US 12,423,348 B2
Classification apparatus, classification method and computer readable medium
Asako Fujii, Tokyo (JP); Iain Melvin, Princeton, NJ (US); Yuki Chiba, Tokyo (JP); Masayuki Sakata, Tokyo (JP); Erik Kruus, Hillsborough, NJ (US); and Chris White, Branchburg, NJ (US)
Assigned to NEC CORPORATION, Tokyo (JP)
Filed by NEC Corporation, Tokyo (JP)
Filed on Mar. 1, 2023, as Appl. No. 18/176,841.
Claims priority of provisional application 63/315,755, filed on Mar. 2, 2022.
Prior Publication US 2023/0315783 A1, Oct. 5, 2023
Int. Cl. G06F 16/583 (2019.01); G06F 16/55 (2019.01); G06F 16/58 (2019.01)
CPC G06F 16/583 (2019.01) [G06F 16/55 (2019.01); G06F 16/5866 (2019.01)] 10 Claims
OG exemplary drawing
 
1. A classification apparatus comprising:
at least one memory storing instructions, and
at least one processor configured to execute the instructions to:
extract moving image data by using a predetermined rule;
display an icon corresponding to the extracted moving image data on a screen of a display unit;
receive an operation performed by a user;
detect a movement of the icon on the screen caused by the operation performed by the user;
specify a classification of the moving image data corresponding to the icon based on a position of the icon on the screen;
learn a weight of each of a plurality of feature information generated from moving image data;
generate a plurality of feature information from the extracted moving image data;
calculate a score for the extracted moving image data by using the generated plurality of feature information and previously learned weights respectively corresponding to each of the plurality of feature information; and
place the icon corresponding to the extracted moving image data at a position on the screen corresponding to the calculated score of the moving image data.