Apparatus and method for collating image

• US 6,707,934 B1
• Filed: 12/22/1999
• Issued: 03/16/2004
• Est. Priority Date: 12/28/1998
• Status: Expired due to Fees

• Current Assignee: Casio Computer Company Limited
• Original Assignee: Casio Computer Company Limited
• Inventors: Satoh, Katsuhiko, Takeda, Tsuneharu
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): GORADIA, SHEFALI DINESH
• Application Number:
  US09/468,633
• Time in Patent Office: 1,546 Days
• Field of Search: 382/124, 382/125, 382/135, 382/205, 382/126, 382/127, 283/68, 283/69, 283/70, 356/71
• US Class Current: 382/124
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

An image collation apparatus has stored therein first image (registered fingerprint) beforehand. Regarding second image (fingerprint to be collated) that is input when collation is performed, the apparatus thereby determines the identicalness between this second image and the first image. At this time, the apparatus defines with respect to the first image a plurality of regions each having a predetermined positional relationship with respect thereto. The apparatus searches from the second image an image region having a maximum correlation with the image of each of the respective defined regions. The identicalness between the first image and the second image is determined according to the difference between the positional relationship of each of the respective image regions defined on the first image and the positional relationship of the maximum correlation region that comprises been searched out on the second image.

Claims

1. An image collating method for determining identity between a first image and a second image with each other, the method comprising:

defining a rectangular reference region in the first image as a template;

searching for a maximum correlation region in the second image that has a maximum correlation with the rectangular reference region;

defining rectangular sub-regions located at four corners of the rectangular reference region as sub-templates;

searching for maximum correlation sub-regions in the second image that have maximum correlations with the rectangular sub-regions in the first image; and

determining identity between the first and second images based on a difference between a positional relationship between the rectangular sub-regions in the first image and a positional relationship between the maximum correlation sub-regions in the second image.

2. The image collating method according to claim 1, wherein the rectangular sub-regions in the first image and the rectangular reference region contact at corners.

3. The image collating method according to claim 1, wherein the rectangular sub-regions in the first image and the rectangular reference region overlap.

4. The image collating method according to claim 1, wherein the rectangular sub-regions in the first image and the rectangular reference region are spaced from each other.

5. The image collating method according to claim 1, further comprising:

detecting whether the maximum correlation regions searched by the maximum correlation region searching are in a predetermined relationship to the second image; and

re-defining at least one of the rectangular sub-regions when it is detected that at least one of the maximum correlation regions is in the predetermined relationship to the second image.

6. The image collating method according to claim 5, wherein:

the detecting includes detecting whether any of the maximum correlation regions are displaced from the second image by an amount that is larger than a predetermined amount; and

the re-defining includes moving at least one of the rectangular sub-regions in accordance with a detected displacement amount.

7. The image collating method according to claim 1, wherein the first image is a reference fingerprint image which is registered, and the second image is a fingerprint image which is to be collated with the reference fingerprint image.

8. The image collating method according to claim 1, wherein the maximum correlation region searching comprises:

setting, in the second image, a corresponding region of the rectangular reference region; and

calculating a correlation between the rectangular reference region and the corresponding region while moving the corresponding region.

9. An image collating apparatus for determining identity between a first image and a second image with each other, the apparatus comprising:

a reference region defining section configured to define a rectangular reference region in the first image as a template;

a maximum correlation region search section configured to search for a maximum correlation region in the second image that has a maximum correlation with the rectangular reference region;

a sub-region defining section configured to define rectangular sub-regions located at four corners of the rectangular reference region as sub-templates;

a maximum correlation sub-region search section configured to search for maximum correlation sub-regions in the second image that have maximum correlations with the rectangular sub-regions in the first image; and

a determining section configured to determine identity between the first and second images based on a difference between a positional relationship between the rectangular sub-regions in the first image and a positional relationship between the maximum correlation sub-regions in the second image.

10. The image collating apparatus according to claim 9, further comprising:

a detector configured to detect whether the maximum correlation regions searched by the maximum correlation region search section are in a predetermined relationship to the second image; and

a re-defining section configured to re-define at least one of the rectangular sub-regions that have been defined by the sub-region defining section when the detector detects that at least one of the maximum correlation regions is in the predetermined relationship to the second image.

11. The image collating apparatus according to claim 10, wherein:

the detector includes a section configured to detect the maximum correlation regions are displaced from the second image by an amount that is larger than a predetermined amount; and

the re-defining section includes a section configured to move at least one of the rectangular sub-regions in accordance with a detected displacement amount.

12. The image collating apparatus according to claim 9, wherein the first image is a reference fingerprint image which is registered, and the second image is a fingerprint image which is to be collated with the reference fingerprint image.

13. The image collating apparatus according to claim 9, wherein the maximum correlation region search section comprises:

a section configured to set, in the second image, a corresponding region of the rectangular reference region; and

a section configured to calculate a correlation between the rectangular reference region and the corresponding region while moving the corresponding region.

14. An article of manufacture comprising a computer usable medium having an image collating program for determining identity between a first image and a second image with each other, the program comprising:

computer readable program code means for causing a computer to search for a maximum correlation region in the second image that has a maximum correlation with a rectangular reference region defined in the first image as a template;

computer readable program code means for causing a computer to define rectangular sub-regions located at four corners of the rectangular reference region as sub-templates;

computer readable program code means for causing a computer to search for maximum correlation sub-regions in the second image that have maximum correlations with the rectangular sub-regions in the first image; and

computer readable program code means for causing a computer to determine identity between the first and second images based on a difference between a positional relationship between the rectangular sub-regions in the first image and a positional relationship between the maximum correlation sub-regions in the second image.

15. The article of manufacture according to claim 14, wherein the program further comprises:

computer readable program code means for causing a computer to detect whether the searched maximum correlation regions are in

a predetermined relationship to the second image; and

computer readable program code means for causing a computer to re-define at least one of the rectangular sub-regions when it is detected that at least one of the maximum correlation regions is in the predetermined relationship to the second image.

16. The article of manufacture according to claim 15, wherein:

the computer readable program code means for causing a computer to detect includes computer readable program code means for causing a computer to detect whether any of the maximum correlation are displaced from the second image by an amount that is larger than a predetermined amount; and

the computer readable program code means for causing a computer to re-define includes computer readable program code means for causing a computer to move at least one of the rectangular sub-regions in accordance with a detected displacement amount.

17. The article of manufacture according to claim 14, wherein the first image is a reference fingerprint image which is registered, and the second image is a fingerprint image which is to be collated with the reference fingerprint image.

18. The article of manufacture according to claim 14, wherein the computer readable program code means for causing a computer to search for a maximum correlation region comprises:

a computer readable program code means for causing a computer to set, in the second image, a corresponding region of the rectangular reference region; and

computer readable program code means for causing a computer to calculate a correlation between the rectangular reference region and the corresponding region while moving the corresponding region.