US 12,277,751 B2
Image processing apparatus, learning apparatus, inference apparatus, and image processing method
Takashi Ida, Kawasaki Kanagawa (JP); and Toshiyuki Ono, Kawasaki Kanagawa (JP)
Assigned to Kabushiki Kaisha Toshiba, Tokyo (JP)
Filed by KABUSHIKI KAISHA TOSHIBA, Tokyo (JP)
Filed on Sep. 9, 2022, as Appl. No. 17/930,755.
Claims priority of application No. 2022-019857 (JP), filed on Feb. 10, 2022.
Prior Publication US 2023/0252762 A1, Aug. 10, 2023
Int. Cl. G06V 10/77 (2022.01); G06V 10/26 (2022.01); G06V 10/75 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/7715 (2022.01) [G06V 10/26 (2022.01); G06V 10/751 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. An image processing apparatus, comprising processing circuitry configured to:
generate, for N processed images based on an input image, N being an integer equal to greater than 3, N feature amounts by performing feature amount extraction processing using a neural network;
store process data generated during the feature amount extraction processing in a memory;
select a maximum feature amount by performing two or more comparisons with M combinations among the N feature amounts, M being an integer equal to 2 or more and (N−1) or less; and
release (M−1) or less pieces of process data that correspond to (M−1) or less feature amounts not having been selected from the memory for each of the two or more comparisons.