IP Library › Granted Patent US 12,739,506
Granted Patent B2
US 12,739,506 · App. 18/146,442 · Granted Sep 15, 2026

Information processing apparatus, learning device, imaging apparatus, control method of information processing apparatus, and program

Inventor: Akihiro Uchida (Saitama, JP)
Assignee: FUJIFILM Corporation
H04N23/675G06T3/40G06V10/25G06V10/761G06V2201/07
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,739,506
App. No.
18/146,442
Granted
Sep 15, 2026
Kind
B2
Abstract

An information processing apparatus includes a processor and a memory connected to or built in the processor. In a case in which imaging accompanied by a focus operation in which a specific subject is used as a focus target region is performed by an image sensor, the processor outputs specific subject data related to a specific subject image indicating the specific subject in a captured image obtained by the imaging as data used in machine learning.

Claims (66)

1 . An information processing apparatus comprising:

a processor; and

a memory connected to or built in the processor,

wherein,

the processor displays a plurality of label candidates on a screen for selection and receives a selected label among the plurality of label candidates, wherein each of the plurality of label candidates is a class of a subject image,

in a case in which imaging accompanied by a focus operation in which a specific subject is used as a focus target region is performed by an image sensor, the processor extracts an image of the focus target region as a specific subject image from a captured image obtained by the imaging, and generates training data comprising the specific subject data related to the specific subject image indicating the specific subject in a captured image obtained by the imaging, the selected label which is a class of the specific subject image, and coordinates of the focused target region in the captured image

the processor transmits the generated training data to a computing device for machine learning.

2 . The information processing apparatus according to claim 1 ,

wherein the machine learning is supervised machine learning, and

the processor

gives a label, which is the class of the specific subject image, to the specific subject data, and

outputs the specific subject data as the training data used in the supervised machine learning.

3 . The information processing apparatus according to claim 1 ,

wherein the processor displays the focus target region in an aspect that is distinguishable from other image regions in a state in which a video for display based on a signal output from the image sensor is displayed on a monitor, and

the specific subject image is an image corresponding to a position of the focus target region in the captured image.

4 . The information processing apparatus according to claim 3 ,

wherein the processor displays the focus target region in the aspect that is distinguishable from the other image regions by displaying a frame that surrounds the focus target region in the video for display.

5 . The information processing apparatus according to claim 4 ,

wherein a position of the frame is changeable in accordance with a given position change instruction.

6 . The information processing apparatus according to claim 4 ,

wherein a size of the frame is changeable in accordance with a given size change instruction.

7 . The information processing apparatus according to claim 1 ,

wherein the processor

displays a video for display based on a signal output from the image sensor on a monitor,

receives designation of the focus target region in the video for display, and

extracts the specific subject image based on a region of which a similarity evaluation value indicating a degree of similarity to the focus target region is within a first predetermined range in a predetermined region including the focus target region.

8 . The information processing apparatus according to claim 7 ,

wherein the processor displays the focus target region in an aspect that is distinguishable from other image regions.

9 . The information processing apparatus according to claim 7 ,

wherein at least one of the focus target region or the specific subject image is determined in units of division regions obtained by dividing the predetermined region.

10 . The information processing apparatus according to claim 7 ,

wherein the similarity evaluation value is a value based on a focus evaluation value used in the focus operation.

11 . The information processing apparatus according to claim 7 ,

wherein the similarity evaluation value is a color evaluation value based on color information of the predetermined region.

12 . The information processing apparatus according to claim 7 ,

wherein the processor performs abnormality detection processing in a case in which a degree of difference between a specific subject image for display indicating the specific subject in the video for display and the specific subject image exceeds a second predetermined range, and

the specific subject image for display is determined based on the similarity evaluation value.

13 . The information processing apparatus according to claim 1 ,

wherein the specific subject data includes coordinates of the specific subject image, and

the processor outputs the captured image and the coordinates of the specific subject image as the training data used in the machine learning.

14 . The information processing apparatus according to claim 1 ,

wherein the specific subject data is the specific subject image cut out from the captured image, and

the processor outputs the cut out specific subject image as the training data used in the machine learning.

15 . The information processing apparatus according to claim 1 ,

wherein the processor

stores the training data in the memory, and

performs the machine learning using the training data stored in the memory.

16 . The information processing apparatus of claim 1 ,

wherein the coordinates of the focused target region are position coordinates of at least two corners of the focused target region in the captured image.

17 . A learning device comprising:

a reception device that receives the training data output from the information processing apparatus according to claim 1 ; and

an operation device that performs the machine learning using the training data received by the reception device.

18 . An imaging apparatus comprising:

the information processing apparatus according to claim 1 ; and

the image sensor.

19 . The imaging apparatus according to claim 18 ,

wherein the image sensor performs the imaging at a plurality of focus positions, and

for a plurality of the captured images obtained by performing the imaging, the processor outputs coordinates of the specific subject image obtained from a focus image in which the specific subject is in focus as coordinates of the specific subject image in an out-of-focus image in which the specific subject is not in focus.

20 . A control method of an information processing apparatus, the method comprising:

displaying a plurality of label candidates on a screen for selection and receiving a selected label among the plurality of label candidates, wherein each of the plurality of label candidates is a class of a subject image;

in a case in which imaging accompanied by a focus operation in which a specific subject is used as a focus target region is performed by an image sensor, extracting an image of the focus target region as a specific subject image from a captured image obtained by the imaging, and generating training data comprising the specific subject data related to the specific subject image indicating the specific subject in a captured image obtained by the imaging, the selected label which is a class of the specific subject image, and coordinates of the focused target region in the captured image; and

transmitting the generated training data to a computing device for machine learning.

21 . A non-transitory computer-readable storage medium storing a program executable by a computer to perform a process comprising:

displaying a plurality of label candidates on a screen for selection and receiving a selected label among the plurality of label candidates, wherein each of the plurality of label candidates is a class of a subject image;

in a case in which imaging accompanied by a focus operation in which a specific subject is used as a focus target region is performed by an image sensor, extracting an image of the focus target region as a specific subject image from a captured image obtained by the imaging, and generating training data comprising the specific subject data related to the specific subject image indicating the specific subject in a captured image obtained by the imaging, the selected label which is a class of the specific subject image, and coordinates of the focused target region in the captured image; and

transmitting the generated training data to a computing device for machine learning.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 27, 2022
From: UCHIDA, AKIHIRO
To: FUJIFILM CORPORATION
Reel/Frame 062217/0784 →
Priority Claims (1)
JP 2020-113522 · Jun 30, 2020 · national
Continuity (2)
Continuation PCTJP2021021754 · Jun 8, 2021
Related Publication 20230131704A1 · Apr 27, 2023
References Cited (39)
US 8111304B2 · Ohtsuka et al. · 2012 [cited by applicant]
US 8660344B2 · Nakajima · 2014 [cited by applicant]
US 8953895B2 · Kawanishi et al. · 2015 [cited by applicant]
US 9473694B2 · Inoue · 2016 [cited by applicant]
US 9681037B2 · Sugawara et al. · 2017 [cited by applicant]
US 10455163B2 · Kanatsu · 2019 [cited by applicant]
US 11295426B2 · Horita · 2022 [cited by applicant]
US 20100103286A1 · Akiyama · 2010 [cited by examiner]
US 20160019412A1 · Kang · 2016 [cited by examiner]
US 20190387175A1 · Kikuchi et al. · 2019 [cited by applicant]
US 20200112685A1 · Li · 2020 [cited by examiner]
US 20200387533A1 · Nolte · 2020 [cited by examiner]
US 20230131704A1 · Uchida · 2023 [cited by applicant]
CN 104113686 · 2014 [cited by applicant]
CN 104871058 · 2015 [cited by applicant]
CN 110915193 · 2020 [cited by applicant]
JP H04346580 · 1992 [cited by applicant]
JP 2006333443 · 2006 [cited by applicant]
JP 2009055432 · 2009 [cited by applicant]
JP 2009069996 · 2009 [cited by applicant]
JP 2011160044 · 2011 [cited by applicant]
JP 2012133607 · 2012 [cited by applicant]
JP 2013080428 · 2013 [cited by applicant]
JP 2016099668 · 2016 [cited by applicant]
JP 2018036331 · 2018 [cited by applicant]
JP 2018107593 · 2018 [cited by applicant]
JP 2019118097 · 2019 [cited by applicant]
JP 2019215489 · 2019 [cited by applicant]
JP 2020091702 · 2020 [cited by applicant]
JP 7495498 · 2024 [cited by applicant]
WO 2008133237 · 2008 [cited by applicant]
WO 2012073421 · 2012 [cited by applicant]
“Notice of Reasons for Refusal of Japan Counterpart Application”, issued on Feb. 20, 2024, with English translation thereof, p. 1-p. 11. [cited by applicant]
“Written Opinion of the International Searching Authority (Form PCT/ISA/237) of PCT/JP2021/021754,” mailed on Sep. 14, 2021, with English translation thereof, pp. 1-10. [cited by applicant]
“International Search Report (Form PCT/ISA/210) of PCT/JP2021/021754,” mailed on Sep. 14, 2021, with English translation thereof, pp. 1-5. [cited by applicant]
“Notice of Reasons for Refusal of Japan Counterpart Application”, issued on May 7, 2025, with English translation thereof, p. 1-p. 12. [cited by applicant]
“Office Action of China Counterpart Application”, issued on Dec. 8, 2025, with English translation thereof, pp. 1-30. [cited by applicant]
“Notice of Reasons for Refusal of Japan Counterpart Application”, issued on Nov. 4, 2025, with English translation thereof, p. 1-p. 12. [cited by applicant]
“The Second Office Action of China Counterpart Application”, with English translation thereof, issued on Jun. 6, 2026, pp. 1-32. [cited by applicant]