IP Library › Granted Patent US 11,284,010
Granted Patent B2
US 11,284,010 · App. 17/076,236 · Granted Mar 22, 2022

Apparatus and method for exposure estimation

Inventors: Hironori Aokage (Plainview, NY); Haruki Sekiyama (Port Washington, NY)
Assignees: Canon U.S.A., Inc.; Canon Kabushiki Kaisha
H04N5/2351H04N5/2353H04N5/2355
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 11,284,010
App. No.
17/076,236
Granted
Mar 22, 2022
Kind
B2
Abstract

An apparatus for evaluating an image is provided and includes one or more processors, and one or more memories storing instructions that, when executed by the one or more processors configure the apparatus to perform operations including receiving an input image, determining whether an exposure value corresponding to an input image is to be evaluated based on information obtained by the input image, and evaluating the exposure value corresponding to the input image according to the determined result.

Claims (40)

1. An image evaluating apparatus comprising:

one or more processors, and

one or more memories storing instructions that, when executed by the one or more processors configure the apparatus to perform operations including

receiving an input image;

determining whether an exposure value corresponding to an input image is to be evaluated based on information obtained by the input image, and

evaluating the exposure value corresponding to the input image according to the determined result using an exposure evaluation model generated based on a plurality of training images which have different exposure values and exposure information corresponding to each of the training images.

2. The image evaluating apparatus according to claim 1 , wherein,

in a case where the input image includes night scene image, it is determined that the exposure value corresponding to the input image is not to be evaluated.

3. The image evaluating apparatus according to claim 2 , wherein

the night scene image is an image whose brightness corresponds to a predetermined exposure value and which includes at least one of firework, light from a building, fire, star, and moon.

4. The image evaluating apparatus according to claim 1 , wherein execution of the instructions further configure the apparatus to perform operations including

generating an exposure evaluation model by using a plurality of training images which have different exposure value and exposure information corresponding to each image.

5. The image evaluating apparatus according to claim 1 , further comprising:

a display for displaying an image,

wherein execution of the instructions further configure the apparatus to perform operations including

outputting evaluation information and the input image on the display together, the evaluation information being related to the exposure value corresponding to the evaluated input image.

6. The image evaluating apparatus according to claim 5 , wherein,

in a case where it is determined that the exposure value corresponding to the input image is not to be evaluated, the predetermined information and the input image are output on the display together, the predetermined information being different from the evaluation information and indicating that the exposure value corresponding to the input image is not to be evaluated.

7. The image evaluating apparatus according to claim 5 , wherein,

in a case where it is determined that the exposure value corresponding to the input image is not to be evaluated, the input image is not output on the display.

8. An image evaluating apparatus comprising:

one or more processors, and

one or more memories storing instructions that, when executed by the one or more processors configure the apparatus to perform operations including

receiving an image;

determining a method to evaluate an exposure value corresponding to an input image input by the input unit based on information obtained by the input image, and

evaluating the exposure value corresponding to the image based on the determined method using an exposure evaluation model generated based on a plurality of training images which have different exposure values and exposure information corresponding to each of the training images.

9. An image evaluating method comprising:

inputting an image;

determining if an exposure value corresponding to an input image is to be evaluated based on information obtained by the input image, and

evaluating the exposure value corresponding to the input image according to a determination result using an exposure evaluation model generated based on a plurality of training images which have different exposure values and exposure information corresponding to each of the training images.

10. The image evaluating method according to claim 9 , wherein

in a case where the input image includes night scene image, it is determined that the exposure value corresponding to the input image is not to be evaluated.

11. The image evaluating method according to claim 10 , wherein

the night scene image is an image whose brightness corresponds to a predetermined exposure value and which includes at least one of fire work, light from a building, fire, star, and moon.

12. The image evaluating method according to claim 9 , further comprising:

outputting, on a display, evaluation information and the input image together, the evaluation information being related to the exposure value corresponding to the evaluated input image.

13. A non-transitory computer-readable storage medium storing one or more programs for causing a computer to execute an image evaluating method comprising:

inputting an image;

determining if an exposure value corresponding to an input image is to be evaluated based on information obtained by the input image, and

evaluating the exposure value corresponding to the input image according to a determination result using an exposure evaluation model generated based on a plurality of training images which have different exposure values and exposure information corresponding to each of the training images.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 16, 2022
From: AOKAGE, HIRONORI; SEKIYAMA, HARUKI
To: CANON U.S.A., INC.
Reel/Frame 059027/0508 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 16, 2022
From: CANON U.S.A., INC
To: CANON U.S.A., INC.; CANON KABUSHIKI KAISHA
Reel/Frame 059027/0762 →
Continuity (2)
Provisional Application 62924448 · Oct 22, 2019
Related Publication 20210120164A1 · Apr 22, 2021