Methods and apparatus for power-efficient iris recognition

• US 10,032,075 B2
• Filed: 12/23/2014
• Issued: 07/24/2018
• Est. Priority Date: 12/23/2013
• Status: Active Grant

• Current Assignee: EyeLock LLC (VOXX International Corporation)
• Original Assignee: EyeLock LLC (VOXX International Corporation)
• Inventors: Hanna, Keith J.
• Primary Examiner(s): Harandi, Siamak
• Application Number:
  US15/107,390
• Publication Number:
  US 20160342836A1
• Time in Patent Office: 1,309 Days
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06V 10/141 Control of illumination
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G06V 40/197 Matching; Classification
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 23/56 provided with illuminating means
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/651 for reducing power consumption by affecting camera operations, e.g. sleep mode, hibernation mode or power off of selective parts of the camera
• CPC Class Codes: H04N 23/90 Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

Abstract

Disclosed herein are systems and methods wherein the iris biometric of an individual person is acquired using a mobile or static device. This acquisition may involve the use of active illumination and repeated use of the camera and processor, as examples. These modules consume considerable power however, and this can significantly reduce battery life. There is a need therefore for a power-efficient iris recognition system.

Claims

1. A system for power-efficient iris recognition, the system comprising:

a sensor to acquire at least one image of an iris of a user; and

circuitry configured to implement;

an iris recognition engine, operably coupled to the sensor, to perform iris recognition of the user based on the at least one image of the iris of the user;

a sensor power controller, operably coupled to the sensor, to provide electrical power to the sensor; and

an iris acquisition mode detector, operably coupled to the sensor and to the sensor power controller, to determine an operational mode of the system using an output from the sensor, and to adjust a time period between successive sensing enablements of the sensor according to the operational mode so as to control the electrical power provided to the sensor,

wherein the operational mode of the system is at least one of iris recognition is not possible, iris recognition is possible but not preferred, or iris recognition is possible and preferred.

2. The system of claim 1 wherein the iris acquisition mode detector is configured to set the time period between successive sensing enablements of the sensor to be less than 20 seconds in response to a determination that the operational mode is that no iris recognition is possible.

3. The system of claim 1 wherein the iris acquisition mode detector is configured to set the time period between successive sensing enablements of the sensor to be less than 5.5 seconds in response to a determination that the operational mode is that iris recognition is possible but preferred or that iris recognition is possible and preferred.

4. The system of claim 1 wherein the iris acquisition mode detector is configured to determine the operational mode according to at least one of:

a determination that one or both eyes of the user are detected to be within a region illuminated by a light source used for iris recognition;

determination that the user is detected to be within a depth afield of the sensor;

a determination that the user is moving at a speed less than a speed threshold;

a determination that the brightness level of the at least one image is less than a brightness threshold;

a determination that a change between a first image and a second image acquired by the sensor is below a change threshold;

or

a determination that an acceleration of the sensor is below an acceleration threshold.

5. The system of claim 4 wherein the speed threshold is 13.75 cm/second.

6. The system of claim 1 wherein the sensor is configured to move an active sensor region of interest of the sensor over time so as to image a region larger than the active sensor region of interest.

7. The system of claim 1 wherein the sensor is configured to be in a first sensor configuration for iris acquisition mode determination and to be in a second sensor configuration for iris recognition.

8. The system of claim 1, further comprising:

an alignment engine, operably coupled to the sensor, to determine at least one common feature between at least two images of an eye of the user acquired over time and to align the at least two images to the at least one common feature; and

a motion detector, operably coupled to the sensor, to estimate motion of at least one other features of the eye.

9. A system for a power efficient iris recognition, the system comprising:

at least one sensor to acquire at least one image of an iris of a user, the at least one sensor having a spatial area of coverage; and

circuitry configured to implement;

an iris recognition engine, operably coupled to the at least one sensor, to perform iris recognition of the user using the at least one image of the iris of the user;

an iris acquisition mode detector, operably coupled to the at least one sensor and to the iris recognition engine, to determine an operational mode of the system using an output from the at least one sensor; and

a sensor region of interest controller, operably coupled to the at least one sensor, to adjust a proportion of the spatial are of coverage, within which the at least one sensor'"'"'s sensor pixels are active, according to the operational mode,

wherein the operational mode of the system is at least one of iris recognition is not possible, iris recognition is possible but not preferred, or iris recognition is possible and preferred.

10. The system of claim 9 wherein the iris acquisition mode detector is configured to determine the operational mode according to at least one of:

determination that one or both eyes of the user are detected to be within a region illuminated by a light source used for iris recognition;

a determination that the user is detected to be within a depth of field of the at least one sensor;

a determination that the user is moving at a speed less than a speed threshold;

a determination that the brightness level of the at least one image is less than a brightness threshold;

a determination that a change between a first image and a second image acquired by the at least one sensor is below a change threshold;

or

a determination that an acceleration of the at least one sensor is below an acceleration threshold.

11. The system of claim 10 wherein the speed threshold is 13.75 cm/second.

12. The system of claim 9 wherein the sensor region of interest controller is configured to adjust the proportion of the spatial area of coverage, within which the at least one sensor'"'"'s sensor pixels are active, to be less than a region of interest of the at least one sensor in response to a determination that the operational mode is that no iris recognition is possible.

13. The system of claim 9 wherein the sensor region of interest controller is configured to adjust the proportion of the spatial area of coverage, within which the at least one sensor'"'"'s sensor pixels are active, such that the ratio of an active vertical window of the at least one sensor to a diameter of the iris is equal to or greater than 3.12.

14. The system of claim 9 further comprising:

an illumination region of interest controller configured to illuminate a first region of the image with a first illumination power and a second region of the image with a second illumination power so as to produce a resultant bright and dark banded image.

15. The system of claim 14 wherein the iris recognition engine is configured to process the bright and dark banded image by normalizing the intensities in the image corresponding to the first illumination power and the image corresponding to the second illumination power.

16. The system of claim 9 wherein the at least one sensor is configured to be in a first sensor configuration for iris acquisition mode determination and to be in a second sensor configuration for iris recognition.

17. The system of claim 9, further comprising:

an alignment engine, operably coupled to the at least one sensor, to determine at least one common feature between at least two images of an eye of the user acquired over time and to align the at least two images to the at least one common feature; and

a motion detector, operably coupled to the at least one sensor, to estimate motion of at least one other features of the eye.

18. A method for a power efficient iris recognition, the method comprising:

acquiring, by at least one sensor, at least one image of an iris of a user, the at least one sensor having a spatial area of coverage;

determining, by an iris acquisition mode detector operably coupled to the sensor and to the iris recognition engine, an operational mode of the at least one sensor using an output from the at least one sensor; and

adjusting, by a sensor region of interest controller operably coupled to the sensor, a proportion of the spatial area of coverage, within which the at least one sensor'"'"'s sensor pixels are active, according to the determined operational mode,

wherein the operational mode of the at least one sensor is at least one of iris recognition is not possible, iris recognition is possible but not preferred, or iris recognition is possible and preferred.

19. The method of claim 18, comprising adjusting, by the sensor region of interest controller, the proportion of the spatial area of coverage, within which the at least one sensor'"'"'s sensor pixels are active, to be less than a region of interest of the sensor in response to a determination that the operational mode is that no iris recognition is possible.

20. The method of claim 18, comprising adjusting, by the sensor region of interest controller, the proportion of the spatial area of coverage, within which the at least one sensor'"'"'s sensor pixels are active, such that the ratio of an active vertical window of the at least one sensor to a diameter of the iris is equal to or greater than 3.12.