Face detection computer program product for redeye correction

• US 20030161506A1
• Filed: 02/25/2002
• Published: 08/28/2003
• Est. Priority Date: 02/25/2002
• Status: Abandoned Application

• Current Assignee: Eastman Kodak Company
• Original Assignee: Eastman Kodak Company
• Inventors: Schildkraut, Jay S., Velazquez, Belimar
• Application Number:
  US10/082,458
• Publication Number:
  US 20030161506A1
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/179 metadata assisted face recognition
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A method of calculating the size of a human face in a digital image, includes the steps of: providing image capture metadata associated with a digital image that includes the image of a human face, the metadata including subject distance, focal length, focal plane resolution; providing a standard face dimension; and calculating the size of a human face at the focal plane using the metadata and the standard face size.

Claims

1. A method of calculating the size of a human face in a digital image, comprising the steps of:

a) providing image capture metadata associated with a digital image that includes the image of a human face, the metadata including subject distance, focal length, focal plane resolution;

b) providing a standard face dimension; and

c) calculating the size of a human face at the focal plane using the metadata and the standard face size.

4. The method of claim 1, wherein the digital image is captured by a digital camera that includes means for appending the metadata to a digital image file in the camera.

9. A computer program product for performing the method of claim 1.

2. A method of detecting a face in an image, comprising the steps of:

a) detecting a skin colored region in a digital image;

b) calculating the expected size of a human face in the digital image by,

i) providing image capture metadata associated with a digital image that includes the image of a human face including subject distance, focal length, focal plane resolution,

ii) providing a standard face dimension, and

iii) calculating the size of a human face using the metadata and the standard face dimension; and

c) comparing the size of the detected skin color region with the calculated size of a human face to determine if the skin color region is a human face.

3. The method claimed in claim 2, further comprising the step of evaluating a detected face region for red-eye defects.

5. The method of claim 2, wherein the digital image is captured by a digital camera that includes means for appending the metadata to a digital image file in the camera.

10. A computer program product for performing the method of claim 2.

6. A method of calculating the expected size range of human faces in a digital image, comprising the steps of:

a) providing image capture metadata associated with a digital image that includes the image of a human face, the metadata including subject distance, focal length, focal plane resolution and f-number;

b) providing a standard face dimension;

c) calculating the depth of field using the metadata; and

d) calculating the range of expected face sizes in the digital image based on the depth of field calculation and standard face size.

11. A computer program product for performing the method of claim 6.

7. A method of detecting faces in an image, comprising the steps of:

a) detecting a skin colored region in a digital image;

b) calculating the expected size of a human face in the digital image by,

i) providing image capture metadata associated with a digital image that includes the image of a human face, the metadata including subject distance, focal length, focal plane resolution and f-number,

ii) providing a standard face dimension,

iii) calculating the depth of field with the metadata, and

iv) calculating the range of expected face sizes in a digital image based on the depth of field calculation and standard face size.

8. The method of claim 7, further comprising the step of evaluating the region for eye color defects.

12. A computer program product for performing the method of claim 7.