System and method for determining block direction in fingerprint images

• US 6,289,112 B1
• Filed: 02/25/1998
• Issued: 09/11/2001
• Est. Priority Date: 08/22/1997
• Status: Expired due to Term

• Current Assignee: Uniloc 2017 LLC (SoftBank Group Corp.)
• Original Assignee: International Business Machines Corporation
• Inventors: Pankanti, Sharathchandra Umapathirao, Bolle, Rudolf Maarten, Hong, Lin, Jain, Anil K.
• Primary Examiner(s): Bella, Matthew C.
• Assistant Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US09/030,438
• Time in Patent Office: 1,294 Days
• Field of Search: 382/116, 382/124, 382/125, 382/126, 382/289, 382/274, 382/266, 382/263, 382/272, 382/296, 283/68, 283/69, 283/78, 356/71, 340/825.34, 396/15
• US Class Current: 382/116
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

A reliable estimate of image pixel (fingerprint ridge) orientations, and block orientations for a given block is determined by finding an optimal block size in an area of an image, e.g., a fingerprint image. An initial block size is chosen. Then a block direction is determined, e.g., by analyzing intensity gradients in two directions, preferably two orthogonal directions, at a plurality (preferably all) of the pixels locations in the block. Block directions of blocks in a given area of the images (fingerprint) are compared. If the compared directions are within a tolerance of one another, the determined direction of the block is considered correct. However, if the compared directions are not within a tolerance of one another, the block size is changed and the process is repeated.

Claims

1. A system for determining orientations of one or more blocks of pixels in an image displayed by a computer system, comprising:

a computer with a memory, a central processing unit, and a database of one or more images, the images having a plurality of pixels, the image partitioned into one or more blocks having a plurality of pixels, each of the blocks having a size;

a block direction process, executed by the central processing unit, that determines a line orientation of one or more lines within one or more of the blocks, the block direction process further determining a block orientation of the block based on the line orientations within the block; and

a segmentation process, executed by the central processing unit, that determines an overall gradient magnitude for the each of the blocks and an overall projected gradient magnitude for each of the blocks, the overall gradient magnitude being a measure of accepting the estimated block orientation if a consistency metric is within a consistency threshold.

2. A system, as in claim 1, where the line orientations are determined by gradients of brightness.

3. A system, as in claim 1, where the images are fingerprint images and the line orientations are orientations of ridges in the fingerprint images.

4. A system, as in claim 1, where the consistency metric is the root mean square of each of the differences between the orientation of the current block and the orientation of one or more of the neighboring blocks.

15. The system of claim 1, wherein the estimated block orientation is accepted if the consistency metric is below a consistency threshold.

5. A system for determining orientations of one or more blocks of pixels in an image displayed by a computer system, comprising:

a computer with a memory, a central processing unit, and a database of one or more images, the images having a plurality of pixels, the image partitioned into one or more blocks of one or more of the pixels, each of the blocks having a size;

a block direction process, executed by the central processing unit, that determines a line orientation of one or more lines within one or more of the blocks, the block direction process further determining a block orientation of the block based on the line orientations within the block; and

an orientation process, executed by the central processing unit, that determines a current block and one or more neighboring blocks that neighbor the current block, the orientation process comparing an estimated block orientation of the current block to the block orientation of one or more of the neighboring blocks using a consistency metric, the orientation process accepting the estimated block orientation if the consistency metric is within a consistency threshold, the orientation process rejecting the estimated block orientation if the consistency metric is not within the consistency threshold.

6. A system, as in claim 5, where the rejected estimated block orientation is used.

7. A system, as in claim 5, where the pixels within the block with the rejected estimated block orientation are considered background pixels in the image.

8. A system, as in claim 5, where the orientation process increases the block size and re-executes the block direction process and the orientation process if the estimated block orientation is rejected.

9. A system, as in claim 8, where the orientation process stops increasing the block size if the block is larger than a maximum block size.

10. A system, as in claim 8, where the block size is increased by a factor of n² in area.

11. A system, as in claim 10, where n is an integer.

16. The system of claim 5, wherein the estimated block orientation is accepted if the consistency metric is below a consistency threshold.

12. A method for determining orientations a plurality of pixels in an image displayed by a computer system, each of the blocks having a size, the method comprising the steps of:

determining a block orientation of one or more of the blocks based on a line orientation of one or more lines within the block;

determining a current block and one or more neighboring blocks that neighbor the current block;

comparing an estimated block orientation of the current block to block orientation of one or more of the neighboring blocks using a consistency metric; and

accepting the estimated block orientation if the consistency metric is within a consistency threshold.

13. A method, as in claim 12, comprising the further step of:

rejecting the estimated block orientation if the consistency metric is not within the consistency threshold.

17. The method of claim 12, wherein the estimated block orientation is accepted if the consistency metric is below a consistency threshold.

14. A system for determining orientations of a plurality of pixels in an image displayed by a computer system, each of the blocks having a size, comprising:

means for determining a block orientation of one or more of the blocks based on a line orientation of one or more lines within the block;

means for determining a current block and one or more neighboring blocks that neighbor the current block;

means for comparing an estimated block orientation of the current block to the block orientation of one or more of the neighboring blocks using a consistency metric; and

means for accepting the estimated block orientation if the consistency metric is within a consistency threshold.

18. The system of claim 14, wherein the estimated block orientation is accepted if the consistency metric is below a consistency threshold.