US 12,175,670 B2
Systems and methods for image classification
Pierre Courtiol, Paris (FR); Eric W. Tramel, Le Kremlin Bicetre (FR); Marc Sanselme, Paris (FR); and Gilles Wainrib, Pantin (FR)
Filed by OWKIN, INC., New York, NY (US); and OWKIN FRANCE SAS, Paris (FR)
Filed on Oct. 24, 2022, as Appl. No. 18/049,205.
Application 18/049,205 is a continuation of application No. 17/183,321, filed on Feb. 23, 2021, granted, now 11,482,022.
Application 17/183,321 is a continuation of application No. 16/778,179, filed on Jan. 31, 2020.
Claims priority of provisional application 62/799,936, filed on Feb. 1, 2019.
Prior Publication US 2023/0186467 A1, Jun. 15, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06F 18/21 (2023.01); G06T 7/00 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/69 (2022.01)
CPC G06T 7/0012 (2013.01) [G06F 18/2163 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method for classifying an input image comprising:
extracting a plurality of feature vectors for a plurality of sub-images by applying a convolutional neural network; and
processing the plurality of extracted feature vectors of the plurality of sub-images to classify the input image using a subset of sub-image scores generated for a subset of the plurality of sub-images, wherein, for the plurality of sub-images, a plurality of sub-image scores is generated from the extracted plurality of feature vectors and the subset of sub-image scores is selected from the generated plurality of sub-image scores, wherein the subset of the plurality of sub-images has a smaller number of sub-images than the plurality of sub-images; and
applying a classifier to the selected subset of sub-image scores in order to classify the input image.