IP Library Granted Patent US 11,042,771
Granted Patent B2
US 11,042,771 · App. 16/348,414 · Granted Jun 22, 2021

Image evaluation device, image evaluation method, and image evaluation program

Inventors: Tokinobu Mitasaki (Yokosuka, JP); Kazuya Hayase (Yokosuka, JP); Atsushi Shimizu (Yokosuka, JP)
Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
G06K9/4609G06K9/3233G06T7/0002H04N5/232H04N5/92H04N5/93H04N17/00
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 11,042,771
App. No.
16/348,414
Granted
Jun 22, 2021
Kind
B2
Abstract

An image evaluation device includes a determination result acquisition unit acquires a result of determining the presence or absence of a difference between an object image that is one of a plurality of images that include three or more images obtained by imaging substantially the same spatial region and each of reference images that are images other than the object image among the plurality of images and an evaluation index acquisition unit configured to acquire an evaluation index for the plurality of images on the basis of at least one of the number of determinations of the presence of the difference between the object image and each reference image and the number of determinations of the absence of the difference between the object image and each reference image.

Claims (34)

1. An image evaluation device, comprising:

a processor; and

a non-transitory storage medium having computer program instructions stored thereon, when executed by the processor, perform to:

a determination result acquisition unit configured to acquire a determination result of determining a presence or absence of a difference between an object image that is one of a plurality of images that include three or more images obtained by imaging substantially the same spatial region and each of reference images that are images other than the object image among the plurality of images; and

an evaluation index acquisition unit configured to acquire an evaluation index for the plurality of images on the basis of at least one of the number of determinations of the presence of the difference between the object image and each reference image and the number of determinations of the absence of the difference between the object image and each reference image,

wherein the plurality of images are time-series images,

wherein the determination result acquired by the determination result acquisition unit indicates the presence or absence of a difference between a small image of a region within the object image and a small image of a region within the reference image, and

wherein the evaluation index acquisition unit is configured to obtain a result of determining the number of pairs of regions determined to have a difference between small images among each pair of a region within the object image and a region within each image of the time-series images other than the object image as the evaluation index.

2. The image evaluation device according to claim 1 , wherein, if a probability that the presence or absence of a difference between the small images is erroneously determined is less than a first threshold value, the evaluation index acquisition unit is configured to obtain a value indicating a priority for evaluating the difference as the evaluation index.

3. The image evaluation device according to claim 2 , further comprising a binarization unit configured to obtain a binary evaluation index indicating the presence or absence of the difference between the small images on the basis of a result of comparing a value according to the evaluation index with a second threshold value.

4. The image evaluation device according to claim 1 , wherein, if a probability that the presence or absence of a difference between the small images is erroneously determined is greater than or equal to a first threshold value, the evaluation index acquisition unit is configured to obtain a value indicating accuracy of a result of determining that the difference between the small images is present as the evaluation index.

5. The image evaluation device according to claim 1 , further comprising a difference determination unit configured to determine the presence or absence of the difference between the small image of the region within the object image and the small image of the region within the reference image and obtain the determination result.

6. The image evaluation device according to claim 1 , further comprising an image processing unit configured to enlarge the small image of the region within the object image on the basis of the evaluation index obtained for each region within the object image.

7. The image evaluation device according to claim 1 , wherein the evaluation index acquisition unit is configured to sort the plurality of images into images that satisfy a quality standard related to the spatial region and images that do not satisfy the quality standard on the basis of the evaluation index.

8. The image evaluation device according to claim 7 , wherein the evaluation index acquisition unit is configured to acquire a ratio of the number of reference images determined to have differences from the object image to the total number of reference images among the plurality of images as the evaluation index.

9. The image evaluation device according to claim 8 , further comprising a removal unit configured to remove the object image that does not satisfy the quality standard from the plurality of images on the basis of a magnitude relationship between the evaluation index and a threshold value.

10. The image evaluation device according to claim 7 , wherein the evaluation index acquisition unit is configured to acquire as the evaluation index either: a first ratio or a second ratio,

wherein the first ratio being a ratio of a total area of small images of regions within the reference images determined to have differences from small images of regions within the object image to a total area of the reference images among the plurality of images, and

the second ratio being a ratio of the number of regions within the reference images including the small images determined to have the differences from the small images of the regions within the object image to the total number of regions within the reference images among the plurality of images.

11. The image evaluation device according to claim 7 , further comprising a difference determination unit configured to determine the presence or absence of the difference between the object image and each reference image.

12. The image evaluation device according to claim 11 , wherein the difference determination unit is configured to determine the reference image determined to have the difference from the object image in an area having a fixed proportion or more with respect to an area of the reference image as the reference image having the difference from the object image.

13. The image evaluation device according to claim 11 , wherein the difference determination unit is configured to add another image determined not to have a difference from an image selected from the plurality of images in the plurality of images.

14. An image evaluation method, comprising the steps of:

acquiring a result of determining a presence or absence of a difference between an object image that is one of a plurality of images that include three or more images obtained by imaging substantially the same spatial region and each of reference images that are images other than the object image among the plurality of images; and

acquiring an evaluation index for the plurality of images on the basis of at least one of the number of determinations of the presence of the difference between the object image and each reference image and the number of determinations of the absence of the difference between the object image and each reference image,

wherein the plurality of images are time-series images,

wherein the determination result acquired by the acquiring of the result of determining indicates the presence or absence of a difference between a small image of a region within the object image and a small image of a region within the reference image, and

wherein, in the acquiring of the evaluation index, a result of determining the number of pairs of regions determined to have a difference between small images among each pair of a region within the object image and a region within each image of the time-series images other than the object image, is obtained as the evaluation index.

15. A non-transitory computer-readable medium storing an image evaluation program for causing a computer provided in an image evaluation device to function as:

a determination result acquisition unit configured to acquire a result of determining a presence or absence of a difference between an object image that is one of a plurality of images that include three or more images obtained by imaging substantially the same spatial region and each of reference images that are images other than the object image among the plurality of images; and

an evaluation index acquisition unit configured to acquire an evaluation index for the plurality of images on the basis of at least one of the number of determinations of the presence of the difference between the object image and each reference image and the number of determinations of the absence of the difference between the object image and each reference image,

wherein the plurality of images are time-series images,

wherein the determination result acquired by the determination result acquisition unit indicates the presence or absence of a difference between a small image of a region within the object image and a small image of a region within the reference image, and

wherein the evaluation index acquisition unit is configured to obtain a result of determining the number of pairs of regions determined to have a difference between small images among each pair of a region within the object image and a region within each image of the time-series images other than the object image as the evaluation index.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 8, 2019
From: MITASAKI, TOKINOBU; HAYASE, KAZUYA; SHIMIZU, ATSUSHI
To: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Reel/Frame 049119/0013 →
Priority Claims (2)
JP JP2016-219716 · Nov 10, 2016 · national
JP JP2016-224922 · Nov 18, 2016 · national
Continuity (1)
Related Publication 20190272439A1 · Sep 5, 2019