Image processing apparatus, image processing method and program

• US 8,385,656 B2
• Filed: 10/21/2009
• Issued: 02/26/2013
• Est. Priority Date: 10/23/2008
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Sohma, Hidetomo, Shiiyama, Hirotaka, Matsushita, Masahiro, Magai, Koichi
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US12/603,427
• Publication Number:
  US 20100104197A1
• Time in Patent Office: 1,224 Days
• Field of Search: 382/181, 382/190, 382/195, 382/209, 382/224, 382/225, 382/305, 382/218, 382/298, 382/299
• US Class Current: 382/195
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/52 Scale-space analysis, e.g. wavelet analysis multi-scale boundary representations G06V10/42

Abstract

An image processing apparatus reduces two input images to be compared by the predetermined number of times to generate two image groups, extracts a plurality of feature points and a local feature amount of each feature point from these image groups, and determines a combination of feature points in which local feature amounts are similar to each other, between the image groups. Then, the image processing apparatus determines a relation of a reasonable combination, assigns high weights to the reasonable combination, and calculates a similarity degree between the two input images.

Claims

1. An image processing apparatus comprising:

a conversion unit configured to reduce an input image by a predetermined number of times to generate an image group containing the input image;

an extraction unit configured to extract a plurality of feature points and a local feature amount of each feature point from the image group;

a determination unit configured to compare a first image of a first image group generated from a first input image by the conversion unit with a second image of a second image group generated from a second input image by the conversion unit, and to determine a relation between the first image and the second image in which a size of an object of the first image and that of the second image get closer; and

a calculation unit configured to assign high weights to a combination of feature points extracted from images having the relation determined by the determination unit to calculate a similarity degree between the first input image and the second input image.

2. The image processing apparatus according to claim 1, wherein the determination unit determines a feature point of the second image group having a local feature amount similar to a local feature amount of each feature point of the first image group as a combination.

3. The image processing apparatus according to claim 1, wherein the extraction unit extracts a position of respective feature points and the calculation unit generates a transformation matrix based on a position relation of each feature point to calculate reasonableness of the transformation matrix as the similarity degree.

4. The image processing apparatus according to claim 1, further comprising:

an output unit configured to output information concerning the second image having an object similar to an object of the first image as a search result.

5. The image processing apparatus according to claim 1,

wherein the determination unit regards a feature point of the second image group having a local feature amount similar to each of the feature points of the first image group as a corresponding feature point based on a degree of similarity of a local feature amount of each feature point, and

wherein the determination unit determines a ratio or a difference between a reduction rate of the first image and a reduction rate of the second image in which the corresponding feature point frequently appears as a relation in a case where the size of the object of the first image and that of the second image get closer.

6. An image processing apparatus comprising:

a conversion unit configured to reduce an input image by a predetermined number of times to generate an image group containing the input image;

an extraction unit configured to extract a plurality of feature points and a local feature amount of each feature point from the image group;

a determination unit configure to compare a first image of a first image group generated from a first input image by the conversion unit with a second image of a second image group generated from a second input image by the conversion unit, and to determine a relation between the first image and the second image in which a size of an object of the first image and that of the second image get closer; and

a calculation unit configured to determine, as to the first image and the second image which are in the relation determined by the determination unit, a combination of feature points in which local feature amounts are similar to each other, and to calculate a similarity degree between the first input image and the second input image based on the combination.

7. The image processing apparatus according to claim 6,

wherein a feature point of the second image group having a local feature amount similar to each of the feature points of the first image group is regarded as a corresponding feature point based on a degree of similarity of a local feature amount of each feature point, and

wherein a ratio or a difference between a reduction rate of the first image and a reduction rate of the second image in which the corresponding feature point frequently appears is determined as a relation in a case where the size of the object of the first image and that of the second image get closer.

8. An image processing method performed using a computer or a processor, the method comprising:

reducing an input image by a predetermined number of times to generate an image group containing the input image;

extracting a plurality of feature points and a local feature amount of each feature point from the image group;

comparing a first image of a first image group generated from a first input image with a second image of a second image group generated from a second input image;

determining a relation between the first image and the second image in which a size of an object of the first image and that of the second image get closer; and

assigning high weights to a combination of feature points extracted from images having the determined relation to calculate a similarity degree between the first input image and the second input image.

9. A non-transitory computer-readable storage medium storing a program causing a computer to execute a method, the method comprising:

reducing an input image by a predetermined number of times to generate an image group containing the input image;

extracting a plurality of feature points and a local feature amount of each feature point from the image group;

comparing a first image of a first image group generated from a first input image with a second image of a second image group generated from a second input image;

determining a relation between the first image and the second image in which a size of an object of the first image and that of the second image get closer; and

assigning high weights to a combination of feature points extracted from images having the determined relation to calculate a similarity degree between the first input image and the second input image.

10. An image processing method performed using a computer or a processor, the method comprising:

reducing an input image by a predetermined number of times to generate an image group containing the input image;

extracting a plurality of feature points and a local feature amount of each feature point from the image group;

comparing a first image of a first image group generated from a first input image with a second image of a second image group generated from a second input image, and determining a relation between the first image and the second image in which a size of an object of the first image and that of the second image get closer; and

determining, as to the first image and the second image which are in the determined relation, a combination of feature points in which local feature amounts are similar to each other, and calculating a similarity degree between the first input image and the second input image based on the combination.

11. A non-transitory computer-readable storage medium encoded with computer-executable instructions for executing a method comprising:

reducing an input image by a predetermined number of times to generate an image group containing the input image;

extracting a plurality of feature points and a local feature amount of each feature point from the image group;

comparing a first image of a first image group generated from a first input image with a second image of a second image group generated from a second input image, and determining a relation between the first image and the second image in which a size of an object of the first image and that of the second image get closer; and

determining, as to the first image and the second image which are in the determined relation, a combination of feature points in which local feature amounts are similar to each other, and calculating a similarity degree between the first input image and the second input image based on the combination.