Adaptive light source

1. A method, comprising:

capturing a first image of a scene;

detecting a face in a section of the scene from the first image;

creating a three dimensional profile of the face;

calculating an amount of infrared (IR) light to illuminate the section of the scene based on the first image and the three dimensional profile of the face;

activating an infrared (IR) light source to selectively illuminate the section of the scene with the amount of IR light, the IR light source comprising an array of IR light emitting diodes (LEDs);

capturing a second image of the scene under selective IR lighting from the IR light source;

detecting the face in the second image; and

identifying a person based on the face in the second image.

2. The method of claim 1 , prior to said capturing the first image of the scene, further comprising activating the IR light source to uniformly illuminate the scene with IR light by driving each of the IR LEDs in the array with a first individual current.

3. The method of claim 2 , wherein said activating the IR light source to selectively illuminate the section of the scene with IR light comprises selecting a group of IR LEDs in the array and driving each of the IR LEDs in the group with a second individual current that is greater than the first individual current.

4. The method of claim 3 , wherein a first total current comprising a sum of the first individual currents and a second total current comprising a sum of the second individual currents are equal.

5. The method of claim 1 , wherein said activating the IR light source to selectively illuminate the section of the scene with IR light comprises selecting a group of IR LEDs in the array and driving each of the IR LEDs in the group with a second individual current less than the first current, a first total current comprising a sum of the first individual currents being greater than a second total current comprising a sum of the second individual currents.

6. The method of claim 1 , wherein said capturing the first image of the scene occurs under ambient lighting.

7. The method of claim 6 , prior to said activating the IR light source to selectively illuminate the section of the scene with IR light, further comprising:

activating the IR light source to uniformly illuminate the scene with IR light;

capturing an intermediate image of the scene under uniform IR lighting from the IR light source;

detecting the face in the intermediate image; and

calculating the amount of IR light to illuminate the section of the scene based on brightness values of the face in the first image and the intermediate image.

8. The method of claim 7 , wherein said calculating the amount of IR light to illuminate the section of the scene is based on a difference between corresponding brightness value of the face from the first image and the intermediate image.

9. A method, comprising:

capturing a first image of a scene;

detecting a face in a section of the scene from the first image;

creating a three dimensional profile of the face;

activating an infrared (IR) light source to uniformly illuminate the scene with uniform IR lighting, the IR light source comprising an array of IR light emitting diodes (LEDs);

capturing an intermediate image of the scene under the uniform IR lighting from the IR light source;

detecting the face in the intermediate image;

calculating an amount of IR light to illuminate the section of the scene based on brightness values of the face in the first and the intermediate images and the three dimensional profile of the face;

activating the IR light source to selectively illuminate the section of the scene with the amount of IR light;

capturing a second image of the scene under selective IR lighting from the IR light source;

detecting the face in the second image; and

identifying a person based on the face in the second image.

10. The method of claim 9 , wherein a first LED in the array emits IR light of a different emission spectrum than IR light emitted by a second LED in the array.

11. The method of claim 9 , wherein the array is a first array of IR LEDs, the IR light source further comprises a second array of IR LEDs, and the first array of IR LEDs and the second arrays of IR LEDs illuminate different portions of the face.

12. The method of claim 11 , wherein a first LED in the array emits IR light of a different emission spectrum than IR light emitted by a second LED in the array.

13. The method of claim 9 , wherein said identifying a person based on the face in the second image comprises comparing the face in the second image against facial images in a database and finding a match.

14. A system, comprising:

a camera having a field of view;

an infrared (IR) light source comprising an array of IR light emitting diodes (LEDs);

nonvolatile memory storing instructions for a face detection and recognition application; and

a microprocessor encoded with instructions that, when executed by the microprocessor, cause the system to:

capture, with the camera, a first image of a scene;

detect a face in a section of the scene from the first image;

create a three dimensional profile of the face;

calculate an amount of IR light to illuminate the section of the scene based on the first image and the three dimensional profile of the face;

activate the IR light source to selectively illuminate the section of the scene with the amount of IR light;

capture, with the camera, a second image of the scene under selective IR lighting from the IR light source;

detect the face in the second image; and

identify a person based on the face in the second image.

15. The system of claim 14 , wherein the instructions that, when executed by the microprocessor, cause the system to, prior to said capturing the first image of the scene, activate the IR light source to uniformly illuminate the scene with IR light by driving each of the IR LEDs in the array with a first individual current.

16. The system of claim 15 , wherein said activating the IR light source to selectively illuminate the section of the scene with IR light comprises selecting a group of IR LEDs in the array and driving each of the IR LEDs in the group with a second individual current that is greater than the first individual current.

17. The system of claim 16 , wherein a first total current comprising a sum of the first individual currents and a second total current comprising a sum of the second individual currents are equal.

18. The system of claim 15 , wherein said activating the IR light source to selectively illuminate the section of the scene with IR light comprises selecting a group of IR LEDs in the array and driving each of the IR LEDs in the group with a second individual current less than the first individual current, a first total current comprising a sum of the first individual currents being greater than a second total current comprising a sum of the second individual currents.

19. The system of claim 14 , wherein said capturing the first image of the scene occurs under ambient lighting.

20. The system of claim 19 , wherein the instructions that, when executed by the microprocessor, cause the system to, prior to said activating the IR light source to selectively illuminate the section of the scene with IR light:

activate the IR light source to uniformly illuminate the scene with IR light capturing an intermediate image of the scene under uniform IR lighting from the IR light source;

detect the face in the intermediate image; and

calculate the amount of IR light to illuminate the section of the scene based on brightness values of the face in the first and the intermediate images.

21. The system of claim 20 , wherein said calculating the amount of IR light to illuminate the section of the scene is based on a difference between corresponding brightness value of the face from the first image and the intermediate image.

22. A system, comprising:

a camera having a field of view;

an infrared (IR) light source comprising an array of IR light emitting diodes (LEDs);

nonvolatile memory storing instructions for a face detection and recognition application; and

a microprocessor encoded with instructions that, when executed by the microprocessor, cause the system to:

capture, with the camera, a first image of a scene;

detect a face in a section of the scene from the first image;

create a three dimensional profile of the face;

activate the IR light source to uniformly illuminate the scene with uniform IR lighting;

capture an intermediate image of the scene under the uniform IR lighting from the IR light source;

detect the face in the intermediate image;

calculate an amount of IR light to illuminate the section of the scene is based brightness values of the face in the first and the intermediate images and the three dimensional profile of the face;

activate the IR light source to selectively illuminate the section of the scene with the amount of IR light;

capture, with the camera, a second image of the scene under selective IR lighting from the IR light source;

detect the face in the second image; and

identify a person based on the face in the second image.

23. The system of claim 22 , wherein a first LED in the array emits IR light of a different emission spectrum than IR light emitted by a second LED in the array.

24. The system of claim 22 , wherein the array of IR LEDs is a first array of IR LEDs, the IR light source further comprises a second array of IR LEDs, the first and the second arrays of IR LEDs illuminate different portions of the face.

25. The system of claim 24 , wherein a first LED in the array emits IR light of a different emission spectrum than IR light emitted by a second LED in the array.

26. The system of claim 22 , wherein said identifying the person based on the face in the second image comprises comparing the face in the second image against facial images in a database and finding a match.

27. A non-transitory, computer-readable storage medium encoded with instructions executable by a microprocessor to selectively illuminate a scene, the instructions, when executed by the microprocessor, cause performance of operations, the operations comprising:

capturing a first image of a scene;

detecting a face in a section of the scene from the first image;

creating a three dimensional profile of the face;

calculating an amount of infrared (IR) light to illuminate the section of the scene based on the first image and the three dimensional profile of the face;

activating an IR light source to selectively illuminate the section of the scene with the amount of IR light, the IR light source comprising an array of IR light emitting diodes (LEDs);

capturing a second image of the scene under selective IR lighting from the IR light source;

detecting the face in the second image; and

identifying a person based on the face in the second image.