Method of processing images captured by digital camera to reduce distortion

• US 8,013,905 B2
• Filed: 04/23/2010
• Issued: 09/06/2011
• Est. Priority Date: 07/15/1997
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Silverbrook Research Pty Limited
• Inventors: Silverbrook, Kia
• Primary Examiner(s): Giles, Nicholas G
• Application Number:
  US12/765,861
• Publication Number:
  US 20100201846A1
• Time in Patent Office: 501 Days
• Field of Search: 348/222.1, 348/239, 348/223.1, 348/228.1, 348/241, 382/118
• US Class Current: 348/222.1
• CPC Class Codes: B41J 2/16585 for paper-width or non-reciprocating print heads
• CPC Class Codes: B41J 2/17513 Inner structure
• CPC Class Codes: B41J 2/17596 Ink pumps, ink valves
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 23/00 Cameras or camera modules comprising electronic image sensors; Control thereof
• CPC Class Codes: H04N 5/2628 Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation

Abstract

A method of processing, in a digital camera, an image captured by the camera is provided, which includes locating faces within the captured image by detecting regions of contiguous color which map a hue, saturation and value of the range of human face colors and passing the detected regions through heuristic tests which produce a resulting probability of a face being present in the image, locating eyes of the located faces, and determining if the captured image of the located eyes has been modified by the act of capturing the image. If the image has been modified any unwanted distortions of the located eyes are located in the captured image that have occurred as a result of the act of capturing the image, and the captured image is modified to at least reduce the effect of the unwanted distortions and to produce a modified image.

Claims

1. A method of processing, in a digital camera, an image captured by the camera, the method including the steps of:

locating faces within the captured image by detecting regions of contiguous color which map a hue, saturation and value of the range of human face colors and passing the detected regions through heuristic tests which produce a resulting probability of a face being present in the image;

locating eyes of the located faces; and

determining if the captured image of the located eyes has been modified by the act of capturing the image, and if so,

locating any unwanted distortions of the located eyes in the captured image that have occurred as a result of the act of capturing the image, and

modifying the captured image to at least reduce the effect of the unwanted distortions and to produce a modified image.

2. The method of claim 1 wherein the determining step includes determining if a flash was used in capturing the image.

3. The method of claim 1 wherein said unwanted distortions include “

red-eye”

effects.

4. The method of claim 1 wherein said unwanted distortions include reflections in the captured image.

5. The method of claim 1 wherein said unwanted distortions include modification of the colors captured.

6. The method of claim 1 further including adding at least one predetermined image to the captured image.

7. The method of claim 1 wherein, if it is determined that the captured image has not been modified by the act of capturing the image, adding at least one predetermined image to the captured image.

8. The method of claim 1 including storing at least one of the modified image and the captured image.

9. The method of claim 1 including displaying at least one of the modified image and the captured image on a display of the camera.