US 11,734,560 B2
Systems and methods for automatic estimation of object characteristics from digital images
Shadrian Strong, Bellevue, WA (US); David Murr, Minneapolis, MN (US); and Lars P. Dyrud, Crownsville, MD (US)
Assigned to OmniEarth, Inc., Arlington, VA (US)
Filed by OmniEarth, Inc., Arlington, VA (US)
Filed on Mar. 5, 2021, as Appl. No. 17/193,651.
Application 17/193,651 is a continuation of application No. 16/118,021, filed on Aug. 30, 2018, granted, now 10,943,149.
Claims priority of provisional application 62/553,011, filed on Aug. 31, 2017.
Prior Publication US 2021/0264217 A1, Aug. 26, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); G06F 16/51 (2019.01); G06F 16/583 (2019.01); G06F 18/21 (2023.01); G06F 18/24 (2023.01); G06F 18/2413 (2023.01); G06N 3/045 (2023.01); G06V 30/19 (2022.01); G06V 30/24 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01)
CPC G06N 3/08 (2013.01) [G06F 16/51 (2019.01); G06F 16/5854 (2019.01); G06F 18/217 (2023.01); G06F 18/24 (2023.01); G06F 18/24143 (2023.01); G06N 3/045 (2023.01); G06V 10/82 (2022.01); G06V 20/176 (2022.01); G06V 30/19173 (2022.01); G06V 30/2504 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for automatic estimation of object features from one or more digital images, comprising:
sub-dividing into two or more segments one or more digital images comprising pixels and depicting one or more object of interest, the one or more object of interest having one or more predetermined feature, wherein each of the two or more segments comprises two or more of the pixels of the digital image, each of the two or more segments sized to be larger than the one or more predetermined feature as depicted in the digital image;
assessing, automatically, content depicted in one or more of the segments for the one or more predetermined feature using machine learning techniques comprising General Image Classification of each of the one or more segments, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined feature; and
determining, automatically, a level of confidence of one or more of the segments having the one or more predetermined feature based on results of the General Image Classification.