US 12,169,984 B2
Training set sufficiency for image analysis
Oron Nir, Herzliya (IL); Royi Ronen, Tel Aviv (IL); Ohad Jassin, Tel Mond (IL); Milan M. Gada, Redmond, WA (US); and Mor Geva Pipek, Giv'Atayim (IL)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed on Jan. 25, 2021, as Appl. No. 17/157,427.
Application 17/157,427 is a continuation of application No. 15/977,517, filed on May 11, 2018, granted, now 10,902,288.
Prior Publication US 2021/0174146 A1, Jun. 10, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/70 (2022.01); G06F 18/21 (2023.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 40/16 (2022.01)
CPC G06V 40/173 (2022.01) [G06F 18/211 (2023.01); G06F 18/2148 (2023.01); G06F 18/217 (2023.01); G06V 10/70 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 40/175 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method of improving a performance of an object recognition model comprising:
training the object recognition model to recognize an object using a set of training images;
calculating a performance score measuring the object recognition model's ability to accurately identify the object in one or more validation images;
selecting an image characteristic that would cause a performance improvement in the object recognition model when a new image containing the image characteristic is added to a new set of training images;
upon selecting the image characteristic, outputting for display to a user an interface asking the user to generate a new training image with a label by selecting an area of the new training image that depicts the object associated with the label, wherein the user selects the new training image from a set of new training images including the image characteristic displayed in a user interface;
adding the new training image to the new set of training images; and
retraining the object recognition model using the new set of training images.