image analysis
Matthew J. Bridges, New Providence, NJ (US); Alessandro Fin, Los Gatos, CA (US); Hartwig Adam, Marina Del Rey, CA (US); and Jeffrey M. Gilbert, Los Altos, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Mar. 27, 2020, as Appl. No. 16/832,182.
Application 16/832,182 is a continuation of application No. 15/754,909, granted, now 10,621,435, previously published as PCT/US2018/017634, filed on Feb. 9, 2018.
Claims priority of provisional application 62/508,873, filed on May 19, 2017.
Prior Publication US 2020/0226382 A1, Jul. 16, 2020
Int. Cl. G06V 30/413 (2022.01); G06V 20/20 (2022.01); G06V 10/98 (2022.01); H04N 5/445 (2011.01); H04N 5/765 (2006.01); G06F 18/24 (2023.01); G06F 18/20 (2023.01); H04N 23/62 (2023.01); H04N 23/68 (2023.01); G06V 30/19 (2022.01); G06F 3/04842 (2022.01)
CPC G06V 30/413 (2022.01) [G06F 18/24 (2023.01); G06F 18/285 (2023.01); G06V 10/993 (2022.01); G06V 20/20 (2022.01); G06V 30/19113 (2022.01); H04N 5/44504 (2013.01); H04N 5/765 (2013.01); H04N 23/62 (2023.01); H04N 23/6812 (2023.01); G06F 3/04842 (2013.01); G06V 2201/10 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a camera configured to capture images;
a data processing apparatus; and
a memory storage apparatus in data communication with the data processing apparatus, the memory storage apparatus storing instructions executable by the data processing apparatus and that upon such execution cause the data processing apparatus to perform operations comprising, for a particular image of the images:
analyzing, using a coarse classifier, the particular image to determine whether the particular image depicts at least one object of one or more particular classes of objects;
when the particular image depicts an object of the one or more particular classes of objects:
causing the particular image to be analyzed using an object recognition process to recognize one or more objects depicted in the particular image; and
presenting content related to the one or more recognized objects; and
when the particular image does not depict an object of the one or more particular classes of objects, determining to not analyze the particular image using the object recognition process.