AUTO FOCUS SPEED ENHANCEMENT USING OBJECT RECOGNITION AND RESOLUTION

• US 20100208091A1
• Filed: 02/19/2009
• Published: 08/19/2010
• Est. Priority Date: 02/19/2009
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Chang, E-Cheng
• Granted Patent: US 8,233,078 B2
• Time in Patent Office: Days
• US Class Current: 348/222.100
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/67 Focus control based on electronic image sensor signals

Abstract

Autofocus operations in a digital camera are described. In one embodiment, a processor detects a face in an image captured by the camera, and calculates the size of the face. It selects from amongst a number of previously stored face sizes, one that is closest to the calculated face size. It retrieves a previously stored lens focus position that is associated with the selected, previously stored face size. It signals a moveable lens system of the digital camera to move to a final focus position given by the retrieved, previously stored lens focus position. Other embodiments are also described and claimed.

Claims

1. An autofocus digital camera comprising:

a moveable lens system;

an image sensor coupled with the moveable lens system;

a processor coupled with the image sensor; and

data storage coupled with the processor and having stored therein a table, the table having a plurality of entries, each entry including a stored face size and a corresponding stored lens focus position,

wherein the processor is to perform an autofocus operation when taking a picture, wherein in the autofocus operation, the processor is to detect a face in an image captured by the image sensor, calculate size of the face, select a stored lens focus position from the table based on the calculated face size, and signal the moveable lens system to move to the selected stored lens focus position,

and wherein the processor is to signal the image sensor to take the picture once the moveable lens system is at the selected stored lens focus position.

2. The apparatus of claim 1, wherein the stored face size is given by a percentage of field of view taken up by the detected face.

3. The apparatus of claim 1 wherein the memory stores a second table of stored face sizes and corresponding stored lens focus positions, the second table being for an angle of view that is different from that of the first table, the processor to perform the autofocus operation by further determining a current angle of view and selecting a table from among the first table and the second table based on the current angle of view.

4. The apparatus of claim 1, wherein the processor comprises:

a face detector to detect a face in an image captured by the image sensor; and

a measurement unit to measure a size of the detected face in the image.

5. The apparatus of claim 4 wherein the processor comprises:

a calculation unit to determine a percentage of a field of view covered by the face, based on the measured size of the face in the image.

6. The apparatus of claim 1, wherein the storage stores machine-code that programs the processor to perform the autofocus operation.

7. A method for performing an autofocus operation in a digital camera, comprising:

capturing an image of a scene;

detecting a face in the captured image;

calculating size of the detected face;

selecting from amongst a plurality of previously stored face sizes one that is closest to the calculated face size;

retrieving a previously stored lens focus position that is associated with the selected one of the previously stored face sizes; and

signaling a moveable lens system of the digital camera to move to a final focus position given by the retrieved, previously stored lens focus position.

8. The method of claim 7 further comprising:

determining angle of view used when capturing the image; and

selecting a group of previously stored face sizes and associated lens focus positions, from amongst a plurality of such groups, that are associated with the determined angle of view.

9. The method of claim 8 further comprising:

calculating field of view used when capturing the image, and wherein

calculating the size of the detected face comprises measuring the area of the detected face in relation to the calculated field of view.

10. The method of claim 9 wherein calculating the size of the detected face comprises calculating a ratio of the measured area of the detected face to the calculated field of view.

11. The method of claim 8, wherein calculating the size of the detected face comprises measuring dimensions of the smallest rectangle or square in which the detected face fits.

12. The method of claim 8, wherein the stored face size is given by a percentage of a field of view covered by the face in the captured picture.

13. The method of claim 12, wherein the memory stores instructions that program the processor to perform the autofocus operation.

14. An article of manufacture for use when performing an autofocus method using a moveable lens system, comprising:

storage that stores a first table having a plurality of entries, each entry containing a different face size and an associated lens focus position for the moveable lens system,

wherein the storage stores machine code which programs a processor to select one of the entries in the first table based on a calculated face size, retrieve the associated lens focus position from the selected entry, and signal the moveable lens system to move to a final focus position given by the retrieved lens focus position.

15. The article of manufacture of claim 14, wherein the storage stores further machine code that programs the processor to take a picture using the final focus position.

16. The article of manufacture of claim 14, wherein the storage stores a second table having a plurality of entries each containing a different face size and an associated lens focus position for the moveable lens system, the second table being associated with a different angle of view than the first table.

17. A method for building a look up table, comprising:

a) capturing an image of a face using a moveable lens system that is set to a lens focus position;

b) evaluating sharpness of the captured face in the image;

c) when the sharpness is sufficient, storing the lens focus position in a first look up table and storing size of the captured face in the look up table in association with the stored lens focus position;

d) when the sharpness is not sufficient, signaling the lens system to move to a different lens focus position and repeating a)-b) with the moveable lens system set to the different lens focus position; and

e) repeating c)-d) at least once.

18. The method of claim 17, further comprising:

repeating a)-e) with the moveable lens system set to a different angle of view, to build a second look up table associated with said different angle of view; and

storing the first and second look up tables in a digital camera.

19. The method of claim 17, wherein evaluating sharpness of the captured face in the image comprises:

performing an automatic sharpness evaluation process upon the captured image.

20. The method of claim 17, further comprising:

detecting the face in the captured image and calculating the size of the face, by analyzing the captured image.

21. The method of claim 20, wherein calculating the size of the face comprises:

measuring dimensions of the smallest rectangle or square in which the detected face fits.

22. The method of claim 20, wherein calculating the size of the face comprises:

calculating a ratio of a measured area of the detected face to a field of view.