Granted Patent B2

US 12,632,920 · App. 18/325,015 · Granted May 19, 2026

Inventor: Satoshi Ihara (Tokyo, JP)

Assignee: FUJIFILM Corporation

G06T3/4007G06T7/11G06T2207/20084

Abstract

Claims (26)

1 . An image processing apparatus comprising:

at least one processor, configured to:

convert a size of a target image to derive a size-converted image;

segment the size-converted image into regions of at least one class by using a segmentation model constructed by machine-learning a neural network to derive a plurality of class images in which a pixel value of each pixel represents class-likeness for the at least one class;

convert a size of at least one class image into the size of the target image to derive at least one converted class image; and

segment the target image based on a pixel value in each pixel of the at least one converted class image.

2 . The image processing apparatus according to claim 1 ,

wherein the size conversion is enlargement, reduction, or normalization in at least one direction in which pixels are arranged in the target image.

3 . The image processing apparatus according to claim 1 ,

wherein the pixel value of the class image is a score, which is derived by the neural network and represents a probability of being in the at least one class.

4 . The image processing apparatus according to claim 1 ,

wherein the at least one processor is configured to convert the size of the class image into the size of the target image through an interpolation calculation.

5 . The image processing apparatus according to claim 1 ,

wherein the at least one processor is configured to derive argmax of a pixel value of a corresponding pixel in the at least one converted class image to segment the target image.

6 . The image processing apparatus according to claim 1 ,

wherein the at least one processor is configured to sequentially perform derivation of the converted class image and segmentation of the target image for each class.

7 . An image processing method implemented by an image processing apparatus having at least one processor, the method comprising:

converting, by the at least one processor, a size of a target image to derive a size-converted image;

segmenting, by the at least one processor, the size-converted image into regions of at least one class by using a segmentation model constructed by machine-learning a neural network to derive a plurality of class images in which a pixel value of each pixel represents class-likeness for the at least one class;

converting, by the at least one processor, a size of at least one class image into the size of the target image to derive at least one converted class image; and

segmenting, by the at least one processor, the target image based on a pixel value in each pixel of the at least one converted class image.

8 . A non-transitory computer-readable storage medium that stores an image processing program causing a computer having at least one processor to execute:

a procedure of converting, by the at least one processor, a size of a target image to derive a size-converted image;

a procedure of segmenting, by the at least one processor, the size-converted image into regions of at least one class by using a segmentation model constructed by machine-learning a neural network to derive a plurality of class images in which a pixel value of each pixel represents class-likeness for the at least one class;

a procedure of converting, by the at least one processor, a size of at least one class image into the size of the target image to derive at least one converted class image; and

a procedure of segmenting, by the at least one processor, the target image based on a pixel value in each pixel of the at least one converted class image.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (54)