IP Library Granted Patent US 12,401,880
Granted Patent B2
US 12,401,880 · App. 18/352,176 · Granted Aug 26, 2025

Image pickup apparatus and control method therefor

Inventors: Nobushige Wakamatsu (Tokyo, JP); Shinnosuke Osawa (Yokohama, JP); Ryota Ogawa (Kawasaki, JP); Yuki Tsuihiji (Yokohama, JP); Yusuke Shimizu (Kawasaki, JP)
Assignee: Canon Kabushiki Kaisha
H04N23/60H04N23/56H04N23/617G03B17/02
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 12,401,880
App. No.
18/352,176
Granted
Aug 26, 2025
Kind
B2
Abstract

An image pickup apparatus is configured to change a shooting process based on data on a shot image. The image pickup apparatus is configured to, when the image pickup apparatus changes the shooting process, assign greater weights to the data on the shot image based on an instruction from a user than to the data on the shot image automatically processed.

Claims (46)

1. An image processing apparatus comprising:

one or more processors and/or circuitry which functions as:

an acquisition unit configured to acquire first image data obtained by performing a first process using a parameter obtained through machine learning and second image data obtained by performing a second process different from the first process according to an instruction from a user,

wherein the parameter is updated by the machine learning and the machine learning is performed such that a value of the second image data is higher than a value of the first image data.

2. The image processing apparatus according to claim 1 , wherein the one or more processors and/or circuitry further functions as:

an output unit configured to output the first image data and the second image data as training data to a computation unit configured to update the parameter through the machine learning.

3. The image processing apparatus according to claim 1 , wherein

the first process is a process of picking up an image for recording, a timing for the first process being designated automatically, and

the second process is a process of picking up an image for recording, a timing for the second process being designated manually by the user.

4. The image processing apparatus according to claim 1 , wherein the first process and the second process are any one of an image pickup process, an image processing, an image editing process, a subject searching process and a subject registering process.

5. The image processing apparatus according to claim 4 , wherein the image pickup process is a process of picking up an image for recording.

6. The image processing apparatus according to claim 4 , wherein the image processing is at least any one of image processing including distortion correction, white balance adjustment and color interpolation.

7. The image processing apparatus according to claim 4 , wherein the image editing process is at least any one of an image trimming process, an image rotation process, a process for HDR effect, a process for blur effect and a process for color conversion filter effect.

8. The image processing apparatus according to claim 4 , wherein the subject searching process is a process to be applied to an image picked up by driving an image pickup unit in a pan direction.

9. The image processing apparatus according to claim 4 , wherein the subject searching process is a process to be applied to an image picked up by driving an image pickup unit in a tilt direction.

10. The image processing apparatus according to claim 4 , wherein the subject searching process is a process to be applied to an image picked up by driving an image pickup unit in pan and tilt directions.

11. The image processing apparatus according to claim 4 , wherein the subject searching process is a process of searching a subject within a range obtained by cropping a part of a picked-up image.

12. The image processing apparatus according to claim 1 , wherein the image processing apparatus generates a learning model for evaluating images using the first image data and the second image data as training data.

13. An image processing apparatus comprising:

one or more processors and/or circuitry which functions as:

an acquisition unit configured to acquire an image obtained by performing a process using a parameter obtained through machine learning; and

a learning unit configured to value the image according to a user instruction and perform machine learning by using the valued image in order to update the parameter.

14. The image processing apparatus according to claim 13 , wherein the parameter is updated by the machine learning and the machine learning is performed such that the value of the valued image has a higher value than the value of an unvalued image.

15. The image processing apparatus according to claim 13 , wherein the process using the parameter is any one of an image pickup process, an image processing, an image editing process, a subject searching process and a subject registering process.

16. An image processing apparatus comprising:

one or more processors and/or circuitry which functions as:

an acquisition unit configured to acquire an image obtained by performing a process using a parameter obtained through machine learning; and

an output unit configured to value the image according to a user instruction and output the valued image as training data to a computation unit configured to update the parameter through the machine learning.

17. The image processing apparatus according to claim 16 , wherein the process using the parameter is any one of an image pickup process, an image processing, an image editing process, a subject searching process and a subject registering process.

18. The image processing apparatus according to claim 17 , wherein the image editing process is at least any one of an image trimming process, an image rotation process, a process for HDR effect, a process for blur effect and a process for color conversion filter effect.

19. The image processing apparatus according to claim 17 , wherein the subject searching process is a process to be applied to an image picked up by driving an image pickup unit in a pan direction.

20. The image processing apparatus according to claim 17 , wherein the subject searching process is a process to be applied to an image picked up by driving an image pickup unit in a tilt direction.

21. The image processing apparatus according to claim 17 , wherein the subject searching process is a process to be applied to an image picked up by driving an image pickup unit in pan and tilt directions.

22. The image processing apparatus according to claim 17 , wherein the subject searching process is a process of searching a subject within a range obtained by cropping a part of a picked-up image.

23. The image processing apparatus according to claim 17 , wherein the image pickup process is a process of picking up an image for recording.

24. The image processing apparatus according to claim 17 , wherein the image processing is at least any one of image processing including distortion correction, white balance adjustment and color interpolation.

25. The image processing apparatus according to claim 16 , wherein the image processing apparatus generates a learning model for evaluating images using the first image data and the second image data as training data.

26. A method for controlling an image processing apparatus, the method comprising:

acquiring first image data obtained by performing a first process using a parameter obtained through machine learning and second image data obtained by performing a second process different from the first process according to an instruction from a user,

wherein the parameter is updated by the machine learning and the machine learning is performed such that a value of the second image data is higher than a value of the first image data.

27. A method for controlling an image processing apparatus, the method comprising:

acquiring an image obtained by performing a process using a parameter obtained through machine learning; and

valuing the image according to a user instruction and performing machine learning by using the valued image in order to update the parameter.

28. A method for controlling an image processing apparatus, the method comprising:

acquiring an image obtained by performing a process using a parameter obtained through machine learning; and

valuing the image according to a user instruction and outputting the valued image as training data to a computation unit configured to update the parameter through the machine learning.

Priority Claims (3)
JP 2017-188938 · Sep 28, 2017 · national
JP 2017-254231 · Dec 28, 2017 · national
JP 2018-053078 · Mar 20, 2018 · national
Continuity (4)
Continuation 17371437 · Jul 9, 2021
Continuation 16830028 · Mar 25, 2020
Continuation PCTJP2018034818 · Sep 20, 2018
Related Publication 20230362472A1 · Nov 9, 2023
References Cited (9)
US 20030052978A1 · Kehtarnavaz · 2003 [cited by examiner]
US 20090115865A1 · Kamada et al. · 2009 [cited by applicant]
US 20170061329A1 · Kobayashi · 2017 [cited by examiner]
US 20180089592A1 · Zeiler · 2018 [cited by examiner]
US 20190080347A1 · Smith · 2019 [cited by examiner]
CN 105657257A · 2016 [cited by applicant]
JP 2011139230A · 2011 [cited by applicant]
JP 2017158083A · 2017 [cited by applicant]
WO 2016125372A1 · 2016 [cited by applicant]