Biometric recognition system

1. A biometric recognition system for a hand held computing device incorporating an inertial measurement unit (IMU) comprising a plurality of accelerometers and at least one gyroscope, said system comprising a tremor analysis component arranged to:

obtain from said IMU accelerometer signals indicating device translational acceleration along each of X, Y and Z axes as well as a gyroscope signal indicating rotational velocity about the Y axis during a measurement window;

filter each of said IMU signals to provide filtered frequency components for said signals during said measurement window;

provide a spectral density estimation for each of said filtered accelerometer magnitude signal and said filtered gyroscope signal;

determine an irregularity for each spectral density estimation, each spectral density estimation comprising a periodogram, wherein said irregularity comprises;

and irregularity (IJ P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows;

IJ

p

=

∑

i

=

1

N

-

1

⁢

(

p

m

⁡

(

i

)

-

p

m

⁡

(

i

+

1

)

)

2

∑

i

=

1

N

-

1

⁢

(

p

m

⁡

(

i

)

)

2

,

 and

an irregularity (IK P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows;

IK

p

=

∑

i

=

1

N

-

1

⁢



p

m

⁡

(

i

)

-

p

m

⁡

(

i

-

1

)

+

p

m

⁡

(

i

)

+

p

m

⁡

(

i

+

1

)

3



where p m holds the magnitude coefficient of each periodogram, and N is the number of elements in p m ; and

based on said determined irregularities, authenticating a user of said handheld computing device further comprising a first authentication component requiring a higher level of authentication than provided by said tremor analysis component, said system being responsive to said first authentication component authenticating a given user to place said handheld computing device in first authentication state and said tremor analysis component, being responsive to said handheld computing device entering said first authentication state to periodically verify said user to maintain said handheld computing device in a second authentication state, said second authentication state providing greater access to said handheld computing device than said first authentication state.

2. The system as claimed in claim 1 further comprising a first authentication component requiring a higher level of authentication than provided by said tremor analysis component, said system being responsive to said first authentication component and said tremor analysis component authenticating a given user to place said device in an authenticated state providing user access to said device.

3. The system as claimed in claim 1 wherein each spectral density estimation extends across a range from 4Hz to 15Hz.

4. The system as claimed in claim 1 wherein said tremor analysis component is arranged to provide an accelerometer X axis periodogram and to calculate an irregularity (IK P ) for said accelerometer X axis periodogram as follows:

IK

p

=

∑

i

=

1

N

-

1

⁢



p

m

⁡

(

i

)

-

p

m

⁡

(

i

-

1

)

+

p

m

⁡

(

i

)

+

p

m

⁡

(

i

+

1

)

3



where p m holds the magnitude coefficient of said accelerometer X axis periodogram, and N is the number of elements in p m .

5. The system according to claim 1 wherein said filter comprises a Fourier linear (FLC) combiner for adaptively estimating the Fourier coefficients of said IMU signals.

6. The system according to claim 5 wherein said filter comprises one of: a weighted Fourier Linear Combiner (WFLC) or a Bandlimited FLC for adaptively estimating a quasi-periodic signal.

7. The system according to claim 1 wherein said matching module comprises a random forest classifier.

8. The system according to claim 7 wherein said classifier comprises no more than 130 trees.

9. The system according to claim 1 wherein said matching module comprises a bagged ensemble of trees classifier.

10. The system according to claim 1 wherein said measurement window is 1 second.

11. The system according to claim 1 wherein a sampling frequency of said IMU signals is at least 100Hz.

12. The system according to claim 1 wherein said tremor analysis component is operable in a normal mode for authenticating a user; and a training mode for obtaining signals indicative of said user's tremor.

13. A device incorporating an inertial measurement unit (IMU) comprising a plurality of accelerometers and at least one gyroscope and a biometric recognition system comprising a tremor analysis component arranged to;

obtain from said IMU accelerometer signals indicating device translational acceleration along each of X, Y and Z axes as well as gyroscope signal indicating rotational velocity about the Y axis during a measurement window;

filter each of said IMU signals to provide filtered frequency components for said signals during said measurement window;

provide a special density estimation for each of said filtered accelerometer magnitude signal and said filtered gyroscope signal;

determine an irregularity for each spectral density estimation, each spectral density estimation comprising a periodogram, wherein said irregularity comprises;

an irregularity (IJ P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IJ

p

=

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

-

p

m

⁡

(

i

+

1

)

)

2

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

)

2

,

 and

and irregularity (IK P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IK

p

=

∑

i

=

1

N

-

1

⁢

⁢



p

m

⁡

(

i

)

-

p

m

⁡

(

i

-

1

)

+

p

m

⁡

(

i

)

+

p

m

⁡

(

i

+

1

)

3



where p m holds the magnitude coefficient of each periodogram, and N is the number of elements in p m ; and

based on said determined irregularities, authenticating a user of said device further comprising a first authentication component requiring a higher level of authentication than provided by said tremor analysis component, said device being responsive to said first authentication component authenticating a given user to place said device in first authentication state and said tremor analysis component, being responsive to said device entering said first authentication state to periodically verify said user to maintain said device in a second authentication state, said second authentication state providing greater access to said device than said first authentication state.

14. A computer program product stored on a non-transitory computer readable medium which when executed on a handheld computing device incorporating an inertial measurement unit (IMU) comprising a plurality of accelerometers and at least one gyroscope is arranged to perform the steps of:

obtaining from the IMU, accelerometer signals indicating device translational acceleration along each of X, Y and Z axes as well as a gyroscope signal indicating rotational velocity about the Y axis during a measurement window;

filtering each of said IMU signals to provide filtered frequency components for said signals during said measurement window; providing a spectral density estimation for each of said filtered accelerometer magnitude signal and said filtered gyroscope signal;

determining an irregularity for each spectral density estimation, each spectral density estimation comprising a periodogram, wherein said irregularity comprises:

an irregularity (IJ P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IJ

p

=

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

-

p

m

⁡

(

i

+

1

)

)

2

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

)

2

,

 and

an irregularity (IK P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IK

p

=

∑

i

=

1

N

-

1

⁢

⁢



p

m

⁡

(

i

)

-

p

m

⁡

(

i

-

1

)

+

p

m

⁡

(

i

)

+

p

m

⁡

(

i

+

1

)

3



where p m holds the magnitude coefficient of each periodogram, and N is the number of elements in p m ; and

based on said determined irregularities, authenticating a user of said handheld computing device further comprising a first authentication component requiring a higher level of authentication than provided by said tremor analysis component, said handheld computing device being responsive to said first authentication component authenticating a given user to place said handheld computing device in first authentication state and said tremor analysis component, being responsive to said handheld computing device entering said first authentication state to periodically verify said user to maintain said handheld computing device in a second authentication state, said second authentication state providing greater access to said handheld computing device than said first authentication state.

15. A biometric recognition system for a hand held computing device incorporating an inertial measurement unit (IMU) comprising a plurality of accelerometers and at least one gyroscope, said system comprising a first authentication component requiring a higher level of authentication than provided by a tremor analysis component, said system being responsive to said first authentication component authenticating a given user to place said device in first authentication state; and

said tremor analysis component, being responsive to said device entering said first authentication state to periodically verify said user to maintain said device in a second authentication state, said second authentication state providing greater access to said device than said first authentication state, the tremor analysis component being arranged to:

obtain from said IMU accelerometer signals indicating device translational acceleration along each of X, Y and Z axes as well as a gyroscope signal indicating rotational velocity about the Y axis during a measurement window;

filter each of said IMU signals to provide filtered frequency components for said signals during said measurement window;

provide a spectral density estimation for each of said filtered accelerometer magnitude signal and said filtered gyroscope signal; and

based on features extracted from said spectral density estimates, attempt to verify said user of said device,

wherein each spectral density estimation comprising a periodogram, and wherein said features comprise irregularities comprising:

an irregularity (IJ P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IJ

p

=

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

-

p

m

⁡

(

i

+

1

)

)

2

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

)

2

,

 and

an irregularity (IK P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IK

p

=

∑

i

=

1

N

-

1

⁢

⁢



p

m

⁡

(

i

)

-

p

m

⁡

(

i

-

1

)

+

p

m

⁡

(

i

)

+

p

m

⁡

(

i

+

1

)

3



where p m holds the magnitude coefficient of each periodogram, and N is the number of elements in p m .

16. A device incorporating an inertial measurement unit (IMU) comprising a plurality of accelerometers and at least one gyroscope, and a biometric recognition system comprising a first authentication component requiring a higher level of authentication than provided by a tremor analysis component, said biometric recognition system being responsive to said first authentication component authenticating a given user to place said device in first authentication state; and

said tremor analysis component, being responsive to said device entering said first authentication state to periodically verify said user to maintain said device in a second authentication state, said second authentication state providing greater access to said device than said first authentication state, the tremor analysis component being arranged to;

obtain from said IMU accelerometer signals indicating device translational acceleration along each of X, Y and Z axes as well as gyroscope signal indicating rotational velocity about the Y axis during a measurement window;

filter each of said IMU signals to provide filtered frequency components for said signals during said measurement window;

provide a spectral density estimation for each of said filtered accelerometer magnitude signal and said filtered gyroscope signal; and

based on features extracted from said spectral density estimates, attempt to verify said user of said device,

wherein each spectral density estimation comprising a periodogram, and wherein said features comprise irregularities comprising;

and irregularity (IJ P ) for said accelerometer magnitude and said gyroscope periodograms calculated as follows;

IJ

p

=

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

-

p

m

⁡

(

i

+

1

)

)

2

-

∑

i

=

1

N

-

1

⁢

⁢

(

p

m

⁡

(

i

)

)

2

,

 and

an irregularity (IK P )for said accelerometer magnitude and said gyroscope periodograms calculated as follows:

IK

p

=

∑

i

=

1

N

-

1

⁢

⁢



p

m

⁡

(

i

)

-

p

m

⁡

(

i

-

1

)

+

p

m

⁡

(

i

)

+

p

m

⁡

(

i

+

1

)

3



where p m holds the magnitude coefficient of each periodogram, and N is the number of elements in p m .