Image processing device, image processing method, and computer-readable recording medium

• US 10,147,015 B2
• Filed: 04/24/2015
• Issued: 12/04/2018
• Est. Priority Date: 05/07/2014
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Higa, Kyota
• Primary Examiner(s): MOTSINGER, SEAN T
• Application Number:
  US15/306,166
• Publication Number:
  US 20170061231A1
• Time in Patent Office: 1,320 Days
• CPC Class Codes: G06F 18/2113 by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06V 10/757 Matching configurations of points or features
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

Provided is an image processing device that can suppress deterioration in the accuracy of identifying a subject, even in cases where the shape of the subject in an image is deformed.

A feature amount calculation means 81 detects feature points from an image, and calculates, for each feature point, a local feature amount for the feature point on the basis of a peripheral region of said feature point, including said feature point. A correlation identifying means 82 specifies the correlation between feature points in a first image and feature points in a second image on the basis of the local feature amount of each feature point in the first image and the local feature amount of each feature point in the second image. A partial region detection means 83 detects, from one of the first image or the second image, partial regions each including a feature point in said image. A matching means 84 determines, for each partial region, whether or not a subject in the first image is identical with or similar to a subject in the second image on the basis of the feature point included in the partial region and a feature point corresponding to the feature point.

Claims

1. An image processing device comprising:

a processor configured to function as;

a local feature amount calculation unit configured to detect feature points in each of a first image and a second image and calculates, for each of the feature points, a local feature amount of the feature point, based on a peripheral region of the feature point, the peripheral region including the feature point;

a correlation identifying unit configured to specify, based on the local feature amount of each of the feature points of the first image and the local feature amount of each of the feature points of the second image, a correlation between the feature point of the first image and the feature point of the second image;

a partial region detection unit configured to detect partial regions including the first image; and

a matching unit configured to determine, for each of the partial regions, whether or not an object in the first image and an object in the second image are the same or similar based on the feature points included in the partial region and the feature points of the second image which corresponds to each of the feature points in the partial region;

wherein the partial region detection unit detects partial regions, based on a first scale value information group and a second scale value information group, the first scale value information group being a set of pieces of size information, of peripheral regions corresponding to each of the feature points of the first image, and the second scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the second image.

2. The image processing device according to claim 1,

wherein the partial region detection unit detects the partial region, based on a coordinate value of each of the feature point in the first image and a coordinate value of each of the feature point in the second image.

3. The image processing device according to claim 1,

wherein the partial region detection unit transforms coordinates of the feature point of the first image by using size information and direction information of a peripheral region corresponding to the feature point, coordinates of a feature point of a different image corresponding to the feature point, and size information and direction information of a peripheral region corresponding to the feature point of the different image corresponding to the feature point.

4. The image processing device according to claim 1,

wherein the matching unit determines whether or not an object in the first image and an object in the second image are same or similar, based on a first scale value information group, a second scale value information group and pieces of coordinate value information of each of the feature points of both the first image and the second image, the first scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the first image and the second scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the second image.

5. The image processing device according to claim 1,

wherein the matching unit determines whether or not an object in the first image and an object in the second image are same or similar, based on a first direction information group, a second direction information group and coordinate value information of each of the feature points of both the first image and the second image, the first direction information group being a set of pieces of direction information corresponding to each of the feature points of the first image and the second direction information group being a set of pieces of direction information corresponding to each of the feature points of the second image.

6. An image processing device comprising:

a processor configured to function as;

a local feature amount calculation unit configured to detect feature points in each of a first image and a second image and calculates, for each of the feature points, a local feature amount of the feature point, based on a peripheral region of the feature point, the peripheral region including the feature point;

a correlation identifying unit configured to specify, based on the local feature amount of each of the feature points of the first image and the local feature amount of each of the feature points of the second image, a correlation between the feature point of the first image and the feature point of the second image;

a partial region detection unit configured to detect partial regions including the feature points in the first image; and

a matching unit configured to determine, for each of the partial regions, whether or not an object in the first image and an object in the second image are the same or similar based on the feature points included in the partial region and the feature points of the second image which corresponds to each of the feature points in the partial region;

wherein the partial region detection unit detects partial regions, based on a first direction information group and a second direction information group, the first direct information group being a set of pieces of direction information corresponding to each of the feature points of the first image, and the second direction information group being a set of pieces of direction information corresponding to each of the feature points of the second image.

7. The image processing device according to claim 6,

wherein the partial region detection unit detects the partial region, based on a coordinate value of each of the feature point in the first image and a coordinate value of each of the feature point in the second image.

8. The image processing device according to claim 6,

wherein the partial region detection unit transforms coordinates of the feature point of the first image, buy using size information and direction information of a peripheral region corresponding to the feature point, coordinates of a feature point of a different image corresponding to the feature point, and size information and direction information of a peripheral region corresponding to the feature point of the different image corresponding to the feature point.

9. The image processing device according to claim 6,

wherein the matching unit determines whether or not an object in the first image and an object in the second image are same or similar, based on a first scale value information group, a second scale information group and coordinate value information of each of the feature points of both the first image and the second image, the first scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the first image and the second scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the second image.

10. The image processing device according to claim 6,

wherein the matching unit determines whether or not an object in the first image and an object in the second image are same or similar, based on a first direction information group, a second direction information group and pieces of coordinate value information of each of the feature points of both the first image and the second image, the first direction information group being a set of pieces of direction information corresponding to each of the feature points of the first image and the second direction information group being a set of pieces of direction information corresponding to each of the feature points of the second image.

11. An image processing method comprising:

detecting feature points in each of a first image and a second image and calculating, for each of the feature points, a local feature amount of the feature point, based on a peripheral region of the feature point, the peripheral region including the feature point;

identifying, based on the local feature amount of each of the feature points of the first image and the local feature amount of each of the feature points of the second image, a correlation between the feature point of the first image and the feature point of the second image;

detecting partial regions including the feature points in the first image based on a first scale value information group and a second scale value information group, the first scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the first image, and the second scale value information group being a set of pieces of size information of peripheral regions corresponding to each of the feature points of the second image; and

determining, for each of the partial regions, whether or not an object in the first image and an object in the second image are the same or similar, based on the feature points included in the partial region and the feature points of the second image which corresponds to each of the feature points in the partial region.

12. An image processing method comprising:

detecting feature points in each of a first image and a second image and calculating, for each of the feature points, a local feature amount of the feature point, based on a peripheral region of the feature point, the peripheral region including the feature point;

identifying, based on the local feature amount of each of the feature points of the first image and the local feature amount of each of the feature points of the second image, a correlation between the feature point of the first image and the feature point of the second image;

detecting partial regions including the feature points in the first image based on a first direction information group and a second direction information group, the first direction information group being a set of pieces of direction information corresponding to each of the feature points of the first image, and the second direction information group being a set of pieces of direction information corresponding to each of the feature points of the second image; and

determining, for each of the partial regions, whether or not an object in the first image and an object in the second image are the same or similar, based on the feature points included in the partial region and the feature points of the second image which corresponds to each of the feature points in the partial region.