Detecting red eye filter and apparatus using meta-data
First Claim
1. A method of detecting and correcting an eye defect within a digital image that has been acquired with a cell phone equipped with a digital camera and that comprises a multiplicity of pixels indicative of luminance and color, the multiplicity of pixels forming various shapes within the image, the method comprising:
- acquiring with said cell phone equipped with said digital camera said digital image including said multiplicity of pixels indicative of luminance and color;
detecting a candidate eye defect region based on color or shape or both within the digital image;
analyzing meta-data information including image acquisition device-specific information including image acquisition device-specific information, including f-stop, aperture, exposure, gain, white balance or color transformation, or focusing distance information at a time of acquisition, or combinations thereof;
analyzing anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof;
utilizing said meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and
filtering said candidate eye defect region from the digital image.
5 Assignments
0 Petitions
Accused Products
Abstract
A method of filtering a red-eye phenomenon from an acquired digital image including a multiplicity of pixels indicative of color, the pixels forming various shapes of the image, includes analyzing meta-data information, determining one or more regions within the digital image suspected as including red eye artifact, and determining, based at least in part on the meta-data analysis, whether the regions are actual red eye artifact. The meta-data information may include information describing conditions under which the image was acquired, captured and/or digitized, acquisition device-specific information, and film information.
53 Citations
24 Claims
-
1. A method of detecting and correcting an eye defect within a digital image that has been acquired with a cell phone equipped with a digital camera and that comprises a multiplicity of pixels indicative of luminance and color, the multiplicity of pixels forming various shapes within the image, the method comprising:
-
acquiring with said cell phone equipped with said digital camera said digital image including said multiplicity of pixels indicative of luminance and color; detecting a candidate eye defect region based on color or shape or both within the digital image; analyzing meta-data information including image acquisition device-specific information including image acquisition device-specific information, including f-stop, aperture, exposure, gain, white balance or color transformation, or focusing distance information at a time of acquisition, or combinations thereof; analyzing anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof; utilizing said meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and filtering said candidate eye defect region from the digital image. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A cell phone equipped with a digital camera, comprising:
-
optics and a sensor for acquiring digital images, a processor and a red eye filter configured to detect a candidate eye defect region based on color or shape or both within a digital image acquired by said cell phone; and wherein the red eye filter is configured to analyze meta-data information including image acquisition device-specific information including f-stop, aperture, exposure, gain, white balance, color transformation, focusing distance information at a time of acquisition, or combinations thereof; and wherein the red eye filter is further configured to analyze anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof; and wherein said red eye filter is further configured to utilize said meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and
to filter said candidate eye defect region from the digital image. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. One or more non-transitory media configured to perform on a cell phone equipped with a digital camera a method of detecting and correcting an eye defect within a digital image that was acquired with said cell phone equipped with said digital camera and that comprises a multiplicity of pixels indicative of luminance and color, the multiplicity of pixels forming various shapes within the image, wherein the method comprises:
-
detecting a candidate eye defect region based on color or shape or both within said digital image acquired with said cell phone equipped with said digital camera; analyzing meta-data information including image acquisition device-specific information, including f-stop, aperture, exposure, gain, white balance, color transformation, or focusing distance information at a time of acquisition, or combinations thereof; analyzing anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof; utilizing meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and filtering said candidate eye defect region from the digital image. - View Dependent Claims (18, 19, 20, 21, 22, 23, 24)
-
Specification