US 12,347,170 B2
Apparatus, methods and computer programs for calibrating machine learning systems
Harry Cronin, Cambridge (GB); Christopher Wright, London (GB); William Schnabel, Surrey (GB); and Phil Catton, Cambridge (GB)
Assigned to NOKIA TECHNOLOGIES OY, Espoo (FI)
Filed by Nokia Technologies Oy, Espoo (FI)
Filed on Mar. 23, 2022, as Appl. No. 17/702,620.
Claims priority of application No. 21165426 (EP), filed on Mar. 29, 2021.
Prior Publication US 2022/0309769 A1, Sep. 29, 2022
Int. Cl. G06V 10/774 (2022.01); G06F 1/16 (2006.01); G06T 3/00 (2006.01); G06V 10/12 (2022.01); G06V 10/776 (2022.01)
CPC G06V 10/774 (2022.01) [G06F 1/1641 (2013.01); G06T 3/00 (2013.01); G06V 10/12 (2022.01); G06V 10/776 (2022.01); G06V 2201/02 (2022.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
at least one processor; and
at least one memory including computer program code,
the at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:
enable at least one of a first device or second device to display a calibration image, the first device comprising an embedded machine learning system, wherein the calibration image is for calibrating the embedded machine learning system, and wherein the calibration image comprises a training image configured to enable training of the embedded machine learning system;
control an imaging device to capture, at least part of, the calibration image, wherein the imaging device is provided within the first device; and
based on the calibration image captured by the imaging device, calibrate the embedded machine learning system of the first device.