System and methods for transforming biometric image data to a consistent angle of inclination

• US 20050276454A1
• Filed: 06/14/2005
• Published: 12/15/2005
• Est. Priority Date: 06/14/2004
• Status: Abandoned Application

• Current Assignee: Mark A. Kelty, Rodney Beatson
• Original Assignee: Mark A. Kelty, Rodney Beatson
• Inventors: Beatson, Rodney, Kelty, Mark A.
• Application Number:
  US11/151,412
• Publication Number:
  US 20050276454A1
• Time in Patent Office: Days
• US Class Current: 382/119
• CPC Class Codes: G06V 30/1478 of characters or characters lines
• CPC Class Codes: G06V 40/30 Writer recognition; Reading and verifying signatures

Abstract

Biometric data are obtained through a biometric input device (120) and subsequently pixelated via a pixelator (130). The pixelator (130) creates an image of the biometric data. Via a processing unit (110), a relationship between pixels of a transformed version of the image is asserted. Thus, the biometric data is rotated to a consistent inclination based on the relationship between pixels regardless of an orientation in which the biometric data were captured in the original image. Once the image has been transformed, features of the biometric data may be extracted and either stored in a data storage unit (140) or compared with previously stored feature values for validation of the biometric data.

Claims

1. A method for spatially transforming biometric data for invariant feature extraction comprising the steps of:

selecting a statistical relationship between pixels of a transformed biometric data image;

pixelating the biometric data to form a biometric image thereof, said image including a plurality of pixels at a corresponding plurality of pixel coordinates, said biometric data oriented in said image at a submission angle with respect to a predetermined axis of said image; and

applying a transform to said biometric image to form said transformed biometric image, said biometric data being thereby rotated to an angle of inclination corresponding to said statistical relationship regardless of said submission angle.

2. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 1, where said statistical relationship selecting step includes the step of selecting as said statistical relationship that a variance of pixel values in a first direction of said transformed biometric image is a scalar multiple of a variance of pixel values in a second direction of said transformed biometric image.

3. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 2, where said statistical relationship selecting step includes the step of establishing that said second direction is perpendicular to said first direction.

4. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 1, where said statistical relationship selecting step includes the step of selecting as said statistical relationship that a covariance of pixel values at each of said pixel coordinates of said transformed biometric image is a constant value.

5. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 4, where said statistical relationship selecting step includes the step of establishing that said constant value is zero.

6. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 1 further including the steps of:

fitting a line to said pixelated biometric data of said transformed biometric image; and

rotating said transformed biometric image so that said fitted line is oriented in said image at a predetermined angle with respect to a predetermined axis of said transformed biometric image.

7. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 6 where said line fitting step includes the step of fitting said line using a regression procedure.

8. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 7 where said line fitting step includes the step of establishing a least square estimation as said regression procedure.

9. The method for spatially transforming biometric data for invariant feature extraction as recited in claim 1, where said pixelating step includes the step of providing a handwriting sample as the biometric data.

10. A method for verifying the validity of biometric data by invariant feature extraction, the method comprising the steps of:

selecting a statistical relationship between pixels of a transformed biometric data image;

providing an input device for obtaining biometric data from a user;

providing a storage unit for storing features of said biometric data;

receiving a first sample of said biometric data from said user;

pixelating said first sample to form a first sample image, said first sample image including a plurality of pixels at a corresponding plurality of pixel coordinates, said first sample being oriented in said first sample image at a first submission angle with respect to a predetermined axis of said first sample image;

applying a transform to said first sample image to produce a first transformed biometric data image, said first sample being oriented in said first transformed biometric data image at an angle of inclination corresponding to said statistical relationship;

extracting biometric features from said first transformed biometric image and storing said features in said storage unit;

receiving a second sample of said biometric data from said user;

pixelating said second sample to form a second sample image, said second sample image including a plurality of pixels at a corresponding plurality of pixel coordinates, said second sample being oriented in said second sample image at a second submission angle with respect to a predetermined axis of said second sample image;

applying said transform to said second sample image to produce a second transformed biometric data image, said second sample being oriented in said second transformed biometric data image at said angle of inclination;

extracting said biometric features from said second transformed biometric data image; and

comparing said biometric features of said second transformed biometric data image to corresponding ones of said features stored in said storage unit.

11. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 10, where said statistical relationship selecting step includes the step of selecting as said statistical relationship that a variance of pixel values in a first direction of said biometric image is a scalar multiple of a variance of pixel values in a second direction of said biometric image.

12. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 11, where said statistical relationship selecting step includes the step of establishing that said second direction is perpendicular to said first direction.

13. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 10, where said statistical relationship selecting step includes the step of selecting as said statistical relationship that a covariance of pixel values at each of said pixel coordinates of said biometric image is a constant value.

14. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 13, where said statistical relationship selecting step includes the step of establishing that said constant value is zero.

15. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 10 further including the steps of:

fitting a line to each of said pixelated first biometric sample and said pixelated second biometric sample of respectively said first transformed biometric data image and second transformed biometric data image;

rotating said first transformed biometric data image so that said respective fitted line is oriented in said first transformed biometric data image at an angle with respect to a predetermined axis of thereof prior to said first transformed biometric data image feature extraction step; and

rotating said second transformed biometric data image so that said respective fitted line is oriented in said second transformed biometric data image at an angle with respect to a predetermined axis of thereof prior to said second transformed biometric data image feature extraction step.

16. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 15 where said line fitting step includes the step of fitting each said respective line using a regression procedure.

17. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 16 where said line fitting step includes the step of establishing a least square estimation as said regression procedure.

18. The method for verifying the validity of biometric data by invariant feature extraction as recited in claim 10, where said first sample pixelating step and said second sample pixelating step each includes the step of providing a handwriting sample as said first sample and said second sample, respectively.

19. A system for spatially transforming biometric data for invariant feature extraction, the system comprising:

an input device operable to obtain biometric data from a user;

a pixelator operable to pixelate said biometric data into an image thereof, said image including a plurality of pixels at a corresponding plurality of pixel coordinates, said biometric data oriented in said image at a submission angle with respect to a predetermined axis of said image;

a storage unit operable to store sequences of program instructions that, when executed by a processing unit, cause said processor to execute a transformation process for transforming said image into a transformed image such that said biometric data are rotated to an angle of inclination in said transformed image corresponding to a predetermined statistical relationship between pixels thereof regardless of said submission angle; and

a processing unit coupled to said input device and said storage unit, said processing unit operable to execute said transformation process.

20. The system for spatially transforming biometric data for invariant feature extraction as recited in claim 19, wherein said storage unit further includes sequences of program instructions that, when executed by a processing unit, cause said processor to execute:

a line fitting process for fitting a line to said pixelated biometric data of said transformed biometric image; and

an image rotation process for rotating said transformed biometric image so that said fitted line is oriented in said image at an angle with respect to a predetermined axis of said rotated transformed biometric image.